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.
npx skills add pvliesdonk/markdown-vault-mcp --skill releasinggit clone --depth 1 https://github.com/pvliesdonk/markdown-vault-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/skills/pvliesdonk/markdown-vault-mcp/releasing)<a href="https://agentmods.dev/skills/pvliesdonk/markdown-vault-mcp/releasing"><img src="https://agentmods.dev/badge/skills/pvliesdonk/markdown-vault-mcp/releasing/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/pvliesdonk/markdown-vault-mcp/releasing"><img src="https://agentmods.dev/badge/skills/pvliesdonk/markdown-vault-mcp/releasing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 7 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Agent Snooping · line 70 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00054 | $0.03592 |
| Opus 5 | $0.00027 | $0.01796 |
| Sonnet 5 | $0.00011 | $0.00718 |
| Haiku 4.5 | $0.00005 | $0.00359 |
Grade A, and why
releasing 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- releasing — 95% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Releasing
Claude Code plugin channel
.claude-plugin/plugin/ ships this server as a Claude Code plugin: .claude-plugin/plugin.json (identity + version) and an exec-form .mcp.json that launches the released PyPI package with uvx --from <pkg>==<version>. Both manifests are version-coupled to the stable release stream — scripts/stamp_manifests.py stamps and stages them inside each stable release PR, so the marketplace entry published by the release workflow always installs the version it points at. That entry is written into the catalog's .claude-plugin/marketplace.json, the only path Claude Code loads a marketplace from — a manifest anywhere else is not a marketplace, and the publish job fails rather than bumping one. The marketplace entry is a rolling pointer, so on rc prepares the script leaves both files at the last published stable rather than pointing everyone browsing the catalog at a candidate (tests/test_release_flow_contract.py gates the invocation pairing and this skip). The env block in .mcp.json, the plugin README, and any skills/ directories are project-owned content: the files are seeded once and never re-rendered by template updates. Values in env may reference plugin userConfig entries as ${user_config.<id>} declared in plugin.json — exec-form fields only; shell-form command strings reject the substitution.
To generate the plugin's configuration screen from the config surface instead of hand-editing it, declare a files: pair in config-presentation.domain.yml: the plugin.json path with kind: claude-plugin-user-config and a fields: map (same field specs as the mcpb install screen (see the config-contract skill)), plus the .mcp.json path with kind: claude-plugin-env and fields_from: naming the first entry. One fields map then drives both the userConfig object and the ${user_config.<id>} env wiring, and scripts/gen_config_surface.py --check gates the pair against drift.
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.
- 4d ago Changed d92fb76486e1
- 11d ago First seen · 77 lines · 54 tokens per session scan A 4ebe22bebb69
releasing is a skill published in the GitHub repository pvliesdonk/markdown-vault-mcp (32 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 3,592 once invoked, about $0.0003 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 skills, from other repositories
hyalo-changelog
Maintain Keep a Changelog files with Hyalo's changelog profile and add/release commands.
solomd
Read, search, edit, and version-control any folder of Markdown notes via the SoloMD MCP server. 13 tools including AutoGit per-note history, semantic search, and write-with-sandbox via an accept/reject branch. Includes 11 starter agent recipes (weekly review, todo extract, link suggester, …).
git-wrapup
Land working-tree changes as logical commits — the work grouped by concern, topped by a release commit (version bump, changelog, regenerated artifacts). Verify, commit. Stops at "committed locally on main" — or, when the project releases through a release PR, at "release branch pushed, PR open". No tag, no push to…
release-and-publish
Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, fast-forwards main when the release rode a release PR, creates the annotated tag on the commit main now points at, pushes commits and tags, then publishes…
release-pr-review
Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…
re0-release
Walk a pending change through this repo's shipping and releasing checklist end to end, then tag and publish once confirmed. User-invoked: run it when you've decided to ship.