Borrowing it
Nothing to install: this file belongs to delexw/claude-code-trace. 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/delexw/claude-code-trace/main/.claude/skills/cut-release/SKILL.mdgit clone --depth 1 https://github.com/delexw/claude-code-traceWrote 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/delexw/claude-code-trace/cut-release)<a href="https://agentmods.dev/skills/delexw/claude-code-trace/cut-release"><img src="https://agentmods.dev/badge/skills/delexw/claude-code-trace/cut-release/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/delexw/claude-code-trace/cut-release"><img src="https://agentmods.dev/badge/skills/delexw/claude-code-trace/cut-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 4 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00211 | $0.01422 |
| Opus 5.5 | $0.00084 | $0.00569 |
| Sonnet 5.5 | $0.00042 | $0.00284 |
| Haiku 4.5 | $0.00021 | $0.00142 |
Grade A, and why
cut-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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cut-release — 98% identical, 10 lines differ
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cut a Release — claude-code-trace
Turns "we should release this" into a tagged, pushed, pipeline-triggered, publicly published release with a curated CHANGELOG, in a way that survives the project's strict pre-commit hook chain and stays honest about what's actually shipping.
The skill is project-local because the steps depend on this repo's specific shape (three
version files, two lockfiles, GH Actions release on v* tag, the spec-drift +
test-reflection pre-commit hook pair).
Operating mode
The skill is fully automated end-to-end and fully synchronous. It never calls
AskUserQuestion, never waits for "yes", never branches on user preference, and
never runs any command in the background. Every Bash invocation runs in the
foreground so the session holds continuously from Phase 1 through Phase 9 — no
run_in_background: true, no trailing &, no nohup, no disown. This includes
long-running steps like gh run watch in Phase 7; set the Bash timeout parameter to
match the expected duration (e.g. 1800000 ms for the release pipeline) rather than
detaching.
Defaults are deterministic:
- Scope — always linear: every commit since
git describe --tags --abbrev=0ships. - Bump tier — highest conventional-commit tier in the subset (see
${CLAUDE_SKILL_DIR}/references/conventional-commits.md).BREAKING CHANGE:or!:produces a minor bump while the version is0.X.Y(pre-1.0 caveat) and a major bump otherwise; the skill never silently promotes to 1.0.0. - CHANGELOG — every Added/Fixed bullet is written from commit subjects + diff reads;
chore:/docs:/test:/ci:are always skipped. - Push order — tag first, then main (so CI sees the tag immediately; main catches up after).
The skill aborts (loudly) only on hard preconditions that would corrupt the release:
- Duplicate version — the proposed
vX.Y.Ztag already exists onorigin. Abort withError: vX.Y.Z already exists on origin (commit <sha>). Refusing to release the same version twice.The user must delete the remote tag intentionally if they want a re-release, or bump again. - Dirty working tree — uncommitted changes the skill didn't create. Abort with a list of dirty files.
npm run checkfails — abort and surface the failure verbatim.
What ships with it
12 files 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.
- references/changelog-template.md 3.6 KB
- references/conventional-commits.md 3.0 KB
- references/project-shape.md 4.0 KB
- steps/phase1-inspect-and-scope.md 2.7 KB
- steps/phase2-build-release-branch.md 1.2 KB
- steps/phase3-bump-versions.md 1.7 KB
- steps/phase4-changelog.md 2.6 KB
- steps/phase5-verify-commit-tag.md 3.0 KB
- steps/phase6-push-tag.md 1.4 KB
- steps/phase7-publish-github-release.md 3.8 KB
- steps/phase8-back-to-main.md 2.1 KB
- steps/phase9-cleanup.md 1.2 KB
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.
- 1mo ago First seen · 124 lines · 211 tokens per session scan A b4d239495ac7
cut-release is a skill published in the GitHub repository delexw/claude-code-trace (380 stars, last pushed today), licensed MIT. It adds 211 tokens to every session and 1,422 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
compiler-commit
Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits with the [compiler] or [rust-compiler] prefix.
merge-seed
Merge upstream React Starter Kit updates (the seed remote) into main, preserving this project's identity, scope, and behavior. Use when asked to sync, pull, or merge the seed / starter kit / upstream template.
git-safety
Git safety rules. INVOKE WHEN: git push, force push, git reset, git clean, destructive git, push force, reset hard. NEVER force push or do destructive git operations.
release-safety
Release safety rules. INVOKE WHEN: yarn release, npm publish, release canary, release packages, publishing, skip checks, skip tests. NEVER skip checks or tests without explicit permission.
commit
Create git commits in the Unovis repo that pass its commitlint rules. Unovis uses a CUSTOM commit format (Type | Scope | Subscope: Sentence-case subject), NOT Conventional Commits, so feat:/fix: will be rejected by the commit-msg hook. Use this whenever staging and committing changes, writing or rewriting a commit…
open-pr
Open a pull request for the Unovis repo with the project's conventions — correct branch off main, the standard commit grouping, and the checklist-style PR body used by the maintainers. Use when asked to open/create/submit a pull request, prepare a branch for review, or write a PR description in this repository.