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/a9a4k/tour/releasenpx skills add a9a4k/tour --skill releasegit clone --depth 1 https://github.com/a9a4k/tourWrote 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/a9a4k/tour/release)<a href="https://agentmods.dev/skills/a9a4k/tour/release"><img src="https://agentmods.dev/badge/skills/a9a4k/tour/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 | $0.00085 | $0.01085 |
| Opus 5 | $0.00043 | $0.00543 |
| Sonnet 5 | $0.00017 | $0.00217 |
| Haiku 4.5 | $0.00009 | $0.00109 |
Grade A, and why
release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release
Tag-driven release: bun run release X.Y.Z --push bumps package.json+bun.lock, commits, tags vX.Y.Z, pushes both. CI does the rest (npm publish, GitHub Release, Homebrew formula bump in a9a4k/homebrew-tap). Full pipeline ~3 min. See docs/releasing.md for the underlying reference.
Workflow
Run each step. Stop and surface to the user on anything unexpected.
1. Sync with remote
git fetch origin
git status # must be on main, up-to-date or ahead
If local main is behind origin/main: git pull --rebase first. The release script doesn't guard against this — pushing a tag against a stale base will fail or ship the wrong commit.
2. Review what's shipping
LAST=$(git describe --tags --abbrev=0)
git log "$LAST"..HEAD --oneline
Read every commit title. Flag anything you don't recognise or that looks like in-progress work — ask the user before tagging.
3. Suggest the semver bump
Classify each commit since $LAST by conventional-commit prefix:
BREAKING CHANGE/!:anywhere → major (X+1.0.0)feat:present → minor (X.Y+1.0)fix:/perf:/refactor:only → patch (X.Y.Z+1)docs:/test:/chore:only → patch (still a release, but smallest bump)
State the proposed version with the reasoning, then ask the user to confirm or override.
4. Check working-tree dirt
git status --porcelain
The release script tolerates dirt outside package.json/bun.lock (it only stages those two), but unexpected modifications to source/docs/tests deserve a quick git diff and a question before shipping — they may belong in a pre-release commit.
5. Run the release
bun run release X.Y.Z --push
This runs typecheck + full test suite as preflight. On failure, see Failure modes below.
6. Confirm pipeline fired
gh run watch # or: gh run list --limit 3
Surface CI failures to the user. After CI succeeds, verify the user can install:
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 · 101 lines · 85 tokens per session scan A 8d63d1aedae4
release is a skill published in the GitHub repository a9a4k/tour (5 stars, last pushed 2mo ago), licensed MIT. It adds 85 tokens to every session and 1,085 once invoked, about $0.0004 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
changeset
Generate comprehensive changeset release logs with OG cover images for vobase releases. Use this skill when the user says "changeset", "release notes", "release log", "write changelog", "version bump", or when a feature implementation is complete and needs to be documented for release. Also triggers when the user asks…
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.
project-change-log
Automatically maintain a CHANGELOG.md file following the Keep a Changelog standard.
update-changelog
Add a CHANGELOG.md entry for a user-facing change. Use after implementing a feature or bug fix, when finishing a PR, or whenever a change is worth recording, to append a terse bullet under the [Unreleased] section.
release-announcement
Draft or revise ax release announcements and website changelog pages. Triggers when the user says "write release notes", "draft release announcement", "prepare changelog", "release page", "version page", "what changed in vX.Y.Z", "generate announcement for vX.Y.Z", or asks for a release narrative. Uses Release Please…
pr-explainer
Use when writing pull request descriptions, release notes, or summary diffs.