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 saitarrun/Devforge-ai --skill pr-reviewgit clone --depth 1 https://github.com/saitarrun/Devforge-aiWrote 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/saitarrun/devforge-ai/pr-review)<a href="https://agentmods.dev/skills/saitarrun/devforge-ai/pr-review"><img src="https://agentmods.dev/badge/skills/saitarrun/devforge-ai/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/skills/saitarrun/devforge-ai/pr-review"><img src="https://agentmods.dev/badge/skills/saitarrun/devforge-ai/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 | $0.00064 | $0.02148 |
| Opus 5.5 | $0.00026 | $0.00859 |
| Sonnet 5.5 | $0.00013 | $0.00430 |
| Haiku 4.5 | $0.00006 | $0.00215 |
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 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Pull Request Code Review
Multi-angle code review using 5 parallel agents + confidence scoring. Audits CLAUDE.md compliance, detects bugs, checks git history, reviews prior feedback, validates comment guidance. Filters issues by confidence (≥80) to reduce false positives.
Process Overview
1. Eligibility check (Haiku)
├─ Skip if: closed, draft, automated, trivial, already reviewed
│
2. Collect CLAUDE.md files (Haiku)
├─ Root CLAUDE.md + phase-specific CLAUDE.md files
│
3. Get PR summary (Haiku)
├─ Understand the change at high level
│
4. Parallel 5-agent review (5x Sonnet)
├─ Agent #1: CLAUDE.md compliance audit
├─ Agent #2: Shallow bug scan (large bugs only)
├─ Agent #3: Git blame & history context
├─ Agent #4: Prior PR comments (similar files)
└─ Agent #5: Code comments in modified files
│
5. Confidence scoring (Parallel Haiku agents)
├─ Score each issue 0-100
├─ Filter: keep only score ≥ 80
│
6. Final eligibility check (Haiku)
├─ Verify PR still eligible (not closed/merged while reviewing)
│
7. Post comment via gh (Bash)
└─ Format: brief description, file link with full SHA, line range
Step 1: Eligibility Check
Skip review if:
- Closed: PR is already closed
- Draft: PR marked as draft
- Automated: Author is bot/automation (e.g., dependabot)
- Trivial: Obvious fix (typo, docs, one-liner) with no risk
- Pre-reviewed: You already reviewed this PR earlier
Use:
gh pr view <number> --json state,isDraft,author,commits
Step 2: Collect CLAUDE.md Files
Gather all relevant CLAUDE.md files:
- Root
./CLAUDE.md(if exists) - Any
./some-phase/CLAUDE.md(if modified files are in that phase) - Any
./services/*/CLAUDE.md(if monorepo, for modified service)
Use:
gh pr diff <number> --name-only | xargs -I {} dirname {} | sort -u | xargs -I {} find {} -name CLAUDE.md
Step 3: Get PR Summary
Fetch PR metadata and commit summary:
gh pr view <number> --json title,body,commits
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 First seen · 246 lines · 64 tokens per session scan A d869be29b8f6
pr-review is a skill published in the GitHub repository saitarrun/Devforge-ai (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 64 tokens to every session and 2,148 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
phx-pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
merge-queue
Process the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify integration.
signing-preflight
Before the first commit of a session, check that commit signing will work — the key is loaded and unlocked — and ask the operator to unlock it once, up front, instead of discovering it after a hundred unsigned commits. Never disables signing silently, never re-signs history without asking. Use at the start of…