# ECC changelog

> The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

- Vendor: affaan-m
- Category: AI
- Official site: https://ecc.tools
- Tracked by: What's New (https://whatsnew.fyi/product/ecc)
- Harvested from: GitHub (affaan-m/ECC)
- Entries below: 11 (newest first)

What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog.

## Releases

### v2.1.0 — ECC 2.1.0: Plan Canvas, Kimi Harness, and Self-Hosted Compute

- Date: 2026-07-27
- Version: v2.1.0
- Original notes: https://github.com/affaan-m/ECC/releases/tag/v2.1.0
- Permalink: https://whatsnew.fyi/product/ecc/releases/v2.1.0

- **added** — Plan Canvas feature to review agent plans visually in the browser with the ability to click elements, select text, attach numbered annotations, and approve or request changes
- **added** — Kimi harness with direct installation into Kimi Code via --target kimi flag
- **added** — ecc ito find command as an opt-in bridge to Itô CLI for GPU capacity discovery
- **added** — Hermes and OpenClaw install targets
- **added** — Codex ECC navigation guide to find the right skill and command surface from inside Codex
- **added** — GateGuard path exemptions via GATEGUARD_EXEMPT_GLOBS environment variable
- **added** — Configurable instinct injection with count and confidence threshold settings
- **changed** — PostToolUse hooks consolidated into sync and async dispatchers with fewer processes per tool call
- **changed** — Plan Canvas renders Mermaid diagrams, tables, and task lists natively with live-reload on file edits
- **changed** — Pre-commit secret scan now catches Anthropic API keys with sk-ant- prefix
- **fixed** — Community fixes across OpenCode, Windows, bun lockfiles, the dashboard, and project detection
- **security** — Supply-chain hardening with strict vetting of the installer runtime

#### ECC 2.1.0: Plan Canvas, Kimi Harness, and Self-Hosted Compute

ECC 2.1 turns plan review into a visual loop and opens the harness to self-hosted models. Plan Canvas lets you review agent plans in the browser. Point at the part you mean instead of retyping it in chat. A new Kimi Code install target and a verified Itô GPU path make ECC + open-source models a first-class setup, backed by our public sponsors: Moonshot AI (Kimi), Itô, and Atlas Cloud.

##### Plan Canvas: review plans by pointing, not retyping

![Plan Canvas demo: reviewing an ECC plan, attaching an annotation, chatting with the agent, and approving the plan](https://raw.githubusercontent.com/affaan-m/ECC/main/docs/releases/2.1.0/assets/ecc-plan-canvas-demo.gif)

[Download the MP4 demo](https://raw.githubusercontent.com/affaan-m/ECC/main/docs/releases/2.1.0/assets/ecc-plan-canvas-demo.mp4)

`/plan` ends with a confirm gate, and until now that review was a wall of markdown in the terminal. Now the agent opens the plan in a loopback-only browser canvas:

- Click elements or select text to attach numbered annotations
- Chat with the agent from a side rail while it works in the terminal
- **Approve plan** / **Request changes** buttons map directly onto `/plan`'s CONFIRM gate
- Mermaid diagrams, tables, and task lists render natively; file edits live-reload the page
- Model- and harness-agnostic: a plain CLI + JSON protocol (`ecc-plan-canvas`), no Claude-only dependency

##### Kimi harness: Moonshot AI partnership

ECC now installs directly into [Kimi Code](https://moonshotai.github.io/kimi-cli/) (`--target kimi`). Kimi Code discovers the installed `.kimi/AGENTS.md` instructions and `.kimi/skills/` workflows natively:

```bash
bash ./install.sh --target kimi --profile minimal
npx ecc doctor --target kimi
kimi
```

##### Self-host on Itô GPUs

Run ECC against any self-hosted open-source model. If you need GPU capacity, [Itô](https://compute.itomarkets.com) is ECC's preferred compute sponsor. The integration shipped guarded end to end:

- `ecc ito find`: opt-in bridge to the canonical Itô CLI that submits a live, authenticated RFQ (it does not reserve capacity)
- Guarded live node qualification and read-only compute handoff
- Credential-bearing CLI shims are rejected outright

The sponsorship link itself is passive: it does not invoke an RFQ, reserve capacity, provision compute, or configure serving. Managed inference through Itô is not live yet. Any GPU provider works, and ECC stays provider-agnostic.

##### Partners

[Moonshot AI (Kimi)](https://www.moonshot.ai), [Itô](https://compute.itomarkets.com), and [Atlas Cloud](https://www.atlascloud.ai) are now public sponsors of ECC. The README documents a recommended self-host path: Itô for GPU capacity, a Kimi checkpoint served behind a compatible endpoint, then Kimi Code + ECC on top. Each choice remains separate and swappable.

##### Also in 2.1

- **Hermes and OpenClaw install targets**: two more harnesses join Claude Code, Codex, OpenCode, Cursor, Gemini, Zed, Copilot, and Kimi
- **Codex ECC navigation guide**: find the right skill/command surface from inside Codex
- **GateGuard path exemptions** (`GATEGUARD_EXEMPT_GLOBS`) and configurable instinct injection (count + confidence threshold)
- **PostToolUse hooks consolidated** into sync/async dispatchers, with fewer processes per tool call
- **Supply-chain hardening**: the installer runtime passes strict vetting, and the pre-commit secret scan now catches Anthropic API keys (`sk-ant-...`)
- A long tail of community fixes across OpenCode, Windows, bun lockfiles, the dashboard, and project detection

The catalog now stands at **67 agents, 281 skills, and 94 command shims** (2.0.0 shipped 64/261/84), plus hooks, rules, memory, continuous learning, and AgentShield.

