harness-score: Skill for Claude Code

.agents/skills/pr-release-audit/SKILL.md

pr-release-audit is a skill for Claude Code, Codex from paladini/harness-score. It costs 70 tokens per session (1,588 once invoked), scanned A, original, MIT.

A review procedure for checking whether a pull request and its related release materials are ready. A pull request is proposed code, while release materials include items such as changelogs, version data, documentation, and release notes.

In plain words
What is it for?
Use it to audit correctness, tests, architecture, security, compatibility, documentation, CI, websites, changelogs, and release readiness.
Why use it?
It checks the whole change lifecycle instead of judging only the code diff, while avoiding claims that something was released without evidence.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

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

Reuse

Borrowing it

Nothing to install: this file belongs to paladini/harness-score. 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/paladini/harness-score/main/.agents/skills/pr-release-audit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/paladini/harness-score

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 pr-release-audit

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/paladini/harness-score/pr-release-audit"><img src="https://agentmods.dev/badge/skills/paladini/harness-score/pr-release-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,588 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 $0.00070 $0.01588
Opus 5 $0.00035 $0.00794
Sonnet 5 $0.00014 $0.00318
Haiku 4.5 $0.00007 $0.00159

Measured yesterday against content hash 2833036d8ef2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

pr-release-audit 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 yesterday.

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/pr-release-audit/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR and Release Audit

Perform an evidence-backed audit of the complete change lifecycle. Treat the repository instructions, current branch state, PR metadata, vendor contracts, CI, generated site, and release artifacts as separate evidence surfaces.

Authority and safety

  • Read AGENTS.md, contributor guidance, release guidance, and relevant local rules before changing files.
  • Preserve unrelated worktree changes. Inspect status before and after edits.
  • Review and diagnostics are read-only by default. Implement requested fixes, documentation, or release artifacts when they are in scope.
  • Never merge, tag, publish packages, create a GitHub release, close issues, or send external messages unless the user explicitly authorizes that action.
  • Do not claim that a change is released, deployed, public, or complete until the corresponding public state has been independently verified.

1. Establish the change boundary

  1. Identify the repository, PR number, base and head commits, author, linked issue, labels, changed files, and current review/check status.
  2. Compare the PR with its actual base, not with a stale local branch.
  3. Classify every changed file as implementation, test, configuration, docs, generated output, release metadata, or unrelated noise.
  4. Record the initial worktree state and do not overwrite unrelated changes.

2. Review implementation and structure

Check behavior before style:

  • correctness, error handling, edge cases, and backward compatibility;
  • public API and data-shape contracts, including sync/async behavior;
  • path traversal, symlinks, generated files, platform differences, and incomplete or unreadable inputs when relevant;
  • security, performance, determinism, and dependency/supply-chain impact;
  • whether the design adds the smallest material change or creates a new structural coupling;
  • tests for the changed behavior, regression cases, and negative cases.

Reproduce important claims with the project commands. Do not treat a green lint job as proof that behavior, documentation, or release metadata is right.

Read the full file on GitHub · 157 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. yesterday Changed · +8 lines 2833036d8ef2
  2. 2d ago First seen · 149 lines · 70 tokens per session scan A 74c5ba92188d

Subscribe to this mod's changes

pr-release-audit is a skill published in the GitHub repository paladini/harness-score (409 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 1,588 once invoked, about $0.0003 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 2026-09-06.