codex-harness: Skill for Claude Code

.codex/skills/x-release-harness/SKILL.md

release-harness is a skill for Claude Code, Codex from Chachamaru127/codex-harness. It costs 43 tokens per session (1,251 once invoked), scanned A, original, MIT.

A release workflow for the Claude Code Harness project. It combines the version change, changelog update, release notes, and Git tag into one release process.

In plain words
What is it for?
Use it to create patch or minor harness releases, inspect recent commits, prepare release notes, update the version, and create a tag.
Why use it?
It reduces the manual coordination needed to prepare a harness release and checks the repository’s recent changes first. It is intended for harness releases, not general release planning.

Skill for Claude CodeCodex

Written for Claude Code and Codex: allowed-tools in frontmatter, but also installed under .codex/. Also seen: mentions Claude Code.

This is Chachamaru127/codex-harness's own configuration. It tells Claude Code and Codex how to work on codex-harness 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 codex-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Chachamaru127/codex-harness. 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/Chachamaru127/codex-harness/main/.codex/skills/x-release-harness/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Chachamaru127/codex-harness

Made for: Claude Code, Codex.

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-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/chachamaru127/codex-harness/x-release-harness.svg)](https://agentmods.dev/skills/chachamaru127/codex-harness/x-release-harness)
Your own site
<a href="https://agentmods.dev/skills/chachamaru127/codex-harness/x-release-harness"><img src="https://agentmods.dev/badge/skills/chachamaru127/codex-harness/x-release-harness.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,251 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.
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 $0.00043 $0.01251
Opus 5 $0.00022 $0.00626
Sonnet 5 $0.00009 $0.00250
Haiku 4.5 $0.00004 $0.00125

Measured 7d ago against content hash 19e9fc873744, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

release-harness 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 7d 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.

.codex/skills/x-release-harness/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Harness Skill

Automates the claude-code-harness release process.

Quick Reference

  • "Release a new harness version" -> /release-harness
  • "Bump patch version" -> /release-harness patch
  • "Create a minor release" -> /release-harness minor

Execution Flow

Step 1: Change Verification

Run in parallel:

  1. git status - Check uncommitted changes
  2. git diff --stat - List changed files
  3. git log --format="%h|%s|%an|%ad" --date=short -10 - Recent commit history (structured)

Git Log Flags (CC 2.1.30+)

Use structured log output for release note generation.

Commit List for Release Notes
# Structured format commit list
git log --format="%s" vPREV..HEAD

# Exclude merge commits (actual changes only)
git log --cherry-pick --no-merges --format="%s" vPREV..HEAD

# Detailed info (with author and date)
git log --format="%h|%s|%an|%ad" --date=short vPREV..HEAD
Key Use Cases
Use Case Flags Effect
Release note generation --format="%s" Extract commit messages only
Exclude merges --cherry-pick --no-merges Actual commits only
Detailed list --format="%h|%s|%an|%ad" Structured detailed info
Changed files --raw Impact analysis

Step 2: Version Determination

Check current version:

cat VERSION

Determine version based on changes (Semantic Versioning):

  • patch (x.y.Z): Bug fixes, minor improvements
  • minor (x.Y.0): New features (backward compatible)
  • major (X.0.0): Breaking changes

Ask user: "What should the next version be? (e.g., 2.5.23)"

Step 3: CHANGELOG Update (JP + EN)

Important: Focus on user-facing changes. Keep internal fixes brief.

Update both CHANGELOG_ja.md and CHANGELOG.md.

CHANGELOG Rules
Change Type How to Document
User-facing impact What's Changed + Before/After table
New feature Added section, concise
Internal (CI/test/docs) Internal section, one line
Bug fix (user-facing) Fixed section
Bug fix (internal only) Omit or merge into Internal

Read the full file on GitHub · 201 lines

Files

What ships with it

1 file 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.

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. 7d ago First seen · 201 lines · 43 tokens per session scan A 19e9fc873744

Subscribe to this mod's changes

release-harness is a skill published in the GitHub repository Chachamaru127/codex-harness (2 stars, last pushed 6mo ago), licensed MIT. It adds 43 tokens to every session and 1,251 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 2026-08-31.