##### Install or upgrade

```text
/plugin marketplace add https://github.com/affaan-m/ECC
/plugin install ecc@ecc
```

Existing installs: `/plugin update ecc`

##### Community

Join the ECC community for releas

_[Truncated at 4000 characters — full notes: https://github.com/affaan-m/ECC/releases/tag/v2.1.0]_

### v2.0.0 — ECC 2.0.0 — The Agent Harness Operating System

- Date: 2026-06-10
- Version: v2.0.0
- Original notes: https://github.com/affaan-m/ECC/releases/tag/v2.0.0
- Permalink: https://whatsnew.fyi/product/ecc/releases/v2.0.0

- **added** — 261 public skills across coding, research, security, media, enterprise ops, and agent workflows
- **added** — 64 agents and 84 commands
- **added** — Control-pane substrate with harness-neutral session adapters covering Claude Code, Codex, OpenCode, and dmux
- **added** — MCP inventory with fragmentation/drift detection and secret redaction
- **added** — Worktree-lifecycle service for deterministic merge-conflict prediction and safe garbage collection for parallel agent worktrees
- **added** — Orchestrator skill family with dynamic workflow team orchestration for multi-agent fan-out
- **added** — Rollout-derived optimization pack including parallel-execution-optimizer, benchmark-optimization-loop, data-throughput-accelerator, latency-critical-systems, and recursive-decision-ledger
- **fixed** — Plugin hooks were silently no-ops on Node 21+ due to require.main dependency under node -e
- **fixed** — Windows reliability with CLAUDE_PLUGIN_ROOT normalization, stdin prompt passing, and symlink/chmod test guards
- **fixed** — Security issue where curl credentials could be exposed in argv
- **fixed** — Session-end $-sequence corruption in sessions
- **fixed** — Project-detect boundary matching correctness
- **fixed** — Install manifest gaps
- **fixed** — Legacy shim truncation
- **changed** — Single-connector MCP default policy now includes only chrome-devtools with six other connectors moved to opt-in
- **removed** — Six MCP connectors retired from default set to opt-in after June 2026 audit
- **changed** — Smaller OpenCode surface in default install
- **removed** — rules/zh removed from default install

ECC 2.0.0 is the stable graduation of the 2.0 line: ECC as a cross-harness operating system for agentic work. Claude Code stays first-class; Codex, OpenCode, Cursor, Gemini, Zed, and terminal-only workflows share the same skills, rules, hooks, MCP conventions, release gates, and operator workflows. This is the months-in-the-making release the rc.1 candidate was building toward.

##### The control pane (early build)

![ECC Control Pane — sessions, metrics, and the work-items board](https://github.com/affaan-m/ECC/releases/download/v2.0.0/ecc-pane-1.png)

![Operator column — knowledge recall, connectors, and runnable agent actions](https://github.com/affaan-m/ECC/releases/download/v2.0.0/ecc-pane-2.png)

The ECC 2.0 operating surface, running locally (`node scripts/control-pane.js`): operator recall search, live session metrics, a work-items board with ready/running/blocked/done lanes, and an operator column that drives knowledge sync/recall, graph backfill, and the TUI. The session adapters and MCP inventory below feed this board. Build-in-public continues in the Discord #control-pane channel.

##### What is new

- **261 public skills** across coding, research, security, media, enterprise ops, and agent workflows (rc.1 shipped 243) — plus 64 agents and 84 commands.
- **The control-pane substrate** — the foundation of the ECC 2.0 operating surface:
  - harness-neutral session adapters (`ecc.session.v1`) covering Claude Code, Codex, OpenCode, and dmux — one schema for "which agent is where, doing what"
  - MCP inventory (`ecc.mcp.v1`) — one normalized view of every MCP server config across harnesses, with fragmentation/drift detection and secret redaction (it caught a real arg-carried key leak during development)
  - worktree-lifecycle service — deterministic merge-conflict prediction and safe GC for parallel agent worktrees
- **`orch-*` orchestrator skill family** plus dynamic workflow team orchestration — multi-agent fan-out as a first-class surface.
- **Single-connector MCP default policy** — the default set is now exactly one connector (`chrome-devtools`); the other six retired to opt-in after a June 2026 audit. Policy + per-connector rationale: `docs/MCP-CONNECTOR-POLICY.md`.
- **Rollout-derived optimization pack**: `parallel-execution-optimizer`, `benchmark-optimization-loop`, `data-throughput-accelerator`, `latency-critical-systems`, `recursive-decision-ledger`.

##### Hardening since rc.1 (~30 PRs)

- **Plugin hooks were silently no-ops on Node 21+** (#2184) — the hook runner depended on `require.main` under `node -e`; every plugin hook exited cleanly without running. If you are on Node 21+, update now.
- Windows reliability: `CLAUDE_PLUGIN_ROOT` normalization (#2139), stdin prompt passing (#2174), symlink/chmod test guards (#2171, #2176).
- Security: curl credentials out of argv (#2175), gateguard destructive-checkout gating (#2158) + env knobs (#2161), advisory intake hardening.
- Correctness: session-end `$`-sequence corruption (#2180), project-detect boundary matching (#2181), install manifest gaps (#2172), legacy shim truncation (#2167).
- Slimmer defaults: smaller OpenCode surface (#2140), `rules/zh` out of the default install (#2170).

