# dotagents-standard-skill changelog

> dotagents-standard-skill release notes.

- Vendor: dotagents-standard-skill
- Category: Developer Tools
- Official site: https://github.com/zaventh/dotagents-standard-skill
- Tracked by: What's New (https://whatsnew.fyi/product/dotagents-standard-skill)
- Harvested from: GitHub (zaventh/dotagents-standard-skill)
- Entries below: 2 (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

### v0.2.0

- Date: 2026-07-31
- Version: v0.2.0
- Original notes: https://github.com/zaventh/dotagents-standard-skill/releases/tag/v0.2.0
- Permalink: https://whatsnew.fyi/product/dotagents-standard-skill/releases/v0.2.0

- **added** — Add "Writing context back (the append trap)" section to SKILL.md with self-check and examples for correct context writing order
- **added** — Name host-local agent memory as a second sink where knowledge is lost to the repo
- **added** — Add Maintenance block to AGENTS.md router example in SKILL.md and to examples/sample-project/
- **changed** — Guard AGENTS.md router against context leaking back into it by making the write path explicit
- **removed** — Drop permissive "You may append durable decisions to .agents/memory/decisions.md" capability line from routers

Guards the `AGENTS.md` router against context leaking back into it.

The value of the dotagents layout depends on the router staying a router. The most common way that decays: an agent learns something durable and writes it into `AGENTS.md`, because that file is already in its context while `.agents/` is not. Repeat a few times and the router *is* the monolith again. This release makes the write path explicit.

##### Install

```bash
npx skills add zaventh/dotagents-standard-skill
```

##### What changed

- **`SKILL.md` — new "Writing context back (the append trap)" section.** States the order: classify the context, write it into `.agents/`, and only then add a routing line — never the content itself. Includes a self-check to run before any `AGENTS.md` write, and a worked trap-vs-correct example.
- **Names the second sink: host-local agent memory.** `~/.claude/` and similar tool-local memory features are machine-local, uncommitted, and invisible to other tools and teammates — knowledge that lands there is lost to the repo just as surely as knowledge appended to the router.
- **`## Maintenance` block** added to `assets/templates/AGENTS.md`, to the router example in `SKILL.md`, and to the worked example in `examples/sample-project/`.
- **Dropped** the permissive `You may append durable decisions to .agents/memory/decisions.md` capability line from both routers — it read as an allowance rather than a constraint.

##### A note on validation

These changes were measured with a behavioral eval — 60 runs across two fixture shapes and both router versions — and the append failure they guard against **did not reproduce in any run**. So this is preventive hardening, not a fix for observed behavior.

The leak that *did* reproduce is the other one: a "remember I prefer X" instruction landed in host agent-memory rather than `.agents/memory/` in most runs, and the router guardrail did not change that. It originates above the project-context layer, so it is documented here but not solved.

Full notes in the [changelog](https://github.com/zaventh/dotagents-standard-skill/blob/main/CHANGELOG.md).

### v0.1.0

- Date: 2026-07-08
- Version: v0.1.0
- Original notes: https://github.com/zaventh/dotagents-standard-skill/releases/tag/v0.1.0
- Permalink: https://whatsnew.fyi/product/dotagents-standard-skill/releases/v0.1.0

- **added** — Initial release of dotagents-standard agent skill with AGENTS.md router and .agents/ library pattern
- **added** — SKILL.md documentation covering mental model, context decision-taxonomy, and utilize/implement workflows
- **added** — Reference guides for .agents/ subdirectories and .agents Protocol integration
- **added** — Templates for AGENTS.md, rules, memory, personas, and skills
- **added** — Worked example with filled-in .agents/ layout for a hypothetical billing API

Initial release of the **dotagents-standard** agent skill — a guide for implementing and utilizing the [dotagents](https://github.com/bgreenwell/dotagents) directory-as-context standard: a slim `AGENTS.md` router plus a `.agents/` library that agents load via progressive disclosure.

##### Install

```bash
npx skills add zaventh/dotagents-standard-skill
```

##### What's included

- **`SKILL.md`** — the mental model, the context decision-taxonomy, the utilize/implement workflows, and the `AGENTS.md` router pattern
- **References** — a per-`.agents/`-subdirectory deep guide, plus the [.agents Protocol](https://dotagentsprotocol.com/) superset
- **Templates** — copy-paste starters for `AGENTS.md`, rules, memory, personas, and skills
- **Worked example** — a filled-in `.agents/` layout for a hypothetical billing API (`examples/sample-project/`)
- MIT licensed; CI validates the skill's frontmatter and Markdown links on every push

Full notes in the [changelog](https://github.com/zaventh/dotagents-standard-skill/blob/main/CHANGELOG.md).