actual-mcp-server: Skill for Claude Code

.claude/skills/release-automation/SKILL.md

release-automation is a skill for Claude Code from agigante80/actual-mcp-server. It costs 136 tokens per session (3,187 once invoked), scanned A, original, MIT.

Automated release rules that check whether the project's version has advanced beyond the latest release tag before code reaches the main branch. A release tag is a version label marking code that was shipped.

In plain words
What is it for?
Use it to maintain the release gate, compare the VERSION file with released tags, and handle approved dependency-update or first-release cases.
Why use it?
It prevents a promotion from silently shipping without a version bump and coordinates the repository's release checks and automatic release paths.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is agigante80/actual-mcp-server's own configuration. It tells Claude Code how to work on actual-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything actual-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to agigante80/actual-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/agigante80/actual-mcp-server/main/.claude/skills/release-automation/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/agigante80/actual-mcp-server

Made for: Claude Code.

Wrote 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.

agentmods badge for release-automation

README.md
[![agentmods](https://agentmods.dev/badge/skills/agigante80/actual-mcp-server/release-automation/github.svg)](https://agentmods.dev/skills/agigante80/actual-mcp-server/release-automation)
Your own site
<a href="https://agentmods.dev/skills/agigante80/actual-mcp-server/release-automation"><img src="https://agentmods.dev/badge/skills/agigante80/actual-mcp-server/release-automation/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.

agentmods 80×15 button for release-automation

Your own site · 80×15
<a href="https://agentmods.dev/skills/agigante80/actual-mcp-server/release-automation"><img src="https://agentmods.dev/badge/skills/agigante80/actual-mcp-server/release-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,187 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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 6
    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 10
    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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00136 $0.03187
Opus 5 $0.00068 $0.01594
Sonnet 5 $0.00027 $0.00637
Haiku 4.5 $0.00014 $0.00319

Measured 12d ago against content hash 60697bf42b16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

release-automation 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 12d 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.

.claude/skills/release-automation/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release automation

Make the missing release impossible. The release skill (.claude/skills/release/SKILL.md) is the invoked ship someone runs; this is the unattended layer that runs without being invoked, so a promotion to main with no version bump is blocked (or, for verified dependency updates, auto-bumped), never silently shipped. In this repo the layer is already partly installed: a local release-gate hook plus two auto-release workflows. This skill documents how the pieces compose and how to maintain them.

Composition, not duplication. Semver rules and the version source live in the release skill and the version-marker section of CLAUDE.md (canonical VERSION file, mirrors managed by scripts/version-bump.js). This skill enforces them, it does not restate them.

The one mechanism: VERSION vs latest tag

All lanes share a single primitive: compare the working-tree VERSION against the latest released vX.Y.Z tag (not the previous commit; the tag is the only truth for "what is released") and act on one verdict:

Verdict Meaning What a lane does with it
first-release no release tag yet allow (historical only; this repo has tags since v0.x)
ahead VERSION > latest tag, already bumped deliberately ship as-is, never re-bump
equal VERSION == latest tag, nobody bumped the lane's policy decides (block, or auto-patch)
behind VERSION < latest tag, branch is stale hard stop (regression)

The ahead/behind handling is the load-bearing part: it is what stops a naive "always patch on merge" from double-bumping a deliberate 0.8.0 into 0.8.1, and what refuses to publish a regression. In this repo the primitive is implemented twice, single-sourced by intent:

  • scripts/version-bump.js (the write path): before any bump it runs the production-tag freshness check (git ls-remote --tags origin) and aborts on behind. This is the guard against the parallel-bump pattern (the scheduled auto-release ships while a local branch is unsynced). Recovery: git fetch origin && git merge origin/main. Override only with --force, and only when production is genuinely wrong; the release-manager agent requires explicit user confirmation first.
  • npm run version:check (scripts/version-check.js, the read path): verifies the canonical VERSION and its mirrors (package.json, doc **Version:** markers, container labels) agree, so the verdict is computed over one value, not several drifting ones. It runs in the Validate job of .github/workflows/ci-cd.yml and in pre-commit; drift fails closed. If it fails, npm run version:bump -- sync re-syncs mirrors without bumping.

Read the full file on GitHub · 189 lines

Changes

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.

  1. 12d ago First seen · 189 lines · 136 tokens per session scan A 60697bf42b16

Subscribe to this mod's changes

release-automation is a skill published in the GitHub repository agigante80/actual-mcp-server (54 stars, last pushed yesterday), licensed MIT. It adds 136 tokens to every session and 3,187 once invoked, about $0.0007 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.

Related

Other skills, from other repositories