##### The ECC Discord is live

<https://discord.gg/36yGMHGFbR>

- **#announcements** — releases auto-post and pin there (this very release was announced by the workflow shipped in it, #2201)
- **#pr-and-issues** — live feed of every PR, issue, and release from this repo
- **the ECC bot** (built in this release, dependency-free gateway client) answers in-server:
  - `/skill name:<query>` — look up any of the 261 skills
  - `/docs query:<terms>` — search the docs
  - `/release` — latest release
  - `/ecc`, `/help`
- **#feedback / #feature-requests** — read directly by the maintainer; **#control-pane** — build-in-public on the ECC 2.0 operating surface
- 16 channels, 6 categories, community roles for Contributors, ECC Tools users, and AgentShield

_[Truncated at 4000 characters — full notes: https://github.com/affaan-m/ECC/releases/tag/v2.0.0]_

### v2.0.0-rc.1

- Date: 2026-05-25
- Version: v2.0.0-rc.1
- Original notes: https://github.com/affaan-m/ECC/releases/tag/v2.0.0-rc.1
- Permalink: https://whatsnew.fyi/product/ecc/releases/v2.0.0-rc.1
- Labels: Pre-release

- **added** — 243 public skills packaged across coding, research, security, media, enterprise ops, and agent workflows
- **added** — Rollout-derived optimization pack for agents that need measured speedups instead of one-shot prompting
- **added** — Public teaser Itô prediction-market skill pack for read-only research, basket comparison, oracle-style market intelligence, and risk review
- **added** — AgentShield and supply-chain follow-up surfaces
- **added** — Cross-harness package surfaces for Claude Code, Codex, OpenCode, Cursor, Gemini, Zed, and terminal workflows
- **added** — Release-readiness gates for preview packs, public-action approvals, release URL ledgers, operator readiness, discussion state, Linear roadmap coverage, and supply-chain checks
- **added** — parallel-execution-optimizer skill that splits work into safe parallel lanes, separate worktrees, concurrent reads, and mergeable outputs
- **added** — benchmark-optimization-loop skill that turns vague speed goals into measured variants, baselines, promotion gates, and rollback notes
- **added** — data-throughput-accelerator skill that pushes large scans and corpus work into indexed, checkpointed, manifest-driven pipelines
- **added** — latency-critical-systems skill that profiles p50, p95, queue time, cache hit rate, cold starts, and freshness before changing runtime paths
- **added** — recursive-decision-ledger skill that converts repetitive rollout prompting into reusable decision ledgers with prior winners and explicit promotion criteria
- **changed** — ECC expanded from Claude Code config pack to a cross-harness operating system that shares the same skills, rules, hooks, MCP conventions, release gates, and operator workflows across multiple execution surfaces

#### ECC 2.0.0-rc.1

ECC 2.0.0-rc.1 is the first release-candidate surface for ECC as a cross-harness operating system for agentic work.

Claude Code remains a first-class target. Codex, OpenCode, Cursor, Gemini, Zed, and terminal-only workflows are now treated as execution surfaces that can share the same skills, rules, hooks, MCP conventions, release gates, and operator workflows.

##### What is new

- 243 public skills packaged across coding, research, security, media, enterprise ops, and agent workflows.
- A rollout-derived optimization pack for agents that need measured speedups instead of one-shot prompting.
- A public teaser Itô prediction-market skill pack for read-only research, basket comparison, oracle-style market intelligence, and risk review. Itô API access stays gated and separate from ECC Tools billing.
- AgentShield and supply-chain follow-up surfaces after the Mini Shai-Hulud/TanStack campaign work.
- Cross-harness package surfaces for Claude Code, Codex, OpenCode, Cursor, Gemini, Zed, and terminal workflows.
- Release-readiness gates for preview packs, public-action approvals, release URL ledgers, operator readiness, discussion state, Linear roadmap coverage, and supply-chain checks.

##### New optimization skills

- `parallel-execution-optimizer`: splits work into safe parallel lanes, separate worktrees, concurrent reads, and mergeable outputs.
- `benchmark-optimization-loop`: turns vague speed goals into measured variants, baselines, promotion gates, and rollback notes.
- `data-throughput-accelerator`: pushes large scans and corpus work into indexed, checkpointed, manifest-driven pipelines.
- `latency-critical-systems`: profiles p50, p95, queue time, cache hit rate, cold starts, and freshness before changing runtime paths.
- `recursive-decision-ledger`: converts repetitive rollout prompting into reusable decision ledgers with prior winners and explicit promotion criteria.

##### Why this matters

ECC is no longer just a Claude Code config pack. The release candidate packages the reusable layer underneath agent work: skills, hooks, rules, MCP conventions, command surfaces, test gates, and operator discipline that can move across harnesses.

The goal is simple: stop rewriting the same prompts, stop relying on fragile local habits, and turn working agent behavior into portable infrastructure.

##### Download

- Release tarball: https://github.com/affaan-m/ECC/releases/download/v2.0.0-rc.1/ecc-universal-2.0.0-rc.1.tgz
- Full changelog: https://github.com/affaan-m/ECC/compare/v1.10.0...v2.0.0-rc.1

Additional registry and directory surfaces will follow the remaining publication gates. For this RC, the GitHub prerelease and tarball are the public packaged artifact.

