Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/arturogarrido/claudinhoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/arturogarrido/claudinho/release-discipline)<a href="https://agentmods.dev/rules/arturogarrido/claudinho/release-discipline"><img src="https://agentmods.dev/badge/rules/arturogarrido/claudinho/release-discipline.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00540 | $0.00540 |
| Opus 5 | $0.00270 | $0.00270 |
| Sonnet 5 | $0.00108 | $0.00108 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
release-discipline scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Release discipline
One feature, one release
- One user-facing feature → one minor. Stack review fixes (tz, dates, guards) into the same PR before merge when they belong to the same feature.
- Do not tag npm until CI is green and
pnpm release:qapasses (tripwires at the end must be 0 failed). - Before tagging:
git diff mainmust not include accidental private paths (docs/,CLAUDE.local.md,.env).
Commit attribution
Every commit produced with an AI agent: follow AGENTS.md § Commit attribution — trailer names the agent and model in use (e.g. Co-Authored-By: Cursor (Composer 2.5) <[email protected]>).
Public vs private docs
Tracked (public engineering guides): AGENTS.md, CLAUDE.md, .cursor/rules/, README, MCP tool descriptions.
Gitignored (maintainer-local): docs/ (e.g. docs/AGENTS.internal.md notebook), CLAUDE.local.md.
- Engineering process → update the public guides above.
- Candid history, strategy, or release post-mortems →
docs/notebook only. - Never add
!docs/…exceptions to.gitignorewithout explicit maintainer approval.
Bracket / live-formatting ship checklist
Before merge or release of bracket or kickoff-formatting work:
- Adversarial tests: 0 games, mid-tournament (2/3 played), degraded standings.
- Surface parity: CLI
bracket+ MCPget_bracket+share bracketall passtzand show calendar dates on multi-week knockouts. - Statusline knockouts (if touched): indirect-resolve via cached
getKnockoutFixtures— hot path fail-closed (no 🏳️ on countdown orlive · syncing…); empty-cache short TTL;knockout-surface-coverage.test.ts+statusline.test.ts/refresh.test.tsgreen. See.cursor/rules/surface-parity.mdc. - After
pnpm -r build, runpnpm release:qaand eyeball the rendered sections; keeppackages/mcp/test/tools.test.tsgreen for MCP arg threading.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 36 lines · 540 tokens per session scan A 07bbb185e4a7
release-discipline is a cursor rule published in the GitHub repository arturogarrido/claudinho (28 stars, last pushed yesterday), licensed MIT. It adds 540 tokens to every session, about $0.0027 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other cursor rules, from other repositories
hatch3r-git-conventions
Conventional Commits type list, subject line rules, breaking-change footer format, branch naming template for type/short-description, and change-size discipline (PR-size ceiling with stacked-change escape hatch).
release-changelog
Keep a Changelog and semver steps when cutting dbt-doctor releases.
changelog
Changelog and release notes rules.
release-checklist
What to update with each code change or version release.
release-policy
Release, versioning, and signing policy for setmac.
sciclaw-papercuts
Papercuts from Sol/ImageMagick/release cycles — release, brew, CI, and workspace hygiene for sciClaw agents.