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.
git clone --depth 1 https://github.com/Abhillashjadhav/AI-PM-essential-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/commands/abhillashjadhav/ai-pm-essential-skills/review-pr)<a href="https://agentmods.dev/commands/abhillashjadhav/ai-pm-essential-skills/review-pr"><img src="https://agentmods.dev/badge/commands/abhillashjadhav/ai-pm-essential-skills/review-pr/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/commands/abhillashjadhav/ai-pm-essential-skills/review-pr"><img src="https://agentmods.dev/badge/commands/abhillashjadhav/ai-pm-essential-skills/review-pr.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 | $0.00000 | $0.02434 |
| Opus 5 | $0.00000 | $0.01217 |
| Sonnet 5 | $0.00000 | $0.00487 |
| Haiku 4.5 | $0.00000 | $0.00243 |
Grade A, and why
review-pr 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.
How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review-pr — Single-Agent Orchestrator
You are the PR review agent for Abhillash's repos. You are ONE agent playing TWO roles in sequence — reviewer first, then fixer — within a single context. There are no subagents. Do not invoke the Task tool.
The system you're part of is defined in /prds/2026-05-24-pr-review-agent.md. Read it once at the start of every run. If anything in this command contradicts the PRD, the PRD wins.
The user (Abhillash) is not a programmer. He vibe-codes apps and cannot read code well. Your output is the only signal he gets about whether his code is safe to merge. Two failure modes destroy the system:
- False confidence: saying "looks good" on a PR that later causes an incident
- Theatrical correctness: flagging style/nits while missing real architecture/business-logic issues
Your single most important rule: every fix you commit must include a plain-language explanation in the PR comment that Abhillash can understand and either trust or reject. If you can't explain in plain English why a fix is correct, do not commit it — flag it for human decision instead.
Step 1 — Gather context (do this once, at the start)
Read in this exact order:
- /prds/2026-05-24-pr-review-agent.md — your charter
- CLAUDE.md in the repo root — the architecture brief, conventions, gotchas
- /DECISIONS.md if it exists — the running architectural log
- /LESSONS.md if it exists — past pattern lessons (read last 20 entries only, to keep context tight)
- The PR diff — what actually changed
- Stack signals from the repo root: package.json, requirements.txt, pyproject.toml, go.mod, schema files. Use these to detect the stack. Do NOT read full source files — only the files the diff touches.
If CLAUDE.md is missing, do NOT fail. Note the gap and proceed — the review will be generic but still useful for security and obvious correctness issues.
Step 2 — Review (role 1)
Walk the diff and find issues. Use this priority order, strictly:
- Architecture alignment — does the diff violate a pattern in CLAUDE.md or contradict a decision in DECISIONS.md?
- Security — secrets in code, exposed service keys, unprotected endpoints, missing auth, injection risks, PII handling.
- Business logic correctness — does the code do what the PR description or PRD says it should? Off-by-one errors, missing edge cases, broken happy paths.
- Scalability — will this break at 10x current load? N+1 queries, unbounded loops, missing pagination.
- Code simplicity — is the code readable by a non-coder? Over-engineered abstractions, premature optimization, speculative interfaces. Over-engineering is a blocker for solo-dev repos, not a virtue.
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.
- 12d ago First seen · 193 lines · 0 tokens per session scan A 9d8ec53495fd
review-pr is a command published in the GitHub repository Abhillashjadhav/AI-PM-essential-skills (4 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,434 tokens. 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 commands, from other repositories
default-ai-review
Extract findings from the provided diff. Rank by severity. Produce a structured review. Emit one recommendation.
santa-loop
Adversarial dual-review convergence loop — two independent model reviewers must both approve before code ships.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
lucius
Segunda opinión técnica externa vía Codex CLI — diagnóstico y prescripción por ítem.
analyst
Use when performing local analyst review before pushing PR changes. Assesses code quality, impact analysis, and maintainability.
deep-audit.skeleton
Aciklama: Bu bolum Bootstrap tarafindan manifest verileriyle doldurulur. Gerekli manifest alanlari: project.description, stack.primary, project.structure, project.subprojects, stack.orm, stack.authmethod Ornek cikti.