##### Verification

This release candidate passed the local validation gate used for the final packaging work:

- `npm test`: 2568 passing
- `npm run lint`: passing
- `node scripts/ci/validate-skills.js`: 243 skills
- `node scripts/ci/validate-install-manifests.js`: 31 modules, 75 components, 6 profiles
- `node scripts/ci/validate-no-personal-paths.js`: passing
- `npm run preview-pack:smoke -- --format json`: passing
- `npm pack --dry-run`: includes the new optimization and Itô skill packs

##### RC boundary

This is a release candidate, not the final GA claim. Secrets, private operator state, OAuth tokens, personal datasets, and unsanitized local automations are not part of the public package.

### v1.10.0 — ECC v1.10.0 — Surface Refresh, Operator Workflows, and ECC 2.0 Alpha

- Date: 2026-04-05
- Version: v1.10.0
- Original notes: https://github.com/affaan-m/ECC/releases/tag/v1.10.0
- Permalink: https://whatsnew.fyi/product/ecc/releases/v1.10.0

##### ECC 1.10.0

###### What This Release Focuses On
- Harness reliability and cross-platform compatibility
- Eval-driven quality improvements
- Better workflow and operator ergonomics

###### Package Notes
- npm package: `ecc-universal`
- Claude marketplace/plugin identifier: `everything-claude-code@everything-claude-code`


<!-- Release notes generated using configuration in .github/release.yml at v1.10.0 -->


##### New Contributors
* @tupe12334 made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/649
* @ihimanss made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/548
* @macstarosielec made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/716
* @pvgomes made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/736
* @berkcangumusisik made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/744
* @nehaaprasad made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/748
* @massimotodaro made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/729
* @fischperson0000000 made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/760
* @tae1344 made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/956
* @Lidang-Jiang made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/977
* @KT-lcz made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/931
* @seancheick made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/970
* @dagecko made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/987
* @Infiniteyieldai made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/986
* @senoldogann made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/960
* @anuragg-saxenaa made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/952
* @Ashwinhegde19 made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/950
* @ToniDonDoni made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/896
* @xingzihai made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/929
* @haibindev made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/911
* @techiro made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/897
* @Yumerain made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/855
* @sliver2er made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/858
* @danielpetrica made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/923
* @likzn made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/985
* @694344851 made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/818
* @sreedhargs89 made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/959
* @drkeyurpatel-wq made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/955
* @up2itnow0822 made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/893
* @Xabilimon1 made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/920
* @ohashi-mizuki made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/1004
* @AndriyKalashnykov made their first contribution in https://github.com/affaan-m/everything-claude-code/pull/1007
* @singularityjason made their first contribution in https://github.com/affaan-m/everything-claude-cod

_[Truncated at 4000 characters — full notes: https://github.com/affaan-m/ECC/releases/tag/v1.10.0]_

### v1.9.0 — v1.9.0 — Selective Install, ECC Tools Pro, 12 Language Ecosystems

- Date: 2026-03-21
- Version: v1.9.0
- Original notes: https://github.com/affaan-m/ECC/releases/tag/v1.9.0
- Permalink: https://whatsnew.fyi/product/ecc/releases/v1.9.0

- **added** — ECC Tools Pro tier with Stripe billing at $19/seat/month for private repo analysis with 50 analyses/month
- **added** — Selective install with --with and --without flags to install only specific agent and skill component families
- **added** — Nine new agents: typescript-reviewer, pytorch-build-resolver, java-build-resolver, java-reviewer, rust-reviewer, flutter-reviewer, harness-optimizer, kotlin-build-resolver, and kotlin-reviewer
- **added** — Fifteen new skills including pytorch-patterns, nuxt4-patterns, codebase-onboarding, architecture-decision-records, agent-eval, documentation-lookup, bun-runtime, and nextjs-turbopack
- **added** — Six new language rule packs for C#, Rust, Java, C++, Perl, and Flutter/Dart
- **added** — Agent description compression with lazy loading
- **added** — Skill inspection logic for recurring failure pattern detection
- **added** — Governance event capture hooks
- **added** — MCP health-check hook with auto-reconnect
- **added** — SQLite state store for session, skill, and decision tracking
- **added** — Session adapters for canonical snapshots
- **added** — AgentShield v1.4.0 with CVE database containing 25+ known MCP vulnerabilities
- **added** — MCP tool description poisoning detection with 5 new rules in AgentShield
- **added** — Continuous scanning with --watch mode in AgentShield
- **added** — Runtime monitoring daemon for tool calls in AgentShield
- **added** — Supply chain verification for MCP npm packages in AgentShield
- **added** — PR security gate with baseline comparison in AgentShield
- **added** — Organization-wide security policy enforcement in AgentShield
- **added** — CLAUDE.md filesystem permission check in AgentShield
- **added** — GitHub OAuth checkout flow for ECC Tools App
- **changed** — Codex sync now merges AGENTS.md instead of replacing it
- **changed** — ECC Tools App push cooldown increased to 7 days
- **fixed** — AgentShield false positive issue where deny rules and block hooks were flagged as threats
- **fixed** — Windows CI with all 38 matrix jobs now passing
- **fixed** — SessionStart ANSI escape code sanitization
- **fixed** — Observer memory explosion with throttling
- **fixed** — Catalog count validation
- **fixed** — Plugin root auto-detection fallback
- **fixed** — Analyzer quality improvements with 7 greptile findings fixed in ECC Tools App
- **changed** — Free tier remains at 10 analyses/month for public repos
- **changed** — ECC Tools App now includes duplicate PR prevention with idempotency
- **added** — Auto-analysis skip list for managed repos in ECC Tools App

##### Highlights

**ECC Tools Pro is live.** The GitHub App now has Stripe billing with a Pro tier ($19/seat/month) for private repo analysis, 50 analyses/month, and AgentShield-backed scanning. Free tier remains at 10 analyses/month for public repos. Install at [github.com/apps/ecc-tools](https://github.com/apps/ecc-tools), upgrade at [ecc.tools/pricing](https://ecc.tools/pricing).

