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/mojoapp-ai/agent-skills/releasenpx skills add mojoapp-ai/agent-skills --skill releasegit clone --depth 1 https://github.com/mojoapp-ai/agent-skillsWrote 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/mojoapp-ai/agent-skills/release)<a href="https://agentmods.dev/skills/mojoapp-ai/agent-skills/release"><img src="https://agentmods.dev/badge/skills/mojoapp-ai/agent-skills/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 5.1 | $0.00084 | $0.01342 |
| Opus 5 | $0.00042 | $0.00671 |
| Sonnet 5 | $0.00017 | $0.00268 |
| Haiku 4.5 | $0.00008 | $0.00134 |
Grade A, and why
release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
release
Cut a new release of mojoapp-ai/agent-skills. Designed to be run from inside the repo with Claude Code.
Prerequisites
- You are at the repo root:
agent-skills/withskills/,.claude/,README.md,CHANGELOG.mdvisible. - Working tree is clean — no uncommitted changes (
git statusshows nothing). ghCLI is logged in for bothhanamizuki(default) andmojoapp-aiaccounts.
If any of the above fails, stop and tell the user what's wrong.
Step 1 — Inspect what's changed
git fetch --tags
LAST_TAG=$(git describe --tags --abbrev=0 2>/dev/null || echo "")
if [ -z "$LAST_TAG" ]; then
echo "No previous tag. This will be the initial release."
COMMITS=$(git log --pretty=format:"%h %s")
else
echo "Last tag: $LAST_TAG"
COMMITS=$(git log "$LAST_TAG..HEAD" --pretty=format:"%h %s")
fi
echo "$COMMITS"
Step 2 — Classify commits and propose a bump
Walk through each commit subject:
| Pattern in subject | Category | Bump signal |
|---|---|---|
feat: / feat(...): |
Added | minor |
fix: / fix(...): |
Fixed | patch |
docs: / docs(...): |
Documentation | patch |
chore: / chore(...): |
(omit from changelog unless notable) | patch |
refactor: |
Changed | patch |
BREAKING CHANGE: or subject contains !: |
breaking | major |
| anything else | Other | patch |
Proposed bump rule:
- Any breaking change present → major (X.0.0)
- Else any
feat:present → minor (0.X.0) - Else → patch (0.0.X)
For pre-1.0 releases (0.x.y), demote one level:
- breaking → minor (0.X.0)
- feat → minor (0.X.0)
- fix/docs → patch (0.0.X)
Show the user the classification + proposed version and ask to confirm before continuing.
Step 3 — Update CHANGELOG.md
Format follows Keep a Changelog.
Insert a new section just below the ## [Unreleased] header (create both if missing). Example for v0.2.0 on 2026-06-15:
## [0.2.0] — 2026-06-15
### Added
- mojo-food-log: support importing fiber-only entries (#42)
### Fixed
- mojo-glp1-knowledge: corrected Wegovy half-life from 7d to 165h
### Documentation
- mojo-app-docs: synced from nextra @ a1b2c3d
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.
- 5d ago First seen · 147 lines · 84 tokens per session scan A bdaac958295d
release is a skill published in the GitHub repository mojoapp-ai/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 1,342 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
comet-archive
Comet Classic 阶段 5 —— 确认归档、合并 delta spec 并完成分支收尾。.
finishing-a-development-branch
当实现完成、所有测试通过、需要决定如何集成这份工作时使用.
skillshare-changelog
Generate CHANGELOG.md entry from recent commits in conventional format. Also syncs the website changelog page. Use this skill whenever the user asks to: generate a changelog, document what changed between tags, or create a new CHANGELOG entry. If you see requests like "write the changelog for v0.17", "what changed…
skillshare-release
End-to-end release workflow for skillshare. Runs tests, generates changelog (via /changelog), optionally writes local RELEASENOTES, updates version numbers, commits, and drafts announcements. Use when the user says "release", "prepare release", "cut a release", "release v0.19", or any request to publish a new version.…
comet-release
根据真实版本和分支范围准备 Comet 发布或发布说明更新,保持 Changelog 面向用户、双语网站文档一致、生成资产已验证,并明确 Git 交付边界。Beta、hotfix、版本检查、发布说明或发布就绪检查时使用。.
comet-safe-delivery
在保护无关脏改动、关联 worktree、子模块和用户明确边界的前提下,提交、推送、合并或完成范围明确的 Comet 变更。用户要求提交、推送、合并回目标分支、清理 worktree 或交付已准备好的改动时使用。.