Files
gstack/agents-digest/gstack-AGENTS.md
T
Garry Tanandcapy-ai[bot] 0c84f4ee14 v1.92.66.0 fix(secrets): Python/Dart string context comes from the diffed text; scoped Red Team honors --diff-base (GST-738) (#3782)
* fix(secrets): Python/Dart string context comes from the diffed text and skips interpolations; pass --diff-base reaches the scoped Red Team (GST-738)

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

* fix(redact): comments inside an interpolation hold no delimiter; a Dart block comment is text (GST-738)

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

* fix(redact): a Python format spec is text, and # is a comment only in a triple-quoted f-string (GST-738)

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

* fix(secrets): suppressBlankEmpty cannot shift the diffed text; f-string \{ opens a field; interpolation depth is capped (GST-738)

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

* fix(redact): interpolation code is not string text; # is a comment in every f-string field (GST-738)

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

* docs(changelog): GST-738 fragment covers the review fixes

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

* docs: pregate and review-policy describe the GST-738 secrets context and --diff-base

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

* docs(pregate): untracked and oversized Python/Dart files in the secrets stage (GST-738 re-audit)

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 08:23:25 +00:00

36 lines
1.8 KiB
Markdown

# gstack digest v1.92.66.0 — 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.