# gstack 1.75.0.0

- Product: gstack (https://whatsnew.fyi/product/gstack)
- Vendor: gstack
- Date: 2026-08-29
- Version: 1.75.0.0
- Original notes: https://raw.githubusercontent.com/garrytan/gstack/main/CHANGELOG.md
- Permalink: https://whatsnew.fyi/product/gstack/releases/1.75.0.0

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.

Reuse: the summaries, labels and curation here are © What's New. Quote freely with attribution and a link back; wholesale republication of the corpus is not permitted — terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'.

---

- **added** — Review gains a simplification specialist lens that flags unrequested structure such as hand-rolled stdlib, one-implementation abstractions, dead flexibility, and dependencies duplicating platform features
- **added** — Every tier-2+ skill gains a reuse ladder that stops at the first rung that holds: this repo, stdlib, native platform, an installed dependency, then build the complete version of what remains
- **added** — Accepted shortcuts now leave a durable trail with a decision-ledger entry plus a gstack-shortcut marker in code, harvested into a debt ledger by /retro
- **added** — Agent hosts without a full install receive a 1.8KB rules digest to copy into their own rules file
- **added** — Simplification review specialist uses a closed tag vocabulary: delete, stdlib, native, speculative, shrink, dispatched on diffs over 100 lines with --simplification force flag
- **added** — Bounded closer reports what changed, what was skipped, and what to watch after completing work
- **added** — With/without-skill arm benchmark runs three build-shaped tasks through real sessions twice
- **changed** — /autoplan now runs the Eng review last, always, with mandatory order CEO → Design → DX → Eng
- **changed** — Simplification review is advisory only and cannot dent your quality score or auto-apply fixes

Your review now hunts over-built code, not just broken code.
And every skill's advice starts with "reuse before you build."
This release imports the best of ponytail, the code-minimalism ruleset, without importing its build-less posture. /review gains an eighth lens: a simplification specialist that flags unrequested structure (hand-rolled stdlib, one-implementation abstractions, dead flexibility, dependencies duplicating platform features) in a closed five-tag vocabulary. It is advisory only. It cannot dent your quality score, its fixes are never auto-applied, and on a lean diff it tells you something no reviewer ever says: "lean already — nothing to cut."
Every tier-2+ skill also gains the reuse ladder (stop at the first rung that holds: this repo, stdlib, native platform, an installed dependency... then build the complete version of what remains) and a bounded closer, so completion reports stop touring every edit.
Accepted shortcuts now leave a durable trail: a decision-ledger entry plus a `gstack-shortcut(dec- )` marker in code, harvested into a debt ledger by /retro.
Agent hosts without a full install (Zed, Amp, Cursor side projects) get a 1.8KB rules digest to copy into their own rules file.
And /autoplan now runs the Eng review last, always, so the required shipping gate reviews the final amended plan instead of a stale one.
Simplification review specialist: closed tag vocabulary (delete: / stdlib: / native: / speculative: / shrink:), dispatched on diffs over 100 lines, --simplification force flag.
Reuse ladder in Search Before Building: before writing new code, stop at the first rung that holds.
Bounded closer: after completing work, report what changed, what was skipped, what to watch.
Shortcut debt ledger: accepting a Completeness ≤ 7 option now logs the ceiling and upgrade trigger to the decision ledger.
Instruction-only host tier: agents-digest/gstack-AGENTS.md, a committed, generated, budget-capped (2,048 B) digest.
With/without-skill arm benchmark: three build-shaped tasks run through real sessions twice.
/autoplan runs Eng last, always: mandatory order is now CEO → Design → DX → Eng.