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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/arturogarrido/claudinho/release-discipline"><img src="https://agentmods.dev/badge/rules/arturogarrido/claudinho/release-discipline.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00639 | $0.00639 |
| Opus 5.5 | $0.00256 | $0.00256 |
| Sonnet 5.5 | $0.00128 | $0.00128 |
| Haiku 4.5 | $0.00064 | $0.00064 |
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 14d 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.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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). scripts/gate.shruns CI's gating list locally (notpnpm release:qa, not CI's Node 22 floor, Windows and macOS jobs), andscripts/push-and-watch.sh <branch>reads CI's per-job result on the pushed SHA.- 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/ (the maintainer's private notes and notebook) and CLAUDE.local.md. Never cite a file under docs/ from a tracked file — the pack guard (scripts/check-pack.mjs, run in CI) fails on any docs/<name> reference.
- 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 and
ambient --jsonknockouts (if touched): indirect-resolve via cachedgetKnockoutFixtures— 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.
- 14d ago Changed · +1 tokens per session 3933ceb92806
- 26d ago Changed · +6 tokens per session 32752286b265
- 29d ago Changed · +1 lines · +57 tokens per session a5b9ed8634fd
- 1mo ago Changed · +35 tokens per session e7f95234e7b8
- 2mo 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 (35 stars, last pushed 5d ago), licensed MIT. It adds 639 tokens to every session, about $0.0026 per session on Opus 5.5. 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.
release-discipline compared with cursor rules from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| release-disciplinearturogarrido/claudinho | Cursor rule | 35 | 5d ago | MIT | A | 639 | Cursor |
| hatch3r-git-conventionshatch3r/hatch3r | Cursor rule | 26 | 1mo ago | MIT | A | 39 | Cursor |
| release-policyv0id-user/setmac | Cursor rule | 16 | 6d ago | MIT | A | 319 | Cursor |
| release-changelognorthgraindata/dbt-doctor | Cursor rule | 70 | 3mo ago | MIT | A | 0 | Cursor |
| release-checklistyoreai/relay | Cursor rule | 2 | 2mo ago | Apache-2.0 | A | 215 | Cursor |
| sciclaw-papercutssciclaw/sciclaw | Cursor rule | 11 | 3mo ago | none | A | 607 | Cursor |
| semver-changelog-agentappboypov/pew-pew-cli | Cursor rule | 6 | 10mo ago | none | A | 74 | Cursor |