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 RashadAnsari/myagents --skill pr-reviewgit clone --depth 1 https://github.com/RashadAnsari/myagentsWrote 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/rashadansari/myagents/pr-review)<a href="https://agentmods.dev/skills/rashadansari/myagents/pr-review"><img src="https://agentmods.dev/badge/skills/rashadansari/myagents/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/rashadansari/myagents/pr-review"><img src="https://agentmods.dev/badge/skills/rashadansari/myagents/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 | $0.00050 | $0.05126 |
| Opus 5.5 | $0.00020 | $0.02050 |
| Sonnet 5.5 | $0.00010 | $0.01025 |
| Haiku 4.5 | $0.00005 | $0.00513 |
Grade C, and why
pr-review scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
If any command fails, clean up with `rm -rf "$REVIEW_DIR"` and report the error. How it starts
The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MANDATORY: Load the humanizer skill (albino:humanizer) now and keep all its rules active for the entire session. Every piece of text you write or post, including comment bodies, the review body, and any output to the user, must pass the humanizer check before it leaves your context.
PR Review
Review the GitHub pull request: $ARGUMENTS
If the line above still shows a placeholder instead of a value, this platform does not pass arguments to skills: take the value from the user's message instead, and treat it as empty when the message gives none. Read every later mention of the placeholder as that value.
Step 1: Validate Input
If $ARGUMENTS is empty or missing, stop immediately and tell the user:
Usage: /pr-review <github-pr-url>
Example: /pr-review https://github.com/owner/repo/pull/123
Parse owner, repo, and number from $ARGUMENTS now (URL format: https://github.com/{owner}/{repo}/pull/{number}). If the URL does not match this format, stop and show the usage message above.
Step 2: Pre-Review Gate
Run both in parallel:
gh pr view "$ARGUMENTS" --json state,isDraft,author --jq '{state: .state, isDraft: .isDraft, author: .author.login}'
gh api repos/{owner}/{repo}/pulls/{number}/reviews --jq '[.[].user.login]'
Stop immediately with a clear message if any condition is true:
stateis not"OPEN"(PR is closed or merged)isDraftistrueauthor.loginends in[bot]or is one of:dependabot,renovate,snyk-bot,github-actions- The authenticated user's login already appears in the reviews list (run
gh api user --jq '.login'to get it if needed)
Step 3: Fetch PR Data
Run all three in parallel:
gh pr view "$ARGUMENTS" --json number,title,body,author,baseRefName,headRefName,headRefOid,state,additions,deletions,changedFiles
gh pr view "$ARGUMENTS" --json files --jq '[.files[].path]'
gh pr diff "$ARGUMENTS"
If any command fails, stop and report the error. If not authenticated, suggest gh auth login.
What ships with it
1 file 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.
- yesterday First seen · 339 lines · 50 tokens per session scan C 0df1b81b7bce
pr-review is a skill published in the GitHub repository RashadAnsari/myagents (6 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 5,126 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-15.
Other skills, from other repositories
prismer-github
GitHub via gh CLI: PRs, issues, reviews, repos, auth.
pr-reviewer
Review a requested pull request, branch diff or completed task against its actual scope, source and checks. Prepare evidence and comments; post or record a human verdict only when explicitly authorized.
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
code-review
Review a diff against its acceptance criteria in four segments (convention adherence, bug scan, historical-context regressions, test-coverage gaps) as a NON-implementing agent. Findings are sorted by severity, each with file:line + a failure scenario. A planted defect must be caught; a clean diff must not be…