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/GGGODLIN/claude-pr-reviewWrote 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/gggodlin/claude-pr-review/pr-review)<a href="https://agentmods.dev/commands/gggodlin/claude-pr-review/pr-review"><img src="https://agentmods.dev/badge/commands/gggodlin/claude-pr-review/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/gggodlin/claude-pr-review/pr-review"><img src="https://agentmods.dev/badge/commands/gggodlin/claude-pr-review/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 | $0.00029 | $0.41879 |
| Opus 5 | $0.00015 | $0.20939 |
| Sonnet 5 | $0.00006 | $0.08376 |
| Haiku 4.5 | $0.00003 | $0.04188 |
Grade B, and why
pr-review scanned grade B with 2 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 11d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
# log 尾停在「mcp: semble/search started」= MCP wedge：先確認 config 前置 mutation 真的跑過（grep -c mcp_servers ~/.codex/config.toml 應為 0）再 retry Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Bitbucket 所有 proposal、approval、Apply 與 read-back 細節以 `bitbucket-pr-mutation` 為唯一權威。若 operation 不在 V1 allowlist，只保留草稿，不退回 raw curl。 How it starts
The opening of the file, as written. The whole thing — 1,561 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review
⚠️ 本檔在契約測試底下：
skills/bitbucket-pr-mutation/scripts/tests/test_no_raw_bitbucket_writes.py會讀 Step 8，斷言步驟 marker 的順序與 tier 保證句；commands/tests/test_pr_review_report_projection_contract.py會讀 Step 5–6，斷言雙層報告投影接線；commands/tests/test_pr_review_c4_dispatch_contract.py會讀 C4 派工段，斷言 prepared marker 接線與人工 prompt 退役；commands/tests/test_pr_review_self_verify_contract.py會讀 Step 6，斷言 Self-Verify 接線與 advisory 行為。改動對應段落後四套都要跑。cd skills/bitbucket-pr-mutation/scripts && python3 -m unittest discover -s tests -qpython3 commands/tests/test_pr_review_report_projection_contract.pypython3 commands/tests/test_pr_review_c4_dispatch_contract.pypython3 commands/tests/test_pr_review_self_verify_contract.py
Orchestrate a multi-axis code review (CC context-aware + Codex neutral & adversarial + Gemini Flash permanent axis; Gemini Pro opt-in) for a pull request and produce a Traditional Chinese comparison report.
Platform support: GitHub needs only the gh CLI — the two skills/bitbucket-pr-* directories are an optional Bitbucket adapter (Bitbucket has no official CLI); GitHub-only users can skip installing them entirely. Every Bitbucket-specific step below (Step 2 Bitbucket fetch, Step 8.2) is inert when the PR is on GitHub.
Scope: Workflow orchestration only. Review criteria and checklists are the responsibility of each reviewer agent — this command does not define what to review, only how to run and compare. Exception: the Step 2.8 cross-cutting baseline (and the strict-liability list) IS defined here and injected into every reviewer — it is the shared review floor, deliberately owned by this command.
流程敘述中的「Opus」是 context-aware CC reviewer 軸的軸名；reviewer agents 的實際模型釘在各自 frontmatter，報告中的 user-facing 標籤必須反映實際 runtime 模型（規則見 Step 5 Report Generation Rules 首條）。
Input
/pr-review <number>— PR number in current repo/pr-review <GitHub URL>—https://github.com/owner/repo/pull/123/pr-review <Bitbucket URL>—https://bitbucket.org/workspace/repo/pull-requests/123
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.
- 11d ago First seen · 1,561 lines · 29 tokens per session scan B e2301d36a249
pr-review is a command published in the GitHub repository GGGODLIN/claude-pr-review (114 stars, last pushed 19d ago), licensed MIT. It adds 29 tokens to every session and 41,879 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.