Borrowing it
Nothing to install: this file belongs to developerz-ai/ai-task-master. 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/developerz-ai/ai-task-master/main/.claude/skills/release-cut/SKILL.mdgit clone --depth 1 https://github.com/developerz-ai/ai-task-masterWrote 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/developerz-ai/ai-task-master/release-cut)<a href="https://agentmods.dev/skills/developerz-ai/ai-task-master/release-cut"><img src="https://agentmods.dev/badge/skills/developerz-ai/ai-task-master/release-cut/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/developerz-ai/ai-task-master/release-cut"><img src="https://agentmods.dev/badge/skills/developerz-ai/ai-task-master/release-cut.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00030 | $0.00410 |
| Opus 5.5 | $0.00012 | $0.00164 |
| Sonnet 5.5 | $0.00006 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
release-cut 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.
What it actually says
House skill — established by dz-runner setup mode from this repo's own evidence, then owned by its maintainers. Correct it in place; setup never overwrites a skill that exists.
- Bump the version in BOTH
packages/aitm/package.jsonandpackages/ai-claude-compat/package.json— keep them in lockstep;aitmpins compat to an exact version. - Run
bun install(updates lock metadata but NOT resolution — a version move is not a resolution change;bun.lockworkspace version lines are allowed to lag). - Do NOT regenerate
bun.lockin this PR — a lockfile resync is its own dependency-upgrade PR. - Commit with a conventional message (no co-author trailers).
- Publish a GitHub Release, or trigger Actions → release → Run workflow (
release.yml). - The workflow runs
bun install --frozen-lockfile,bun run build, thennpm publish -w @developerz.ai/ai-claude-compatBEFOREnpm publish -w @developerz.ai/aitm— order is mandatory (exact-pin dependency). - Publish is OIDC trusted publishing (no NPM_TOKEN); it needs npm ≥ 11.5.1 — the workflow pins [email protected] because 11.6.x broke the provenance path.
- First-ever version of a package is manual bootstrap by an org member (
npm login, build,npm publish -w … --access public) — a trusted publisher can only attach to an existing package. fail -> ifnpm publishdies on "Cannot find module 'sigstore'", the npm version regression hit: stop, do not bump the workflow pin without a task.
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 · 17 lines · 30 tokens per session scan A e75d35691c52
release-cut is a skill published in the GitHub repository developerz-ai/ai-task-master (5 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 410 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-02.
release-cut compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| release-cutdeveloperz-ai/ai-task-master | Skill | 5 | 3d ago | MIT | A | 30 | Claude Code |
| github-repo-managementraphaelmansuy/edgecrab | Skill | 93 | 3mo ago | none | A | 47 | Claude Code, Codex |
| commit-prZaxbyHub/opencode-swarm | Skill | 518 | yesterday | MIT | A | 100 | Codex |
| swarm-migrateyonatangross/orchestkit | Skill | 299 | yesterday | MIT | A | 103 | Claude Code |
| contributingZaxbyHub/opencode-swarm | Skill | 518 | yesterday | MIT | A | 44 | Codex |
| githubbug-ops/zeph | Skill | 66 | 3d ago | MIT | A | 104 | Claude Code, Codex |
| release-engineeringmagnus919/agent-skills | Skill | 166 | 2d ago | MIT | A | 158 | Claude Code, Codex |