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.
curl -O https://raw.githubusercontent.com/hardwood-hq/hardwood/main/.claude/skills/hardwood-pr-git/SKILL.mdgit clone --depth 1 https://github.com/hardwood-hq/hardwoodWrote 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.
[](https://agentmods.dev/skills/hardwood-hq/hardwood/hardwood-pr-git)<a href="https://agentmods.dev/skills/hardwood-hq/hardwood/hardwood-pr-git"><img src="https://agentmods.dev/badge/skills/hardwood-hq/hardwood/hardwood-pr-git/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.
<a href="https://agentmods.dev/skills/hardwood-hq/hardwood/hardwood-pr-git"><img src="https://agentmods.dev/badge/skills/hardwood-hq/hardwood/hardwood-pr-git.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
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 →
- high Tool Misuse · line 232 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 356 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 391 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 384 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00163 | $0.05122 |
| Opus 5.5 | $0.00065 | $0.02049 |
| Sonnet 5.5 | $0.00033 | $0.01024 |
| Haiku 4.5 | $0.00016 | $0.00512 |
Grade A, and why
hardwood-pr-git 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.
How it starts
The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hardwood PR git surgery
History rewriting on hardwood-hq/hardwood PRs. The mechanics are mechanical but unforgiving: a
careless --amend silently replaces a contributor's committer identity with the maintainer's, and
git's default comment character silently deletes the issue key every Hardwood commit subject starts
with.
0. The # rule — read this before running any git command that commits
Every Hardwood commit subject starts with #, and # is git's comment character. Any git
operation that runs a commit message through editor cleanup deletes every line beginning with #
— which is the entire subject line.
What that does, in the two shapes it takes:
| Message shape | What git does | What you see |
|---|---|---|
#9 Subject + body |
Subject deleted, body's first paragraph is promoted to subject | 01d5773 The write path's measurement stopped at the shape stage 17… |
#9 Subject, no body |
Message becomes empty | Aborting commit due to empty commit message. → error: could not commit staged changes → the todo is rescheduled, and git rebase --continue loops forever without advancing |
The second shape is the "the rebase aborts for no reason" symptom. A --continue loop that never
terminates is not a stuck rebase — it is git refusing to write an empty commit, over and over.
The fix, applied once per clone. All worktrees of a clone share it:
git config core.commentChar ';'
This is one of two clone-local settings this repo needs; the other is in
The phantom dirty tree. Both live in
.git/config, which is not version-controlled — a fresh clone starts without them. Both are
documented for contributors under Local git configuration in
CONTRIBUTING.md; keep the two in sync.
Also pass it explicitly on every rewrite command, so the recipes still work in a fresh clone or a CI checkout where the config has not been set:
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.
- 1mo ago Changed · -1 lines 18d022ee44db
- 2mo ago First seen · 392 lines · 163 tokens per session scan A bf2497aab49a
hardwood-pr-git is a skill published in the GitHub repository hardwood-hq/hardwood (417 stars, last pushed 4d ago), licensed Apache-2.0. It adds 163 tokens to every session and 5,122 once invoked, about $0.0007 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.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…