actual-mcp-server: Skill for Claude Code

.claude/skills/release/SKILL.md

release is a skill for Claude Code from agigante80/actual-mcp-server. It costs 103 tokens per session (3,145 once invoked), scanned A, original, MIT.

A release workflow that moves completed code from the develop branch to the main branch, assigns a version tag, checks the publishing pipeline, and closes the shipped GitHub issues.

In plain words
What is it for?
Use it when you want to release, merge develop into main, push a version, or ship a named release such as 0.6.40.
Why use it?
It groups the steps needed to publish a release and prevents implemented tickets from being forgotten in the issue tracker. An optional version check can catch a mismatch before shipping.

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/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

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

agentmods 80×15 button for release

Your own site · 80×15
<a href="https://agentmods.dev/skills/agigante80/actual-mcp-server/release"><img src="https://agentmods.dev/badge/skills/agigante80/actual-mcp-server/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,145 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
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 $0.00103 $0.03145
Opus 5 $0.00051 $0.01572
Sonnet 5 $0.00021 $0.00629
Haiku 4.5 $0.00010 $0.00314

Measured yesterday against content hash 010ca2c4abe2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

release scanned grade A with 1 finding 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 yesterday.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

const { execSync } = require("child_process");
.claude/skills/release/SKILL.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release (develop to main)

Promote the current develop to main as a versioned release, then close the GitHub issues that release implemented. The implement-ticket pipeline stops at develop on purpose; this skill is the explicit, human-triggered step that ships develop to main and tidies the tracker so implemented tickets do not linger open.

The closing-tickets step is the reason this skill exists: without it, every ticket implemented since the last release stays open after shipping, and closing them by hand is easy to forget.

When this runs

Any request to release / merge develop to main. Optional argument: an expected version (e.g. 0.6.40) to assert against the VERSION on develop as a safety check. Everything is on main and the tag; develop is the source.

No em or en dashes anywhere (CLAUDE.md hard rule). Honest reporting: never claim released until the release pipeline is green.

Version sources (single source of truth + mirrors)

The canonical version is the VERSION file. Everything else is a mirror that must be kept equal to it: package.json version, the doc **Version:** markers, and container labels. scripts/version-bump.js propagates the bump to all mirrors; scripts/version-check.js (run as npm run version:check) fails if any mirror disagrees, and runs in the Validate CI workflow and pre-commit so drift is caught before release, not during it.

Bump modes (semver)

Mode Effect
patch / minor / major npm run version:bump -- <level>: bump VERSION, propagate to all mirrors, sync doc markers
sync npm run version:bump -- sync: do NOT bump; only re-sync mirrors + doc markers to the current VERSION (fixes drift)

The bump level is a human judgement; never auto-infer it. Operator contract: breaking the deployment is major, an opt-in feature is minor, a fix / CVE / dependency update is patch. Bumping is a single committed step (chore(release): bump version to X.Y.Z) on develop BEFORE the release runs (implement-ticket normally does this).

Read the full file on GitHub · 262 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. yesterday Changed · +16 lines 010ca2c4abe2
  2. 9d ago First seen · 246 lines · 103 tokens per session scan A eb2937b728ce

Subscribe to this mod's changes

release is a skill published in the GitHub repository agigante80/actual-mcp-server (51 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 3,145 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.