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/floriscornel/todo-mcpWrote 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/floriscornel/todo-mcp/release-management)<a href="https://agentmods.dev/rules/floriscornel/todo-mcp/release-management"><img src="https://agentmods.dev/badge/rules/floriscornel/todo-mcp/release-management.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 | $0.00461 | $0.00461 |
| Opus 5 | $0.00230 | $0.00230 |
| Sonnet 5 | $0.00092 | $0.00092 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
release-management 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 Management
Version Bumping
When preparing a release:
-
Never run
npm publishmanually - This is handled by GitHub Actions -
Update version in
package.jsonandsrc/index.tsusing semantic versioning:- Patch (0.1.2 → 0.1.3): Bug fixes, documentation updates
- Minor (0.1.2 → 0.2.0): New features, backward compatible
- Major (0.1.2 → 1.0.0): Breaking changes
-
Update CHANGELOG.md with release notes:
- What's new
- Bug fixes
- Breaking changes (if any)
- Migration notes
Release Process
-
Prepare Release Branch:
git checkout -b release/v0.1.3 -
Update Version & Changelog:
- Bump version in
package.jsonandsrc/index.ts - Update
CHANGELOG.md - Run
npm run test:coverageto ensure everything works
- Bump version in
-
Create Release PR:
- Title: "Release v0.1.3"
- Include changelog in PR description
- Ensure all CI checks pass
-
Create GitHub Release:
- After PR is merged, create a GitHub release
- Tag format:
v0.1.3 - Include changelog in release notes
- This triggers automatic NPM publishing
Pre-Release Checklist
- All tests pass with coverage
- Documentation is up to date
- CHANGELOG.md is updated
- Version number follows semver
- No breaking changes without major version bump
- CI pipeline passes on main branch
Automated Publishing
The GitHub Actions workflow handles:
- Building the package
- Running final tests
- Publishing to NPM registry
- Creating distribution files
Never bypass this process - it ensures consistency and proper CI validation.
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 · 61 lines · 461 tokens per session scan A c74ecabcb0bf
release-management is a cursor rule published in the GitHub repository floriscornel/todo-mcp (2 stars, last pushed 6mo ago), licensed MIT. It adds 461 tokens to every session, about $0.0023 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 2026-08-31.
Other cursor rules, from other repositories
langfuse-mcp-general-rules
Cursor rule "langfuse-mcp-general-rules" from avivsinai/langfuse-mcp, covering building and publishing to pypi, version numbering and tagging and build and publish workflow.
conventional-commits
Enforce Conventional Commits format for all commit messages.
release-gate
Release & deploy gate for @kadam-net/mcp-server — what the agent may do autonomously vs. what requires explicit human approval. Applies to all branch/MR/release/deploy work in this repo.
git-workflow
Vollagentische Entwicklung, Auto-Commits, Commit-Konventionen.
changelog-maintenance
The CHANGELOG.md file must be maintained for every change to the PHP MCP SDK.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.