Borrowing it
Nothing to install: this file belongs to handarbeit/fabrik. 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/handarbeit/fabrik/main/.claude/skills/cut-release/SKILL.mdgit clone --depth 1 https://github.com/handarbeit/fabrikWrote 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/handarbeit/fabrik/cut-release)<a href="https://agentmods.dev/skills/handarbeit/fabrik/cut-release"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/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/handarbeit/fabrik/cut-release"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/cut-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Tool Misuse · line 92 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 100 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00028 | $0.01633 |
| Opus 5 | $0.00014 | $0.00816 |
| Sonnet 5 | $0.00006 | $0.00327 |
| Haiku 4.5 | $0.00003 | $0.00163 |
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 9d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cut Release
Cut a new Fabrik release. Your job is to author the release notes; scripts/cut-release.sh does everything else (commit, tag, push as @arbeithand, watch workflow, verify identity, file doc-update issue).
Usage
Invoked as /cut-release or /cut-release v0.0.67. If no version is provided, suggest the next patch bump from the current latest tag.
Steps
1. Determine version
- Find the latest tag:
git describe --tags --abbrev=0 - If a version arg was provided, validate semver with
vprefix and that it's greater than the latest tag. - If no version arg, suggest the next patch bump and proceed.
2. Author release notes
This is the part requiring judgment — do not delegate it.
git log <last-tag>..HEAD --onelineto enumerate commits since the last release.- Group user-facing changes by category: Features, Fixes, Improvements, Internal. Omit empty sections.
- Ignore merge commits and
Co-Authored-Bylines. - Collapse internal churn into a single line under Internal. Don't enumerate refactors / test additions.
- Write the notes to
release-notes/<version>.md(one file per release, archived in-tree). The release workflow reads this path directly via${{ github.ref_name }}— there is no repo-rootrelease-notes.mdand you should not create one (it is.gitignored).
Use this schema:
# Fabrik <version>
## Summary
<1-3 sentences. Punchy headline themes only. This block is what the Discussions
announcement post will contain — everything else lives on the GitHub Release page.>
## Features
- Description (#issue)
## Fixes
- Description (#issue)
## Improvements
- Description (#issue)
## Internal
- One-line summary of internal churn
## Upgrading
\```bash
# Auto-upgrade from a running Fabrik instance
# Fabrik checks for new releases each poll cycle and upgrades automatically with --auto-upgrade
# Or download directly (auto-detects OS and architecture)
gh release download --repo handarbeit/fabrik \
--pattern "fabrik_*_$(uname -s | tr A-Z a-z)_$(uname -m | sed 's/x86_64/amd64/' | sed 's/aarch64/arm64/').tar.gz" \
-O - | tar xz
\```
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.
- 9d ago First seen · 115 lines · 28 tokens per session scan A 9f9565057681
cut-release is a skill published in the GitHub repository handarbeit/fabrik (22 stars, last pushed yesterday), licensed Apache-2.0. It adds 28 tokens to every session and 1,633 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 2026-08-30.
Other skills, from other repositories
flame-harness-submit
Phase 10 — upload store text metadata + categories via fastlane, then pause with exact manual steps for the final iOS review submission and Android production promotion.
flame-harness-build
Phase 8 — bootstrap signing credentials, generate fastlane config from templates, and build + upload signed IPA (TestFlight) and AAB (internal track).
no-mistakes
Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a change before it reaches upstream.
changelog-automation
Git history'den otomatik changelog, semantic versioning, release notes, conventional commits.
git-workflow
Guided git workflows: prepare PRs, clean up branches, resolve merge conflicts, handle monorepo tags, squash-and-merge patterns. Use when asked to prepare a PR, clean branches, resolve conflicts, or tag a release.
github-release
Prepare and publish GitHub releases. Sanitizes code for public release (secrets scan, personal artifacts, LICENSE/README validation), creates version tags, and publishes via gh CLI. Trigger with 'release', 'publish', 'open source', 'prepare for release', 'create release', or 'github release'.