Borrowing it
Nothing to install: this file belongs to hhopke/intervals-icu-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.
curl -O https://raw.githubusercontent.com/hhopke/intervals-icu-mcp/main/.claude/skills/release-write/SKILL.mdgit clone --depth 1 https://github.com/hhopke/intervals-icu-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/hhopke/intervals-icu-mcp/release-write)<a href="https://agentmods.dev/skills/hhopke/intervals-icu-mcp/release-write"><img src="https://agentmods.dev/badge/skills/hhopke/intervals-icu-mcp/release-write/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/hhopke/intervals-icu-mcp/release-write"><img src="https://agentmods.dev/badge/skills/hhopke/intervals-icu-mcp/release-write.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.03214 |
| Opus 5 | $0.00027 | $0.01607 |
| Sonnet 5 | $0.00011 | $0.00643 |
| Haiku 4.5 | $0.00005 | $0.00321 |
Grade A, and why
release-write 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Confirm the registry entry landed: `curl -s "https://registry.modelcontextprotocol.io/v0/servers?search=<pkg>" | jq '.servers[]?.version'`. How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
This repo's release path is half-manual:
| Step | Trigger | Workflow |
|---|---|---|
Push chore(release): X.Y.Z to main |
push.branches: main |
release.yml → Docker build/push |
Push tag vX.Y.Z |
(none) | nothing |
| Create GitHub Release on the tag | release.types: [published] |
publish.yml → PyPI + MCP Registry |
Creating the GitHub Release is what actually triggers PyPI publish. It is not optional. CHANGELOG.md is manual (per CLAUDE.md). This skill writes the GitHub Release body so users opening the Releases tab or the PyPI project page see polished notes, not raw commit history.
Prerequisites
- The release commit (
chore(release): X.Y.Z) is already onorigin/main— i.e. CHANGELOG.md has been renamed from[Unreleased]to[X.Y.Z] — YYYY-MM-DD, committed, and pushed. make can-releaseis green.- You are on
main, up to date withorigin/main. server.jsondescriptionis ≤ 100 chars. The MCP Registry rejects longer descriptions with HTTP 422 (expected length <= 100), failing themcp-registryjob after PyPI has already published — a partial release that's annoying to recover. Pre-flight check:jq -r '.description | length' server.json. If it's over 100, stop and get it trimmed onmainfirst.
If any prereq is missing, stop and tell the user what to do first.
Instructions
1. Extract the CHANGELOG section for this version
Find the start line of ## [X.Y.Z] and the start line of the next version section below it. Read everything in between, dropping the leading ## [...] — date heading line (GitHub uses the release title instead).
# Example for v3.0.0:
awk '/^## \[3\.0\.0\]/{flag=1; next} /^## \[/{flag=0} flag' CHANGELOG.md
Save the extracted body to a temp file (e.g. /tmp/release-notes-X.Y.Z.md).
2. Reshape into the project's narrative style
Critical: the release notes are NOT a copy of the CHANGELOG section. The CHANGELOG is the exhaustive source-of-truth; the release body is a curated headline version. Past releases in this repo (v2.0.0, v1.3.0, v1.2.0) follow a narrative style — read 1-2 of them before drafting to anchor on the existing voice:
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 · +45 lines e14313e3a5f3
- 10d ago First seen · 136 lines · 54 tokens per session scan A 59175fef9751
release-write is a skill published in the GitHub repository hhopke/intervals-icu-mcp (64 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 3,214 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 2026-08-30.
Other skills, from other repositories
prep-repo
Use when the user wants to prepare a local project for GitHub or public release. Runs a release-readiness sweep over README structure, bilingual docs, commit hygiene, sensitive-data exposure, broken links, markdown rendering, project layout, tests, CI, Docker, and final cleanup. Fixes issues only inside the target…
pypi-release
This skill should be used when releasing tunacode-cli to PyPI. It keeps the existing local release checks, then hands the actual PyPI upload to a GitHub Actions workflow that uses the repository's PYPIAPITOKEN secret.
github-repo-care
Protocol for safely creating, publishing, releasing, auditing, and maintaining GitHub repositories: check local rules and locks, create .gitignore before the first add, run privacy checks, prepare README/i18n/banner/metadata, verify release tags and GitHub releases, and update organization profiles, llms.txt files…
hmem-release
Pre-publish checklist for hmem: skills synced, version bumped, tests green, nothing forgotten. Use before npm publish or when the user says 'release', 'publish', 'push a release', or 'neue Version'.
metagit-release-audit
Mandatory before calling work complete when the session changed repo files. Runs format, lint, tests, integration tests, context-aware pip-audit/bandit, and optional gitleaks via task qa:prepush. Use before push, release, or hand-off.
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…