Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/salitaba/maven-decoder-mcpnpx agentmods add skills/salitaba/maven-decoder-mcp/project-releaseWrote 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/skills/salitaba/maven-decoder-mcp/project-release)<a href="https://agentmods.dev/skills/salitaba/maven-decoder-mcp/project-release"><img src="https://agentmods.dev/badge/skills/salitaba/maven-decoder-mcp/project-release/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/skills/salitaba/maven-decoder-mcp/project-release"><img src="https://agentmods.dev/badge/skills/salitaba/maven-decoder-mcp/project-release.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 | $0.00000 | $0.00919 |
| Opus 5.5 | $0.00000 | $0.00368 |
| Sonnet 5.5 | $0.00000 | $0.00184 |
| Haiku 4.5 | $0.00000 | $0.00092 |
Grade A, and why
project-release 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 1mo 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Release
Ship a new version of maven-decoder-mcp end to end. The tag is the single source of truth — CI rewrites every version file from it — so the release is mostly ceremony plus verification.
Rules
- Never reuse a version number. If a publish partially succeeded, bump patch and release again (npm refuses republished versions).
- Never retag or force-push a tag after any artifact published. Fix forward.
- Release flow is documented in
RELEASING.md; the authoritative process details live inRELEASE_GUIDE.mdand.github/workflows/release.yml. scripts/release.pyandsimple_release.share legacy and must not be used for real releases — they hardcode v1.0.0 and push a wrong image name.
Workflow
1. Decide the version
Inspect commits since the last tag (git log <last-tag>..HEAD --oneline).
SemVer: patch for fixes, minor for new tools/features, major for breaking
changes. Confirm with the user when ambiguous — the tag cannot be undone
once artifacts publish.
2. Run the gate locally
MAVEN_OFFLINE=true .venv/bin/python -m pytest tests/ -q --no-cov
.venv/bin/python run_tests.py
.venv/bin/python test_startup.py
.venv/bin/python -m build && .venv/bin/python -m twine check dist/*
Do not proceed on failure. All four must pass.
3. Draft release notes
python3 scripts/generate_release_notes.py --tag vX.Y.Z
Read the generated RELEASE_NOTES.md, fix anything the commit subjects got
wrong (the generator groups by feat:/fix: prefixes), and keep the focus
on what a user upgrading needs to know: new tools, behavior changes, breaks.
Commit the notes on main before tagging — CI uses the committed file as the
release body and regenerates from history only if it does not cover the tag.
4. Commit, tag, push
git add -A && git commit -m "release: vX.Y.Z"
git tag -a vX.Y.Z -m "Maven Decoder MCP Server vX.Y.Z"
git push origin main && git push origin vX.Y.Z
5. Watch CI to green
The Release workflow runs test (3.10/3.11/3.12) → build
(PyPI + npm + GitHub release) → docker (multi-arch push). Watch all three:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 96 lines · 0 tokens per session scan A a391c67e5574
project-release is a skill published in the GitHub repository salitaba/maven-decoder-mcp (20 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 919 tokens. 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 2026-09-09.
Other skills, from other repositories
release
Generic release assistant — analyzes repo release rules, caches them in .omc/RELEASERULE.md, then guides the release.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
tendril-release
Updates the used Ivy NuGet packages to the latest stable versions in a branch from development, builds/verifies, merges into development, creates a PR into main, merges it, merges main back to development, and triggers the GitHub Actions release workflow.
merge
The ship gate — the only skill that pushes a feature branch, opens its PR and merges. --staging checks that pre-merge passed on the branch tip, pushes, opens the feature→staging PR, waits for green CI, merges, deploys, verifies, emits a human test script and stamps the staging sign-off on approval. --production ships…
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.
agent-github-modes
Agent skill for github-modes - invoke with $agent-github-modes.