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/MarcoPorcellato/matryca-plumberWrote 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/marcoporcellato/matryca-plumber/05-release-preparation)<a href="https://agentmods.dev/rules/marcoporcellato/matryca-plumber/05-release-preparation"><img src="https://agentmods.dev/badge/rules/marcoporcellato/matryca-plumber/05-release-preparation.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 | $0.00019 | $0.00522 |
| Opus 5 | $0.00010 | $0.00261 |
| Sonnet 5 | $0.00004 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
05-release-preparation 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 7d 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 preparation (Matryca Plumber)
When the user asks to prepare, cut, or ship a release (e.g. “prepare release v1.6.2”, “rilascia 1.6.2”), run this checklist in order without skipping steps.
Inputs
- Target version:
X.Y.Z(from user message; acceptvX.Y.Zand normalize). - Today’s date: ISO
YYYY-MM-DDfor the changelog heading.
Steps
- Read
CHANGELOG.md. Under## [Unreleased], there must be at least one meaningful bullet or the user explicitly confirms an empty/maintenance release. - Finalize changelog
- Rename
## [Unreleased]→## [X.Y.Z] - <today>. - Insert a fresh
## [Unreleased]at the top (after the intro lines) with empty optional subsections or none.
- Rename
- Bump version — set
version = "X.Y.Z"inpyproject.toml(novprefix). - Lockfile — run
uv lockfrom the repo root. - Verify notes — run
python scripts/extract_changelog.py vX.Y.Zand confirm output matches the new section. - Tests — run
make checkif available; otherwiseuv run ruff check src tests,uv run mypy src tests,uv run pytest -q. - Summarize for the user — list changed files and the exact git commands from
docs/RELEASE_PROCESS.md(commit messagechore: release X.Y.Z, tagvX.Y.Z, push branch + tag). Do not create the tag or push unless the user explicitly asks.
Constraints
- Never tag
[Unreleased]or ship with version/changelog mismatch. - Do not use
gh release create --generate-notes; release notes come only fromCHANGELOG.mdvia CI. - Do not commit secrets (
.env). - Only create a git commit when the user explicitly requests it.
Reference
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.
- 7d ago First seen · 38 lines · 19 tokens per session scan A d60492595939
05-release-preparation is a cursor rule published in the GitHub repository MarcoPorcellato/matryca-plumber (96 stars, last pushed today), licensed Apache-2.0. It adds 19 tokens to every session and 522 once invoked, about $0.0001 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
desktop-release-gate
Desktop app fixes must pass a local packaged build smoke test before pushing release tags or CI desktop builds.
release-migrations-authoring
Authoring a release migration (llm-wiki-memory itself) — This rule governs developing llm-wiki-memory itself. Canonical file is .agents/rules/release-migrations-authoring.md.
versioning-and-npm-distribution
Versioning integrity and GitHub/npm distribution flow for AgentProdReady.
branch-dev-main
Always develop on dev; merge to main after verified; keep both in sync.
aionforge-memory
Aionforge Memory cadence and vocabulary — recall first, capture as you go, track tasks as work items.
sciclaw-papercuts
Papercuts from Sol/ImageMagick/release cycles — release, brew, CI, and workspace hygiene for sciClaw agents.