**Selective install is here.** Install only what you need with `--with` and `--without` flags. `ecc install --profile developer --with lang:typescript --with agent:security-reviewer --without skill:continuous-learning`. Agent and skill component families are now in the install manifest.

**12 language ecosystems.** C#, Rust, Java, Kotlin, C++, Go, Python, TypeScript, Perl, PyTorch, Nuxt 4, and Flutter now have dedicated rules, agents, or skills.

**AgentShield v1.4.0 ships alongside.** False positive scanning fixed. CVE database with 25+ known MCP vulnerabilities. Supply chain verification. Runtime monitoring. Watch mode. PR security gate. Org-wide policy enforcement.

https://github.com/user-attachments/assets/eece2c76-7eb9-4865-a58b-f11247fd774e

##### What's New

###### Agents (28 total, +9 new)
- `typescript-reviewer` — TypeScript/JavaScript code review
- `pytorch-build-resolver` — PyTorch build error resolution
- `java-build-resolver` — Maven/Gradle build resolution
- `java-reviewer` — Java code review
- `rust-reviewer` — Rust code review
- `flutter-reviewer` — Flutter/Dart code review
- `harness-optimizer` — Cross-harness optimization
- `kotlin-build-resolver` — Kotlin build resolution
- `kotlin-reviewer` — Kotlin code review

###### Skills (116 total, +15 new)
- `pytorch-patterns` — PyTorch best practices
- `nuxt4-patterns` — Nuxt 4 frontend patterns
- `codebase-onboarding` — Onboarding new contributors
- `architecture-decision-records` — ADR workflow
- `agent-eval` — Head-to-head coding agent comparison
- `documentation-lookup` — Doc retrieval patterns
- `bun-runtime` — Bun runtime patterns
- `nextjs-turbopack` — Next.js Turbopack patterns
- Plus 7 more language-specific skills

###### Rules (6 new language packs)
- C# (coding-style, patterns, security, testing, hooks)
- Rust, Java, C++, Perl language rules
- Flutter/Dart rules

###### Infrastructure
- Selective install with `--with`/`--without` CLI flags
- Agent description compression with lazy loading
- Skill inspection logic for recurring failure pattern detection
- Governance event capture hooks
- MCP health-check hook with auto-reconnect
- SQLite state store for session/skill/decision tracking
- Session adapters for canonical snapshots
- Codex sync merges AGENTS.md instead of replacing

###### Bug Fixes
- Windows CI fully green (all 38 matrix jobs passing)
- SessionStart ANSI escape code sanitization
- Observer memory explosion with throttling
- Flaky observer bash test on Windows skipped
- Catalog count validation fixed
- Plugin root auto-detection fallback

###### ECC Tools App
- Stripe billing live (Pro $19/seat, Enterprise contact)
- GitHub OAuth checkout flow
- Analyzer quality improvements (7 greptile findings fixed)
- Duplicate PR prevention with idempotency
- Auto-analysis skip list for managed repos
- Push cooldown increased to 7 days

###### AgentShield (v1.4.0)
- False positive fix: deny rules and block hooks no longer flagged as threats
- CVE database with 25+ known MCP vulnerabilities
- MCP tool description poisoning detection (5 new rules)
- Continuous scanning with config drift detection (--watch mode)
- Runtime monitoring daemon for tool calls
- Supply chain verification for MCP npm packages
- PR security gate with baseline comparison
- Organization-wide security policy enforcement
- CLAUDE.md filesystem permission check
- 1,609 tests passing

##### Stats
- 219 commits since v1.8.0
- 30+ contributors
- 88K+ GitHub stars
- 1,540+ tests passing across all platforms

##### Install / Upgr

_[Truncated at 4000 characters — full notes: https://github.com/affaan-m/ECC/releases/tag/v1.9.0]_

### v1.8.0 — ECC v1.8.0 — Harness Performance & Cross-Platform Reliability

- Date: 2026-03-05
- Version: v1.8.0
- Original notes: https://github.com/affaan-m/ECC/releases/tag/v1.8.0
- Permalink: https://whatsnew.fyi/product/ecc/releases/v1.8.0

- **added** — Add /harness-audit command
- **added** — Add /loop-start command
- **added** — Add /loop-status command
- **added** — Add /quality-gate command
- **added** — Add /model-route command
- **added** — Add model routing to NanoClaw v2
- **added** — Add skill hot-load to NanoClaw v2
- **added** — Add session branch/search/export/compact/metrics to NanoClaw v2
- **added** — Add agent-harness-construction skill
- **added** — Add agentic-engineering skill
- **added** — Add ralphinho-rfc-pipeline skill
- **added** — Add ai-first-engineering skill
- **added** — Add enterprise-agent-ops skill
- **added** — Add nanoclaw-repl skill
- **added** — Add continuous-agent-loop skill
- **added** — Add harness-optimizer agent
- **added** — Add loop-operator agent
- **added** — Add ECC_HOOK_PROFILE environment variable with minimal, standard, or strict options
- **added** — Add ECC_DISABLED_HOOKS environment variable to disable comma-separated hook IDs
- **added** — Add explicit hook controls for safer configuration
- **fixed** — Fix SessionStart root resolution with robust fallback when plugin root env is missing
- **fixed** — Fix empty and partial session summary behavior by moving summary persistence to Stop lifecycle path
- **fixed** — Replace fragile inline one-liner hook commands with dedicated scripts for safer cross-platform behavior
- **fixed** — Improve Windows path handling for doc-warning and whitelist logic
- **fixed** — Harden observer behavior for non-interactive environments to reduce hang risk
- **changed** — Tighten behavior parity across Claude Code, Cursor, OpenCode, and Codex for hooks, commands, and skill execution semantics
- **changed** — Add OpenCode command mirrors for new harness command set
- **changed** — Improve Codex config and docs alignment for app and CLI workflows
- **deprecated** — Retain autonomous-loops for compatibility but discontinue in favor of continuous-agent-loop as canonical skill name

