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 agentmods add skills/auerbachb/claude-code-config/pr-review-helpnpx skills add auerbachb/claude-code-config --skill pr-review-helpgit clone --depth 1 https://github.com/auerbachb/claude-code-configWrote 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/auerbachb/claude-code-config/pr-review-help)<a href="https://agentmods.dev/skills/auerbachb/claude-code-config/pr-review-help"><img src="https://agentmods.dev/badge/skills/auerbachb/claude-code-config/pr-review-help.svg" alt="Measured on agentmods" 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 | $0.00061 | $0.04079 |
| Opus 5 | $0.00030 | $0.02039 |
| Sonnet 5 | $0.00012 | $0.00816 |
| Haiku 4.5 | $0.00006 | $0.00408 |
Grade C, and why
pr-review-help scanned grade C with 1 finding 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- A safety warning block: `SAFETY: Do NOT delete, overwrite, move, or modify .env files — anywhere, any repo. Exception: template files matching .env.<example|sample|template> (case-insensitive) are committed, non-secret How it starts
The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an executive PR review assistant operating with a CTO + CPO + Chief Data Scientist lens. Your job is to help leadership answer: Should this PR merge now, merge behind a flag, be split, or be held?
Resolve the optional PM config parser before fetching strategic context:
resolve_script() {
local name="$1" candidate
for candidate in \
"$HOME/.claude/skills-worktree/.claude/scripts/$name" \
"$HOME/.claude/scripts/$name" \
".claude/scripts/$name"; do
if [[ -x "$candidate" ]]; then echo "$candidate"; return 0; fi
done
return 1
}
PM_CONFIG_GET_SH=$(resolve_script pm-config-get.sh || true)
if [[ -z "$PM_CONFIG_GET_SH" ]]; then
echo "DEGRADED: pm-config-get.sh not found (checked all three paths) — OKR context unavailable, continuing with README context" >&2
fi
This is not a code-correctness review. Assume CodeRabbit, Greptile, and automated tests already handled low-level issues. Do not duplicate their findings unless something materially affects the ship/no-ship decision.
Evidence rule: Every concern must reference concrete evidence from the diff, issue, PR discussion, or repo context. If there is no evidence, do not speculate. Generic boilerplate like "possible performance risk" without a specific diff reference is prohibited. It is acceptable to say "insufficient evidence" when repo artifacts do not support a confident judgment.
Parse $ARGUMENTS as space-separated PR references. Strip # prefixes to get bare PR numbers. If no arguments provided, show usage:
Usage: /pr-review-help #123 #456 #789
Pass one or more PR numbers to get an executive strategic review.
Optional automated invoke (issue #362): When ENABLE_PR_REVIEW_HELP=1 in .claude/pm-config.md Complexity triggers, maybe-trigger-ai-review.sh may post a PR comment /pr-review-help #N (with the PR number) to trigger an executive review of that PR. This is separate from manually passing #N arguments here.
Step 1: Fetch Shared Repo Context (parent agent — once)
Before spawning subagents, fetch shared context that all PR reviews need. This runs once in the parent agent and is passed to each subagent.
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.
- 4d ago First seen · 325 lines · 61 tokens per session scan C bfcc47a899bf
pr-review-help is a skill published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed 5d ago), licensed MIT. It adds 61 tokens to every session and 4,079 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
fixer
Surgical code fixer for Bug Hunter. Implements minimal, precise fixes for verified bugs. Uses doc-lookup (Context Hub + Context7) to verify correct API usage in patches. Respects fix strategy classifications (safe-autofix vs manual-review vs larger-refactor).
referee
Final arbiter for Bug Hunter. Receives Hunter findings and Skeptic challenges, independently re-reads code, and delivers authoritative verdicts with CVSS scoring and proof-of-concept generation for security findings.
do-competitively
Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis.
adr
Create and manage Architecture Decision Records. Documents significant technical decisions with context, alternatives, and consequences. Also supports evaluate (assess proposals) and design (system design) modes.
deploy-checklist
Pre-deployment verification checklist. Generates customized checklists based on tech-stack with rollback triggers. Auto-invoked by /draft:upload.
judge-with-debate
Evaluate solutions through multi-round debate between independent judges until consensus.