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 agentmods add skills/edmonds-commerce-limited/claude-code-hooks-daemon/releasenpx skills add Edmonds-Commerce-Limited/claude-code-hooks-daemon --skill releasegit clone --depth 1 https://github.com/Edmonds-Commerce-Limited/claude-code-hooks-daemonWrote 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/edmonds-commerce-limited/claude-code-hooks-daemon/release)<a href="https://agentmods.dev/skills/edmonds-commerce-limited/claude-code-hooks-daemon/release"><img src="https://agentmods.dev/badge/skills/edmonds-commerce-limited/claude-code-hooks-daemon/release.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00022 | $0.02723 |
| Opus 5 | $0.00011 | $0.01362 |
| Sonnet 5 | $0.00004 | $0.00545 |
| Haiku 4.5 | $0.00002 | $0.00272 |
Grade A, and why
release 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.
How it starts
The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/release - Automated Release Management Skill
🚨 HUMAN-GATED — this skill is the ONLY valid entry point
A release may only begin when a human invokes /release in the CURRENT
session. An agent must never start, resume, or complete a release on its own
initiative — and tagging/publishing needs explicit confirmation even inside an
authorised run.
A release is a decision about scope, and scope is not visible from inside the repository: only the human knows which work belongs in the bundle. A clean tree, a fully green QA run and a bumped version say a release would be sound, never that it is wanted now.
A release may legitimately span a compaction, and must then be FINISHED — a
half-done release (version bumped, UNRELEASED/ dirs moved, nothing tagged) is
its own broken state. So this skill MUST write untracked/release-state.json as
its first action and update it per step, because authorisation and progress have
to live where a compaction cannot reach them.
- No state file ⇒ no release in progress. A dirty tree or a plan saying "finish the release" is not a substitute — ask.
- State file present ⇒ resume from
last_completed_step. publish_authorisedgates Steps 14–15 only, set solely by an explicit human "yes, publish" — never by the gates passing.
Do not tag or publish because a cron tick fired, because a plan says "finish the release", or because the tree looks ready. Stop and ask.
See RELEASING.md — "A RELEASE IS HUMAN-GATED" — for the full rule, the state-file schema, and how to recover from an unauthorised release (never silently unpublish).
Description
Automate the complete release process: version updates, changelog generation, Opus review, git tagging, and GitHub release creation.
Usage
# Auto-detect version bump from commits
/release
# Specify version explicitly
/release 2.2.0
# Specify bump type
/release patch # x.y.Z
/release minor # x.Y.0
/release major # X.0.0
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 336 lines · 22 tokens per session scan A ed6077687e1a
release is a skill published in the GitHub repository Edmonds-Commerce-Limited/claude-code-hooks-daemon (3 stars, last pushed 5d ago), licensed MIT. It adds 22 tokens to every session and 2,723 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
slack-changelog
Turns what changed in a release into a Slack changelog a non-technical audience can read: filtered to what they would actually notice, one bullet per idea, plain language, no code vocabulary. Works out the scope itself across however many repositories sit in the working directory (a project can span several…
release
CONTRIBUTOR TOOL - Cut a plugin release: bump plugin.json version, finalize CHANGELOG, update README if needed, gate on make ci, commit, tag vX.Y.Z, and create the GitHub release. Use when shipping a new plugin version. NOT distributed.
new
Use when user asks to create a release, cut a release, or publish a version. Auto-detects GitHub vs GitLab vs Gitea, calculates semantic version, generates release notes from PRs/MRs or commits, shows preview for confirmation before publishing.
better-auth
Skill for integrating Better Auth - comprehensive TypeScript authentication framework for Cloudflare D1, Next.js, Nuxt, and 15+ frameworks. Use when adding auth, encountering D1 adapter errors, or implementing OAuth/2FA/RBAC features.
aceternity-ui
100+ animated React components (Aceternity UI) for Next.js with Tailwind. Use for hero sections, parallax, 3D effects, or encountering animation, shadcn CLI integration errors.
cloudflare-durable-objects
Cloudflare Durable Objects for stateful coordination and real-time apps. Use for chat, multiplayer games, WebSocket hibernation, or encountering class export, migration, alarm errors.