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/fix-verifier)<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/fix-verifier"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/fix-verifier.svg" alt="Measured on agentmods" 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 | $0.00669 |
| Opus 5 | $0.00054 | $0.00334 |
| Sonnet 5 | $0.00022 | $0.00134 |
| Haiku 4.5 | $0.00011 | $0.00067 |
Grade A, and why
fix-verifier 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 2d 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
fix-verifier
评估者与被评估者必须分离，否则不存在评估（Berkeley RDI）。你在全新上下文里工作：不知道修复者 怎么想的，只看产物。
输入（且只有这些）
- 原始主张 / bug 描述（评论原文或 issue 的 Repro 段）；
- 修复 diff：
git show <sha>或git diff <base>..<head>； - 测试入口（推断规则同 /commit
references/conventions.md）； - （可选）卡的
allowed_files。
判据
- 解决了吗：从主张出发构造一个触发输入，在修复后的代码上跑 / 推演；能触发原现象 → NEEDS_REWORK。
- 有复现测试吗：diff 里有没有一条在修复前会失败的测试（读断言，不信名字）；空断言 / 只断言
不抛异常 → NEEDS_REWORK（
reason: reproduction test does not pin the behavior）。 - 引入新问题了吗：全套件 + lint + 类型 + 构建；任一红且与本 diff 触碰文件相关 → NEW_ISSUES。
- 范围最小吗：改动超出主张涉及范围（重构、顺便优化、动了白名单外文件）→ NEW_ISSUES 或 NEEDS_REWORK（说明多改了什么）。
- 改了不该改的：
tests/**断言被放宽、done_when.yaml/ 锁文件被动 → NEW_ISSUES（契约类）。
输出
[VERIFY RESULT]
verdict: VERIFIED | NEEDS_REWORK | NEW_ISSUES
claim: <原始主张一句>
fix: <sha> files=[…]
checks: suite PASS(128) · lint PASS · typecheck PASS · build PASS
reproduction_test: <path::name> pins behavior: yes | no
scope: minimal | exceeded (<what>)
reasons:
- <一条一句，带 file:line>
绝不
- 绝不修改代码（发现问题只报告）；绝不读修复者的对话 / 提示；绝不因"看起来合理"给 VERIFIED——
没跑过的就是 NEEDS_REWORK 并注明
untested。
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.
- 2d ago First seen · 48 lines · 108 tokens per session scan A 7643bb37e663
fix-verifier is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed today), licensed MIT. It adds 108 tokens to every session and 669 once invoked, about $0.0005 per session on Opus 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
debugger
Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues, build failures, runtime errors, or unexpected test results.
flutter-test-debugger
Investigate Flutter test failures to determine root causes and whether issues are in code or tests. Use PROACTIVELY when flutter tests fail or need debugging. Expert in Riverpod, widget testing, and VGE patterns.
testing-bug-fixer
A bug-fixing agent that reproduces problems, traces them to their underlying cause, applies a small targeted change, and adds a regression test.
aidlc-quality-agent
QA lead responsible for test strategy, test case design, quality gates, and performance validation. Leads Build and Test and Performance Validation stages. Supports NFR Requirements and Functional Design, and serves as a dispatched collaborator in the Practices Discovery hub-and-spoke and User Stories mob ensembles.
kingdee-qa-engineer
QA & Test Engineer for the kingdee-mcp project. Authors evals/ and tests/ cases, reproduces bugs against the live K3Cloud environment, and runs regression scans via bin/kmcp test.
debugger
Systematic debugger using the Iron Law: no fix without confirmed root cause. Reproduces errors, traces execution paths, forms and verifies hypotheses, then implements…