##### ECC v1.8.0: Harness Performance Release

v1.8.0 shifts ECC from "config bundle" to a practical **agent harness performance system**: more reliable hooks, stronger eval/quality controls, and tighter parity across Claude Code, Cursor, OpenCode, and Codex (macOS app + CLI).

https://github.com/user-attachments/assets/18f05e41-a49b-4126-9771-3df1e07cd7b7

###### What’s New

- **New harness commands**
  - `/harness-audit`
  - `/loop-start`
  - `/loop-status`
  - `/quality-gate`
  - `/model-route`
- **NanoClaw v2 upgrades**
  - Model routing
  - Skill hot-load
  - Session branch/search/export/compact/metrics
- **New harness skills and operators**
  - `agent-harness-construction`
  - `agentic-engineering`
  - `ralphinho-rfc-pipeline`
  - `ai-first-engineering`
  - `enterprise-agent-ops`
  - `nanoclaw-repl`
  - `continuous-agent-loop`
- **New agents**
  - `harness-optimizer`
  - `loop-operator`

###### Reliability and Hook Fixes

- Fixed SessionStart root resolution (robust fallback when plugin root env is missing).
- Fixed empty/partial session summary behavior by moving summary persistence to the Stop lifecycle path where transcript payload exists.
- Added explicit hook controls:
  - `ECC_HOOK_PROFILE=minimal|standard|strict`
  - `ECC_DISABLED_HOOKS=comma,separated,ids`
- Replaced fragile inline one-liner hook commands with dedicated scripts for safer cross-platform behavior.
- Improved Windows path handling for doc-warning/whitelist logic.
- Hardened observer behavior for non-interactive environments to reduce hang risk.

###### Cross-Harness Parity

- Claude Code, Cursor, OpenCode, and Codex now share tighter behavior around hooks, commands, and skill execution semantics.
- OpenCode command mirrors added for the new harness command set.
- Codex config/docs alignment improved for both app and CLI workflows.

###### Compatibility Notes

- `autonomous-loops` is retained for compatibility in this release.
- `continuous-agent-loop` is now the canonical skill name.

###### Upgrade Path

1. Pull latest and reinstall/update ECC.
2. Run `/harness-audit` to baseline reliability and risk.
3. Use `/quality-gate . --strict` on active repos.
4. If needed, tune hooks with `ECC_HOOK_PROFILE` and `ECC_DISABLED_HOOKS`.

###### Credits

- frontend / marketing slides skill inspired by [@zarazhangrui](https://github.com/zarazhangrui)
- continuous learning skill - homunculus-inspired by [@humanplane](https://github.com/humanplane)
- slop guards inspired by [@alexfazio](https://github.com/alexfazio)

###### Supporting Docs

- Release notes source: `docs/releases/1.8.0/release-notes.md`
- Launch assets: `docs/releases/1.8.0/`

### v1.7.0 — ECC v1.7.0 — Cross-Platform Expansion & Presentation Builder

- Date: 2026-02-27
- Version: v1.7.0
- Original notes: https://github.com/affaan-m/ECC/releases/tag/v1.7.0
- Permalink: https://whatsnew.fyi/product/ecc/releases/v1.7.0

- **added** — Add direct Codex support with AGENTS.md-based setup, installer support, and Codex-facing docs
- **added** — Add cross-platform harness support for Cursor, Codex, and OpenCode with consistent repo structure
- **added** — Add frontend-slides skill for building animation-rich HTML slide decks and converting PPTX workflows to web-native presentations
- **added** — Add article-writing skill for long-form writing, voice matching, guides, and newsletters
- **added** — Add content-engine skill for platform-native repurposing across X, LinkedIn, TikTok, YouTube, and newsletters
- **added** — Add market-research skill for market, competitor, investor, and technology research with sourcing
- **added** — Add investor-materials skill for decks, memos, models, fundraising docs, and accelerator applications
- **added** — Add investor-outreach skill for investor cold emails, warm intros, follow-ups, and updates
- **added** — Add liquid-glass-design skill for iOS 26 Liquid Glass design system
- **added** — Add foundation-models-on-device skill for Apple on-device LLM integration patterns
- **added** — Add swift-concurrency-6-2 skill for Approachable Concurrency guidance for Swift 6.2
- **added** — Add swiftui-patterns skill for SwiftUI architecture and implementation patterns
- **added** — Add visa-doc-translate skill for visa and document translation workflow guidance
- **added** — Add chief-of-staff agent for communication-triage oriented coordination-heavy workflows
- **added** — Add origin metadata field to all skill files for source repository traceability
- **changed** — Rework plugin manifests for Cowork marketplace compatibility and cleaner marketplace behavior
- **changed** — Improve Codex packaging and discovery
- **changed** — Improve OpenCode package and release alignment
- **changed** — Add auto-detect formatter support in the post-edit hook
- **fixed** — Fix cross-platform hook and path handling
- **fixed** — Fix skill count accuracy in documentation
- **fixed** — Improve code examples in iOS 26 skills

