fsl: Skill for Claude Code

.claude/skills/release/SKILL.md

release is a skill for Claude Code from ymm-oss/fsl. It costs 58 tokens per session (3,914 once invoked), scanned A, original, Apache-2.0.

A skill for managing a Git-based path from short-lived branches to the main branch, production, and an exact version tag.

In plain words
What is it for?
Use it to follow the project's branch rules, promote changes to production, create releases, and handle production fixes.
Why use it?
It separates ordinary code integration from the stronger decision to release software, reducing mistakes such as tagging the wrong commit or promoting only part of the code.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

This is ymm-oss/fsl's own configuration. It tells Claude Code how to work on fsl itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fsl configures →

View source ↗ ymm-oss/fsl
Reuse

Borrowing it

Nothing to install: this file belongs to ymm-oss/fsl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ymm-oss/fsl/main/.claude/skills/release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ymm-oss/fsl

Made for: Claude Code.

Wrote 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.

agentmods badge for release

README.md
[![agentmods](https://agentmods.dev/badge/skills/ymm-oss/fsl/release/github.svg)](https://agentmods.dev/skills/ymm-oss/fsl/release)
Your own site
<a href="https://agentmods.dev/skills/ymm-oss/fsl/release"><img src="https://agentmods.dev/badge/skills/ymm-oss/fsl/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.

agentmods 80×15 button for release

Your own site · 80×15
<a href="https://agentmods.dev/skills/ymm-oss/fsl/release"><img src="https://agentmods.dev/badge/skills/ymm-oss/fsl/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,914 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.03914
Opus 5.5 $0.00023 $0.01566
Sonnet 5.5 $0.00012 $0.00783
Haiku 4.5 $0.00006 $0.00391

Measured 1mo ago against content hash aab87ebfdf36, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 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.

.claude/skills/release/SKILL.md · 303 lines

How it starts

The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Operate the release flow

Treat CI-green pull requests as integration evidence and release promotion as a separate, stronger decision:

short-lived branch -> main -> production -> vX.Y.Z
                         ^          ^
                  integration   release readiness

Keep main as the default branch. Do not create develop or pre-production. Use a temporary release/vX.Y branch only when main must advance while an exact candidate is stabilized.

Read docs/design/RELEASE.md completely before promote or cut; it is the authoritative command-level procedure. Keep it and this lifecycle contract aligned in the same pull request.

Non-negotiable rules

  • Merge product and quality changes into main through pull requests.
  • Accept changes into production only through a release-promotion pull request.
  • Never tag main; tag the exact production commit approved for release.
  • Never selectively promote commits from main. Promote its complete tree.
  • Never force-move or reuse a published tag.
  • Publish only the tag-driven GitHub Release. Do not publish the frozen Python compatibility reference to PyPI or the Rust crates to crates.io.
  • Release native binaries for macOS arm64, Linux x64, Linux arm64, and Windows x64 only. Intel macOS (macos-x64) is not supported.
  • Populate the GitHub Release body from the matching non-empty changelog section.
  • Fix defects upstream in main first, then promote downstream. Use the hotfix exception only when unreleased main cannot safely ship.
  • Stop before a push, production merge, tag, release publication, or branch protection change unless the user explicitly authorized that exact action.

Route the invocation

Interpret $ARGUMENTS as one of these operations. If the operation or version is missing, inspect the repository state and ask only for the decision that cannot be derived safely.

Operation Outcome
adopt Bootstrap and protect production
integrate Merge a feature, fix, or quality improvement into main
promote Prove the current release candidate and propose main -> production
cut X.Y.Z Prepare, promote, tag, and observe version X.Y.Z
hotfix X.Y.Z Patch the released line without pulling unreleased main into production

Read the full file on GitHub · 303 lines

Changes

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.

  1. 1mo ago Changed · +7 lines aab87ebfdf36
  2. 1mo ago Changed · -2 lines a744a94da1df
  3. 2mo ago First seen · 298 lines · 58 tokens per session scan A f5a5fae1a66f

Subscribe to this mod's changes

release is a skill published in the GitHub repository ymm-oss/fsl (35 stars, last pushed today), licensed Apache-2.0. It adds 58 tokens to every session and 3,914 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

mem0-test-integration

Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…

mem0ai/mem0 · 207 tokens

mem0-integrate

Integrate Mem0 into an existing repository using a goal-driven, TDD pipeline. Detects the repo's language automatically and asks the user to pick between Mem0 Platform (managed) and Mem0 Open Source (self-hosted). Writes failing tests before any implementation. Produces a local feature branch plus .mem0-integration/…

mem0ai/mem0 · 188 tokens

prep-repo

Prepare an existing project for GitHub or public release with scope-appropriate checks for sensitive data, documentation, installation, tests and release artifacts. Separate release blockers from polish, preserve existing authorization, and verify the published result only when publishing is requested. Not for…

KerberosClaw/kc_ai_skills · 64 tokens

pypi-release

This skill should be used when releasing tunacode-cli to PyPI. It keeps the existing local release checks, then hands the actual PyPI upload to a GitHub Actions workflow that uses the repository's PYPIAPITOKEN secret.

alchemiststudiosDOTai/tunacode · 52 tokens

migrate-rename

Evolutionary file renaming with wrapper files, plus the terse MOVED-stub standard for whole folder/file moves. Enables renames without hard breaks — references are organically updated through usage.

ellmos-ai/skills · 42 tokens

reissverschluss-merge

Reißverschluss-Verfahren (englisch: zipper merge) für sehr konfliktreiche Merges: Wenn zwei divergente Branches oder ein PR und sein Zielbranch BEIDE wertvolle, unvereinbar erscheinende Änderungen tragen, wird nicht pauschal eine Seite gewählt, sondern Abschnitt für Abschnitt verglichen, per Entscheidungstabelle…

ellmos-ai/skills · 189 tokens