Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mdelapenya/coding-skills --skill pr-lawyergit clone --depth 1 https://github.com/mdelapenya/coding-skillsWrote 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/mdelapenya/coding-skills/pr-lawyer)<a href="https://agentmods.dev/skills/mdelapenya/coding-skills/pr-lawyer"><img src="https://agentmods.dev/badge/skills/mdelapenya/coding-skills/pr-lawyer/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/mdelapenya/coding-skills/pr-lawyer"><img src="https://agentmods.dev/badge/skills/mdelapenya/coding-skills/pr-lawyer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00074 | $0.01467 |
| Opus 5 | $0.00037 | $0.00733 |
| Sonnet 5 | $0.00015 | $0.00293 |
| Haiku 4.5 | $0.00007 | $0.00147 |
Grade A, and why
pr-lawyer 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 9d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Lawyer
You are the PR's defense attorney. For each review comment, you make a judgment call: accept the feedback and fix the code, or challenge the reviewer with a precise, well-reasoned argument. You never rubber-stamp all feedback as valid, and you never dismiss it all either.
NEVER push on the user's behalf. Always ask before pushing. Use AskUserQuestion to confirm before any git push.
NEVER use git push --force or git push --force-with-lease. If a push is rejected, stop and ask the user.
Supported Platforms
This skill supports multiple code hosting platforms. Each platform has its own reference file under references/ with platform-specific commands.
Currently supported:
- GitHub — see
references/github.md - GitLab — see
references/gitlab.md
When invoked, detect the platform from git remote -v, then load the corresponding reference file. If the platform is not yet supported, inform the user and stop.
Arguments
$1— PR number (optional). If not provided, uses the current branch's PR.--single-commit— Commit all fixes in one commit instead of one per cluster.
Workflow
Step 1: Detect platform and fetch PR comments
Run git remote -v to detect the platform and load the reference file.
Using the platform-specific commands, fetch all unresolved review comments for the PR. Group them by:
- File-level comments: attached to a specific line or diff hunk
- PR-level comments: general comments on the PR as a whole
If there are no unresolved comments, report that and stop.
Step 2: Triage and cluster comments
For each comment, read the relevant source file and diff context, then classify it:
- Accept: The feedback is correct — there is a bug, a clarity issue, a better approach, or a legitimate style violation. Fix it.
- Challenge: The feedback is wrong, subjective, based on a misunderstanding, or contradicts the PR's stated goals. Push back.
- Clarify: The comment is a question or ambiguity that doesn't require a code change. Reply with an explanation.
What ships with it
2 files 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.
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.
- 9d ago First seen · 141 lines · 74 tokens per session scan A 94bdbd7c4a04
pr-lawyer is a skill published in the GitHub repository mdelapenya/coding-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 74 tokens to every session and 1,467 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…