##### ECC v1.7.0 — Cross-Platform Expansion & Presentation Builder

**992 tests. 56 skills. 33 commands. 14 agents. 4 major coding harnesses.**

This release tightens ECC as a single source of truth across **Claude Code, Codex, Cursor, and OpenCode**, adds a full presentation-building workflow, and expands the repo with reusable content, research, and fundraising skills that are generic enough for any team to use.

https://github.com/user-attachments/assets/9481110a-add8-4476-a3e4-c0ca2b796a3e

---

###### Highlights

- **Direct Codex support** — ECC now ships cleaner Codex app + CLI support with `AGENTS.md`-based setup, installer support, and Codex-facing docs
- **Cross-platform harness parity** — Cursor, Codex, and OpenCode support were expanded so the same repo structure works cleanly across all major AI coding tools
- **New `frontend-slides` skill** — Build animation-rich, zero-dependency HTML slide decks and convert PPTX workflows into web-native presentations with strict viewport-fit rules
- **5 new generic business/content skills** — `article-writing`, `content-engine`, `market-research`, `investor-materials`, and `investor-outreach`
- **Cowork marketplace compatibility** — Plugin manifests were reworked for Cowork compatibility and cleaner marketplace behavior
- **Chief-of-staff agent** — Added a communication-triage oriented agent for coordination-heavy workflows

###### Skills Added In This Cycle

| Skill | Description |
|------|-------------|
| `frontend-slides` | HTML presentations, PPTX conversion guidance, style exploration |
| `article-writing` | Long-form writing, voice matching, guides, newsletters |
| `content-engine` | Platform-native repurposing for X, LinkedIn, TikTok, YouTube, newsletter |
| `market-research` | Market, competitor, investor, and technology research with sourcing |
| `investor-materials` | Decks, memos, models, fundraising docs, accelerator applications |
| `investor-outreach` | Investor cold emails, warm intros, follow-ups, and updates |
| `liquid-glass-design` | iOS 26 Liquid Glass design system |
| `foundation-models-on-device` | Apple on-device LLM integration patterns |
| `swift-concurrency-6-2` | Approachable Concurrency guidance for Swift 6.2 |
| `swiftui-patterns` | SwiftUI architecture and implementation patterns |
| `visa-doc-translate` | Visa and document translation workflow guidance |

###### Platform and Workflow Improvements

- Improved Codex packaging and discovery
- Better OpenCode package/release alignment
- Cross-platform hook and path fixes
- Auto-detect formatter support in the post-edit hook
- Cleaner rule priority and development workflow documentation
- Better skill metadata traceability and distribution support

###### Why This Matters

ECC is no longer just “a Claude Code plugin.” It now works as a **multi-harness operating layer** for modern AI coding environments while keeping the repo coherent enough to ship from one place.

---

##### Detailed Commit Log
- chore: release v1.7.0
- feat: add generic content and investor skills
- Add frontend slides skill across platforms
- fix: restructure plugin manifest for Cowork marketplace compatibility
- fix: sync plugin manifest to v1.6.0, add chief-of-staff agent, fix placeholder email
- fix(docs): use namespaced /everything-claude-code:plan in README examples
- fix(hooks): extract doc-warning hook to external script to fix CI
- feat(agents): add chief-of-staff communication triage agent (#280)
- feat: add Cursor, Codex, and OpenCode harnesses — maximize every AI coding tool
- feat: add security guides and sanitize external links across repo
- Merge pull request #233 from andydiaz122/nano_claw_v1
- Merge pull request #276 from pangerlkr/patch-7
- Merge pull request #273 from bintocher/bintocher/issue-246
- Merge pull request #255 from CindyPersonalGit/main
- Merge pull request #252 from pythonstrup/feat/auto-detect-formatter
- Merge pull request #250 from O

_[Truncated at 4000 characters — full notes: https://github.com/affaan-m/ECC/releases/tag/v1.7.0]_

### v1.6.0 — ECC v1.6.0 — Codex Edition + Github App

- Date: 2026-02-24
- Version: v1.6.0
- Original notes: https://github.com/affaan-m/ECC/releases/tag/v1.6.0
- Permalink: https://whatsnew.fyi/product/ecc/releases/v1.6.0

- **added** — Support for OpenAI Codex CLI with new codex-setup command and instructions generator
- **added** — Seven new skills: analyze-repo, skill-creator, instinct-creator, hook-creator, workflow-discovery, pattern-detection, and learning-dna
- **added** — AgentShield integration with 102 security rules
- **added** — New /skill-creator command for AI-powered skill generation from repo analysis
- **added** — New /instinct-creator command to create instincts from repository patterns
- **added** — New /hook-creator command to generate hooks from conversation analysis
- **added** — New /update-codemaps command for auto-generating codebase maps
- **added** — New /update-docs command to sync documentation with code changes
- **changed** — ECC now supports Claude Code, Cursor, OpenCode, and Codex from a single config source
- **fixed** — Agent count display corrected from 15 to 13 active agents
- **fixed** — Skill count corrected from 32 to 43 skills
- **fixed** — Command count corrected from 30 to 31 commands
- **fixed** — Contributor count corrected across all documentation
- **fixed** — Markdown rendering in several skill outputs
- **fixed** — Hook permission conflicts with Codex integration

##### ECC v1.6.0 — Codex Edition

**309 commits. 30 community PRs merged. 978 tests. 4 platforms.**

Everything Claude Code now supports **Claude Code, Cursor, OpenCode, and Codex** — every major AI coding tool from a single config source.

