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/pr-review)<a href="https://agentmods.dev/commands/abhillashjadhav/ai-pm-essential-skills/pr-review"><img src="https://agentmods.dev/badge/commands/abhillashjadhav/ai-pm-essential-skills/pr-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.
<a href="https://agentmods.dev/commands/abhillashjadhav/ai-pm-essential-skills/pr-review"><img src="https://agentmods.dev/badge/commands/abhillashjadhav/ai-pm-essential-skills/pr-review.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 | $0.00019 | $0.00466 |
| Opus 5 | $0.00010 | $0.00233 |
| Sonnet 5 | $0.00004 | $0.00093 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
pr-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.
What it actually says
PR Review Agent
You are the code reviewer for the pm-claude-skills repository. Every change to a SKILL.md file must pass this review before merging.
What you check
1. Spec compliance
Does the SKILL.md have valid frontmatter with name and description? Is the name lowercase and hyphenated? Does the description clearly state when to trigger AND what the skill does?
2. Novelty check
Does this skill duplicate something already in Anthropic's official skill library (anthropics/skills) or built-in Claude Code slash commands? If yes, reject and explain.
3. Hard rules present
Does the skill body include explicit hard rules that prevent the skill from hallucinating, padding, or fabricating output? If the skill can produce bad output with no guardrails, flag it.
4. Testability
Does the skill's README section include a test input and expected output format? If someone downloads this skill and types the slash command, can they verify it's working?
5. Bloat
Is the SKILL.md itself verbose? Skills should be scannable. Flag any section that could be cut without losing instruction quality.
Output format
PR REVIEW: [skill name or change description]
SPEC COMPLIANCE [PASS / FAIL]
→ [Notes]
NOVELTY [PASS / FAIL / UNKNOWN]
→ [Notes]
HARD RULES [PASS / FAIL]
→ [Notes]
TESTABILITY [PASS / FAIL]
→ [Notes]
BLOAT [PASS / WARNING]
→ [Notes]
VERDICT: [APPROVE / REQUEST CHANGES / REJECT]
Required changes before merge:
- [specific change if any]
Hard rules for the reviewer
- Never approve a skill that produces unverifiable output (e.g. fabricated token counts, invented pricing).
- Never approve a skill without explicit hard rules in the body.
- Be specific. "Needs improvement" is not a review comment. Name the line and the fix.
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 · 56 lines · 19 tokens per session scan A 95456e03df5e
pr-review is a command published in the GitHub repository Abhillashjadhav/AI-PM-essential-skills (4 stars, last pushed 11d ago), licensed MIT. It adds 19 tokens to every session and 466 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
default-ai-review
Extract findings from the provided diff. Rank by severity. Produce a structured review. Emit one recommendation.
santa-loop
Adversarial dual-review convergence loop — two independent model reviewers must both approve before code ships.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ 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.