hardwood: Skill for Claude Code

.claude/skills/hardwood-address-review/SKILL.md

hardwood-address-review is a skill for Claude Code from hardwood-hq/hardwood. It costs 75 tokens per session (2,096 once invoked), scanned A, original, Apache-2.0.

A workflow for handling findings from a code-review document for a Hardwood pull request. A pull request is a proposed code change submitted for review.

In plain words
What is it for?
Use it to check out a pull-request branch, apply requested fixes, present decisions to the maintainer, mark findings as addressed, and commit the result without pushing it.
Why use it?
It keeps review findings connected to the code changes, decisions, and review checklist instead of leaving them as unresolved comments.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool.

This is hardwood-hq/hardwood's own configuration. It tells Claude Code how to work on hardwood 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 hardwood configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hardwood-hq/hardwood. 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/hardwood-hq/hardwood/main/.claude/skills/hardwood-address-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/hardwood-hq/hardwood

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 hardwood-address-review

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/hardwood-hq/hardwood/hardwood-address-review"><img src="https://agentmods.dev/badge/skills/hardwood-hq/hardwood/hardwood-address-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,096 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 warn 7 Sept 2026
SkillSpector: 3 findings, up to medium

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 →

  • medium Excessive Agency · line 22
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 48
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • low Excessive Agency · line 89
    Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
    Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 $0.00075 $0.02096
Opus 5 $0.00037 $0.01048
Sonnet 5 $0.00015 $0.00419
Haiku 4.5 $0.00007 $0.00210

Measured 12d ago against content hash e38c2fc97241, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

hardwood-address-review 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 12d 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/hardwood-address-review/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hardwood address-review

Companion to the hardwood-review skill. The review skill produces _reviews/pr-<N>-review.md; this skill consumes it — implements the fixes, ticks the checkboxes, and commits.

Workflow

1. Identify the PR

Parse the user's request for a PR number (e.g. "449", #449, a PR URL). If they didn't supply one, look for the most recently modified file matching _reviews/pr-*-review.md and confirm with the user.

2. Sanity checks

Before touching the working tree:

  • Working tree state. Run git status --porcelain.
    • Clean: proceed.
    • Dirty, but the only entries are under .claude/ or _reviews/ (Claude meta-state — session settings, in-flight skill drafts, review files): proceed without asking. These paths don't touch hardwood project source and will travel safely with git checkout.
    • Anything else modified or untracked: stop and tell the user. Don't risk their in-progress work.
  • Review file exists. _reviews/pr-<N>-review.md must be readable. If missing, suggest running /hardwood-review <N> first.
  • Find the issue number. gh pr view <N> --json title -q .title — the PR title should start with #<issue> … per the project's commit convention. Extract that number for the commit prefix. If the title doesn't have one, ask the user which issue number to use; don't invent one.

3. Check out the PR branch

Preferred: gh pr checkout <N>. This creates or updates a local branch tracking the PR.

Fallback when gh pr checkout fails (typically Host key verification failed in sandboxed environments where SSH to GitHub isn't set up): fetch the fork directly via HTTPS.

gh pr view <N> --json headRepositoryOwner,headRepository,headRefName \
    -q '"https://github.com/" + .headRepositoryOwner.login + "/" + .headRepository.name + ".git " + .headRefName'
# → e.g. https://github.com/muhannd2004/hardwood.git 386-fix-text-cut-off
git fetch <https-url> <head-ref>:pr-<N>
git checkout pr-<N>

Read the full file on GitHub · 142 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. 12d ago First seen · 142 lines · 75 tokens per session scan A e38c2fc97241

Subscribe to this mod's changes

hardwood-address-review is a skill published in the GitHub repository hardwood-hq/hardwood (372 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 2,096 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

pull-request-authoring

Workflow for creating WP Rig pull requests that match the repository template, including release-specific guidance for develop-to-master merges.

wprig/wprig · 23 tokens

review-implement-phase

Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.

prisma/orm · 38 tokens

engram-branch-pr

PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.

Gentleman-Programming/engram · 37 tokens

verify-behavior

Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…

nicknisi/dotfiles · 68 tokens

github-contributor

End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…

daymade/claude-code-skills · 133 tokens

revdiff

Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…

umputun/revdiff · 248 tokens