skillsaw: Skill for Claude Code

.agents/skills/skillsaw-release/SKILL.md

skillsaw-release is a skill for Claude Code from stbenjam/skillsaw. It costs 31 tokens per session (1,456 once invoked), scanned A, original, Apache-2.0.

A release procedure for the Skillsaw Python tool. Releasing means increasing its version, writing release notes, and publishing the package to PyPI, the public package index used to install Python software.

In plain words
What is it for?
Use it when preparing a new Skillsaw release. It checks branch state and test results, updates release information, and publishes the package.
Why use it?
It provides the required checks before publishing and helps avoid releasing from an untested or incomplete main branch.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is stbenjam/skillsaw's own configuration. It tells Claude Code how to work on skillsaw 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 skillsaw configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/bump-version.sh [version].

Part of the skillsaw plugin — 14 skills shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to stbenjam/skillsaw. 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/stbenjam/skillsaw/main/.agents/skills/skillsaw-release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/stbenjam/skillsaw

Made for: Claude Code.

Or install skillsaw, the plugin that ships this one along with the rest of its 14 skills.

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 skillsaw-release

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/stbenjam/skillsaw/skillsaw-release"><img src="https://agentmods.dev/badge/skills/stbenjam/skillsaw/skillsaw-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,456 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 $0.00031 $0.01456
Opus 5 $0.00015 $0.00728
Sonnet 5 $0.00006 $0.00291
Haiku 4.5 $0.00003 $0.00146

Measured 6d ago against content hash 32913dd64630, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

skillsaw-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 6d 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.

.agents/skills/skillsaw-release/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

skillsaw Release

Follow these steps to release a new version of the skillsaw linter.

Step 1: Run pre-flight checks

Before releasing, verify:

  1. Check you are on the main branch, it is clean (git status), and up to date with origin/main (git pull origin main).

  2. Verify the current main commit has a successful push run of the Tests workflow. Do not accept the reduced PR test run: pull requests run Python 3.9 plus the 3.14 coverage job, while a main push must have passed Python 3.9, 3.10, 3.11, 3.12, 3.13, and 3.14. The workflow run must test the exact HEAD being released:

    main_sha=$(git rev-parse HEAD)
    run_id=$(gh run list --workflow test.yml --branch main --commit "$main_sha" \
      --event push --status success --limit 1 --json databaseId --jq '.[0].databaseId')
    test -n "$run_id" && test "$run_id" != "null" || {
      echo "No successful Tests workflow run exists for main at $main_sha" >&2
      exit 1
    }
    gh run view "$run_id" --json jobs | jq -e '
      [.jobs[] | select(.name | test("^test \\(3\\.(9|10|11|12|13|14)\\)$"))]
      | length == 6 and all(.[]; .conclusion == "success")
    ' >/dev/null || {
      echo "The full Python 3.9–3.14 main test matrix did not pass" >&2
      exit 1
    }
    
  3. All local tests pass: make test.

  4. Formatting is clean: make lint.

  5. Determine which version to release. If none was specified, review the commits since the last tag. Add a minor bump for new features or rules; keep a patch bump for fixes only (the bump script defaults to patch when given no argument).

The Makefile creates the .venv and installs dependencies automatically; run make venv first if needed.

Step 2: Run the bump script

Run the bump script:

.venv/bin/python -c "pass" || make venv
bash scripts/bump-version.sh [version]

Read the full file on GitHub · 154 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. 6d ago Changed · +1 lines 32913dd64630
  2. 12d ago First seen · 153 lines · 31 tokens per session scan A 1006f3bb246e

Subscribe to this mod's changes

skillsaw-release is a skill published in the GitHub repository stbenjam/skillsaw (66 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 1,456 once invoked, about $0.0002 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.