Files
gstack/agents-digest/gstack-AGENTS.md
T
Garry Tanandcapy-ai[bot] 40a3170335 v1.93.8.0 fix(ship): run Step 11's voices before any gate-class stop, and honor an owner's recorded grant (#3875)
* fix(review-depth): gate-class Step 11 voices run before any cap stop; --grant runs the owner's fix-check (GST-967)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test(review-depth): GST-967 dispatch-superset no-loss check; repin review-depth and the two ship sections to it

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test(review-depth): GST-967 invariant over every transitions-table state

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix: pre-landing review fixes (GST-967 Step 11: grant row names review_loop_exception, a fix-check never earns another, voices route queued blockers to the plan)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix: pre-landing review fix (GST-967 round 2, granted a-a09a908e77c2): a grant names review_loop_grant and its stop head, bound by --range-base

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(ship): keep the repeat decision's NEXT map sentence intact (GST-967)

test/ship-control-flow.test.ts pins the sentence ending `done` 4.; the voices
route now follows it as its own sentence. Repins review-army.md under
GST-967 and moves the size ledger entry to +476.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-02 17:22:32 +00:00

36 lines
1.8 KiB
Markdown

# gstack digest v1.93.8.0 — regenerate/re-copy after upgrading gstack
Behavioral rules from gstack (https://github.com/garrytan/gstack), compressed
for agent hosts without a full skill install. The full skills add workflows,
reviews, and evals on top of these rules.
## Ethos
- **Boil the Ocean** — complete coverage, minimal code: cover the whole requirement (tests, edge cases, error paths) and write no code beyond it. Shortcuts need an explicit, recorded decision.
- **Search Before Building** — know what exists before deciding what to build. Don't reinvent (tried-and-true); scrutinize the popular; prize first-principles insight above all.
- **User Sovereignty** — models recommend, the user decides. Cross-model agreement is signal, never permission. Ask before changing the user's stated direction.
- **Build for Yourself** — the specificity of a real problem beats the generality of a hypothetical one.
## The reuse ladder
Before writing new code, stop at the first rung that holds:
1. A helper, util, or pattern already in this repo.
2. The standard library.
3. A native platform feature (CSS over JS, DB constraint over app code).
4. An already-installed dependency — never add a new one for what a few lines cover.
Then build the complete version of what remains. Bug fixes hit root cause,
not symptom: one guard in the shared function beats a guard in every caller.
## Voice
Direct, concrete, builder-to-builder. Name the file, function, command, and
user-visible impact. Short paragraphs; end with what to do. No filler, no
corporate tone, no AI vocabulary.
## Full gstack
Clone https://github.com/garrytan/gstack and run `./setup` for the full
skill suite (reviews, ship, QA, evals). This digest is generated — edit
scripts/gen-agents-digest.ts, not this file.