raven-mcp: Skill for Claude Code

.claude/skills/release/SKILL.md

release is a skill for Claude Code from rhinocap/raven-mcp. It costs 54 tokens per session (4,660 once invoked), scanned A, original, Apache-2.0.

A release procedure for publishing new versions of the Raven MCP server, an extension that lets coding agents use Raven tools.

In plain words
What is it for?
Use it after changes are merged to release Raven to npm and the MCP Registry, rebuild its package, update local instances, and push the release tag.
Why use it?
It organizes version changes, builds, publishing, tagging, and updating local Raven installations into one repeatable process.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code.

This is rhinocap/raven-mcp's own configuration. It tells Claude Code how to work on raven-mcp 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 raven-mcp configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/accunliffe/projects/raven-mcp/dist/index.js.

Reuse

Borrowing it

Nothing to install: this file belongs to rhinocap/raven-mcp. 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/rhinocap/raven-mcp/main/.claude/skills/release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/rhinocap/raven-mcp

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/rhinocap/raven-mcp/release.svg)](https://agentmods.dev/skills/rhinocap/raven-mcp/release)
Your own site
<a href="https://agentmods.dev/skills/rhinocap/raven-mcp/release"><img src="https://agentmods.dev/badge/skills/rhinocap/raven-mcp/release.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,660 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.
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 $0.00054 $0.04660
Opus 5 $0.00027 $0.02330
Sonnet 5 $0.00011 $0.00932
Haiku 4.5 $0.00005 $0.00466

Measured 8d ago against content hash cb33b62c6119, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sL "https://ravenmcp.ai/changelog?cb=$RANDOM" | grep -o 'cl-version">v[0-9.]*' | head -1 # must show vX.Y.Z
.claude/skills/release/SKILL.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release raven-mcp

The end-to-end release runbook for raven-mcp. scripts/release.sh does the mechanical work (version bump, manifest/server sync, .mcpb rebuild, npm publish, mcp-publisher publish, commit, tag, push) — but it has two gaps and one propagation step it does not handle, which is why releasing felt hard. This skill wraps it so a release is one predictable pass.

When to use

Any time merged work on main needs to reach Raven consumers — npm (raven-mcp), the public .mcpb at ravenmcp.ai, and your own machine's instances. Run AFTER the feature PR is merged to main, not before.

How Raven is actually consumed (why "merge to main" is not enough)

  1. Your Claude Code (CLI) instances load Raven from a local path, not npm: ~/.claude.json registers raven as node /Users/accunliffe/projects/raven-mcp/dist/index.js (both a global mcpServers.raven entry and a project-scoped one). They read the built dist/, which is gitignored — so a new tool only reaches them after npm run build in this working copy AND the instance reconnects its MCP server (a stdio server is spawned once at session start). New sessions auto-pick-up the rebuilt dist; already-running sessions need /mcp → reconnect raven (or a session restart).
  2. npm package raven-mcp (bin: raven-mcp → dist/index.js) — for any consumer wired via npx raven-mcp / a dependency. Only updates on npm publish.
  3. MCP Registry record ai.ravenmcp/raven-mcp — the discovery metadata for the npm package and hosted remote. Only updates on mcp-publisher publish.
  4. Claude Desktop extension local.mcpb.andrew-cunliffe.raven-mcp — a separate packaged copy under ~/Library/Application Support/Claude/Claude Extensions/. It does NOT read this working copy. It updates only when you rebuild the .mcpb and reinstall the extension in Claude Desktop.

So a full release = publish npm + publish the MCP Registry record + rebuild/redeploy .mcpb + rebuild local dist + reconnect/reinstall.

Read the full file on GitHub · 191 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. 8d ago First seen · 191 lines · 54 tokens per session scan A cb33b62c6119

Subscribe to this mod's changes

release is a skill published in the GitHub repository rhinocap/raven-mcp (6 stars, last pushed 15d ago), licensed Apache-2.0. It adds 54 tokens to every session and 4,660 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.