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/KhaledSaeed18/dotclaudeWrote 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/khaledsaeed18/dotclaude/review-pr)<a href="https://agentmods.dev/commands/khaledsaeed18/dotclaude/review-pr"><img src="https://agentmods.dev/badge/commands/khaledsaeed18/dotclaude/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/khaledsaeed18/dotclaude/review-pr"><img src="https://agentmods.dev/badge/commands/khaledsaeed18/dotclaude/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 | $0.00095 | $0.00919 |
| Opus 5.5 | $0.00038 | $0.00368 |
| Sonnet 5.5 | $0.00019 | $0.00184 |
| Haiku 4.5 | $0.00010 | $0.00092 |
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 25d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
Target: $ARGUMENTS (a PR number, a branch, or empty for the current branch; --post posts the result as a PR comment)
Current branch and merge base:
!git branch --show-current 2>/dev/null; git merge-base HEAD origin/main 2>/dev/null || git merge-base HEAD main 2>/dev/null
Change summary:
!git diff --stat $(git merge-base HEAD origin/main 2>/dev/null || git merge-base HEAD main 2>/dev/null)...HEAD 2>/dev/null | tail -20
Task
Step 1: Resolve the target
- A number:
gh pr view <n> --json headRefName,baseRefName,title,body,urlthengh pr checkout <n>if not already on it. The diff isbase...head. - A branch name: check it out (or use a worktree if the tree is dirty) and diff against its merge base with the default branch.
- Nothing: the current branch against its merge base.
Read the PR description or the last commits for intent. If the diff is empty, say so and stop.
Step 2: Fan out
Launch these four agents in parallel, each with the same scope (the diff range and the intent), and let each work in its own context:
code-reviewer: correctness, security, maintainability, stack-specific issues.silent-failure-hunter: swallowed errors, ignored results, wrong statuses.test-gap-analyzer: behaviours with no asserting test, as test specs.type-design-reviewer: types that permit invalid states, boundary casts.
Give each the explicit diff command (git diff <base>...HEAD) and the PR title and body, and tell each to return its standard report.
Step 3: Merge
Combine the four reports into one review:
- Deduplicate. The same
file:linereported by two agents becomes one finding that credits the stronger analysis. - Rank Critical, High, Medium, Low across all sources. Silent failures with data-loss scenarios and security findings are Critical or High regardless of which agent found them.
- Keep the evidence. Every finding keeps its
file:line, scenario, and fix. - Cap the noise. At most 15 findings in the body; summarise the rest in one line each under "Also noted".
- Verdict in the first line: approve, approve with nits, request changes; and one sentence why.
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.
- 25d ago First seen · 88 lines · 95 tokens per session scan A a0f703d6161e
review-pr is a command published in the GitHub repository KhaledSaeed18/dotclaude (5 stars, last pushed 2d ago), licensed MIT. It adds 95 tokens to every session and 919 once invoked, about $0.0004 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 2026-09-22.
Other commands, from other repositories
refactor
Clean up dead code, reduce duplication, and simplify structure without changing behavior.
review-skills
Review changed skills: automated bash checks + 9 structural dimensions (D1-D9) + 5 intent checks (M1-M5). PASS/FAIL verdict. Fix in-place.
dual-review
Adversarial dual review — two independent reviewers with no shared context; both must approve before merge.
review-pr
Review a GitHub pull request by number.
review
Review the current diff against the project rules.
claude-loop
Use a fresh headless Claude session (Fable by default) as an independent reviewer of the whole repo, area by area (or of one branch's diff with --base), fix every real finding with regression tests, and loop until each area comes back clean twice in a row. The /codex-loop pattern on Anthropic usage. Runs autonomously.