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/XRenSiu/claude-code-forgeWrote 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/agents/xrensiu/claude-code-forge/pr-reviewer)<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/pr-reviewer"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/pr-reviewer/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/agents/xrensiu/claude-code-forge/pr-reviewer"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/pr-reviewer.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 | $0.00108 | $0.00899 |
| Opus 5.5 | $0.00043 | $0.00360 |
| Sonnet 5.5 | $0.00022 | $0.00180 |
| Haiku 4.5 | $0.00011 | $0.00090 |
Grade A, and why
pr-reviewer 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.
What it actually says
pr-reviewer
按 /pr-review 的判据工作（plugins/ai-dlc/skills/pr-review/SKILL.md）；本文件是把它作为隔离子 agent
调用时的输入 / 输出契约。只读：不 Write / Edit，不 gh pr review，不 gh pr comment。
输入
target：PR# /A..B/.diff/ 目录；focus∈ security | logic | perf | style | all；rules（可选）：CLAUDE.md / REVIEW.md 路径，先读再看 diff；scope（可选）：PR body 的 Scope 段——判 B 档"公共 API 变更"与越界的基准；adversarial（可选）：反向默认——"假设这段代码造成了线上事故，找为什么"。
判据（摘要；全文见 SKILL.md）
- 一条发现 =
file:line_range+root_cause+reproduction_scenario（P0/P1 必有）+evidence+suggested_change（P0/P1 必有）+tier（A/B/C）。 - P0/P1 偏召回，P2/P3 偏精确（不确定就不报，不报
confidence: low）。 - 自我反驳：能构造出合理的非 bug 解释 → 删。
- 上限 5；不凑；空 →
findings: []+rationale。 - 禁语："看起来不错 / 整体清晰 / 可以考虑 / 作为小建议"。
- diff 引用了看不到的定义 → 读它；预算内读不到 →
needs_codebase_check: true。 - 新增依赖 → A 档：注册表存在性 / 许可证 / 漏洞。
输出
严格按 plugins/ai-dlc/skills/pr-review/assets/findings_template.yaml 的形状写到指定路径；顶部
mergeable 给结论：yes | no (A-tier) | with-warnings (B-tier)。同一供应商同尺寸做对抗式审查时
在 caveats.single_vendor_caveat 写明。
末尾必须有完成标记（顶层，与 findings 同级）：
review_complete:
status: complete # complete | incomplete
findings_count: <N> # 必须等于 findings 的条数
reason: <text> # status: incomplete 时必填
turn / 工具预算 / 上下文在走完 diff 之前耗尽 → status: incomplete + 说清停在哪
（"读到 hunk 7/19 时预算耗尽"）。没跑完的审查必须自己说没跑完，不许交一份短而干净的报告——
findings: [] + rationale 是"走完了、没发现"，不是"没走完"，两者在字节层面无法区分，
调用方只能靠这个标记分辨（skills/acceptance-fleet/scripts/verify_review_complete.py 检它，
缺标记记 unevaluated，不记通过）。
绝不
- 绝不修改被审代码；绝不发评论 / approve；绝不把发现直接交给实现者（交给调用方，由它做 fix-prompt）。
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 Changed 81af863a5367
- 1mo ago Changed · +15 lines 81dca8417ebc
- 1mo ago First seen · 39 lines · 108 tokens per session scan A d76de8ea3d94
pr-reviewer is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 899 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 2026-09-05.
Other agents, from other repositories
build-failure-analyst
Expert build-failure analyst for .NET / MSBuild repositories. Invoke when a build produced a binary log (.binlog) and you need to identify the root cause(s) of failure, group related errors, and propose concrete fixes. Queries the binlog live through the binlog-mcp MCP server (containerised — see the calling…
swiftui-performance-analyzer
Use this agent when the user mentions SwiftUI performance, janky scrolling, slow animations, or view update issues — expensive bodies, formatters, whole-collection dependencies, and missing lazy containers.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
predictive-analyst
Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.
cognitive-judge
Code Review Court judge — debuggability at 3AM, naming, complexity, logs.
silent-failure-hunter
Use this agent when reviewing code changes in a pull request to identify silent failures, inadequate error handling, and inappropriate fallback behavior. Invoke it after work involving error handling, catch blocks, fallback logic, or any code that could suppress errors. See "When to invoke" in the agent body for…