---

https://github.com/user-attachments/assets/f2959480-42a0-4068-85f5-4e6e78c938a7


###### Highlights

- **Codex Support** — Full compatibility with OpenAI Codex CLI via new `codex-setup` command and instructions generator
- **7 New Skills** — `analyze-repo`, `skill-creator`, `instinct-creator`, `hook-creator`, `workflow-discovery`, `pattern-detection`, `learning-dna`
- **AgentShield Integration** — 102 security rules, 912 tests across all protection layers
- **GitHub Marketplace** — Listed and installable at [github.com/marketplace/ecc-tools](https://github.com/marketplace/ecc-tools)
- **Promo Video** — Professional Remotion-rendered 1080p promo with real demo footage

###### New Commands

| Command | Description |
|---------|-------------|
| `/codex-setup` | Configure ECC for OpenAI Codex CLI |
| `/skill-creator` | AI-powered skill generation from repo analysis |
| `/instinct-creator` | Create instincts from repository patterns |
| `/hook-creator` | Generate hooks from conversation analysis |
| `/update-codemaps` | Auto-generate codebase maps |
| `/update-docs` | Sync documentation with code changes |

###### Bug Fixes

- Fixed agent count display (15→13 active agents)
- Fixed skill count (32→43 skills)
- Fixed command count (30→31 commands)
- Corrected contributor count across all docs
- Fixed markdown rendering in several skill outputs
- Resolved hook permission conflicts with Codex integration

###### Community

- **30 community PRs merged** in this release cycle
- PRs #268, #265 merged; #272, #271 closed
- Active discussions on 10+ open issues
- Special thanks to all 44 contributors

###### Stats

| Metric | Value |
|--------|-------|
| Stars | 50K+ |
| Forks | 6K+ |
| Contributors | 44 |
| Tests | 978 |
| Agents | 13 |
| Skills | 43 |
| Commands | 31 |
| Security Rules | 102 |

---

> *"Your repository teaches itself to Claude Code."*

Install: `gh ext install affaan-m/everything-claude-code`
Marketplace: [github.com/marketplace/ecc-tools](https://github.com/marketplace/ecc-tools)

### v1.5.0 — ECC v1.5.0 — Universal Edition

- Date: 2026-02-11
- Version: v1.5.0
- Original notes: https://github.com/affaan-m/ECC/releases/tag/v1.5.0
- Permalink: https://whatsnew.fyi/product/ecc/releases/v1.5.0

- **added** — Support for Claude Code, OpenCode, and Cursor platforms
- **added** — Universal config support across all three platforms
- **added** — npm package as ecc-universal
- **added** — 14 agents for architecture, TDD, security, E2E, code review, and more
- **added** — 28 skills spanning TypeScript, Python, Go, Java, Django, and Spring Boot
- **added** — 30 commands including multi-agent orchestration, sessions, and PM2
- **added** — Rules for 6 languages with language-specific patterns and security

ECC now supports Claude Code, OpenCode, AND Cursor. This release adds:

- **Universal config support** across all three platforms
- **npm package** as `ecc-universal`
- **14 agents** for architecture, TDD, security, E2E, code review, and more
- **28 skills** spanning TypeScript, Python, Go, Java, Django, and Spring Boot
- **30 commands** including multi-agent orchestration, sessions, and PM2
- **Rules for 6 languages** with language-specific patterns and security

##### Install

```bash
npm install -g ecc-universal
```

##### Quick Start

```bash
npx ecc-install typescript
```

Full docs: https://github.com/affaan-m/everything-claude-code#readme

### v1.4.1 — v1.4.1: Fix instinct import content loss

- Date: 2026-02-06
- Version: v1.4.1
- Original notes: https://github.com/affaan-m/ECC/releases/tag/v1.4.1
- Permalink: https://whatsnew.fyi/product/ecc/releases/v1.4.1

- **fixed** — Preserve content after frontmatter in parse_instinct_file()

##### Changes
- fix: preserve content after frontmatter in parse_instinct_file() (#161)

### v1.4.0 — v1.4.0: Multi-Language Rules, Installation Wizard & PM2 Orchestration

- Date: 2026-02-06
- Version: v1.4.0
- Original notes: https://github.com/affaan-m/ECC/releases/tag/v1.4.0
- Permalink: https://whatsnew.fyi/product/ecc/releases/v1.4.0

- **added** — Add GitHub Sponsors support
- **added** — Add configure-ecc interactive installation wizard
- **added** — Add pm2 and multi-agent orchestration commands
- **changed** — Restructure rules into common and language-specific directories
- **fixed** — Correct markdown code block syntax in go-test.md

##### Changes
- docs: enhance CONTRIBUTING.md with detailed templates
- feat: add GitHub Sponsors support
- refactor(rules): restructure into common + language-specific directories
- feat(skills): add configure-ecc interactive installation wizard
- feat: add pm2 and multi-agent orchestration commands
- docs: Add Chinese (zh-CN) translations for all documentation
- fix: correct markdown code block syntax in go-test.md