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 XRenSiu/claude-code-forge --skill fix-bug-loopgit 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/skills/xrensiu/claude-code-forge/fix-bug-loop)<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/fix-bug-loop"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/fix-bug-loop/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/xrensiu/claude-code-forge/fix-bug-loop"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/fix-bug-loop.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 | $0.00134 | $0.04620 |
| Opus 5.5 | $0.00054 | $0.01848 |
| Sonnet 5.5 | $0.00027 | $0.00924 |
| Haiku 4.5 | $0.00013 | $0.00462 |
Grade A, and why
forge-fix 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.
How it starts
The opening of the file, as written. The whole thing — 511 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge Fix - 独立 Bug 修复
描述 bug → 对抗调试定位根因 → TDD 修复 → 独立验证 → 循环直到修好。
这是 forge-teams 的独立 bug 修复入口。复用已有的对抗调试引擎(hypothesis-investigator、devils-advocate、evidence-synthesizer、issue-fixer),但提供独立编排、快速路径分流和三层迭代控制。
Announce at start: "I'm using the forge-fix skill to create an agent team that will locate and fix this bug through adversarial debugging and TDD."
前置条件: 需要启用 Agent Teams 实验性功能。 在 settings.json 中添加:
"env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" }
用法
/forge-fix <bug-description> [options]
参数说明
| 参数 | 说明 | 默认值 |
|---|---|---|
<bug-description> |
bug 描述(文本、文件路径、或错误日志) | 必填 |
--loop <N> |
最大修复-验证循环次数 | 3 |
--quick |
快速路径:跳过对抗调试,直接用 issue-fixer 修复(适用于简单 bug) | 不启用 |
--team-size <size> |
假设调查团队规模(small=3 假设, medium=4, large=5) | medium |
--no-verify |
修复后跳过独立验证(不推荐) | 启用验证 |
示例
# 直接描述 bug
/forge-fix "支付回调间歇性超时,大约每10次失败2次"
# 简单 bug,快速路径
/forge-fix "登录页面 CSS 错位" --quick
# 复杂 bug,加大团队 + 增加循环
/forge-fix "高并发下 Redis 连接池泄漏" --team-size large --loop 5
# 从错误日志修复
/forge-fix "npm test 报错: TypeError: Cannot read property 'id' of undefined at src/user.ts:42"
输出目录
docs/forge-fix/
└── [bug-slug]-[timestamp]/
├── intake.md # 问题信息收集
├── hypotheses.md # 假设列表(非 quick 模式)
├── debate-log.md # 对抗辩论记录(非 quick 模式)
├── verdict.md # 根因判定
├── fix-report.md # TDD 修复报告
├── verification.md # 独立验证报告
└── summary.md # 最终修复摘要
Quick vs Full Path Decision (快速路径分流)
用户描述 bug
│
├── --quick 指定 → 快速路径
│
└── 未指定 → Lead 评估复杂度
│
├── 简单信号 → 建议快速路径(用户确认)
│ - 单文件、单函数问题
│ - 错误信息直接指向根因(如 TypeError at file:line)
│ - 纯 UI/CSS 问题
│ - typo 或明显逻辑错误
│
└── 复杂信号 → 完整对抗调试路径
- 间歇性故障
- 多个可能根因
- 涉及并发/状态/竞态
- 跨模块/跨服务
- "时有时无"、"偶尔"、"不稳定"
Quick Path (快速路径)
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 First seen · 511 lines · 134 tokens per session scan A 5f7b39f6d699
forge-fix is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 134 tokens to every session and 4,620 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
resolve-author-fix
Find the root cause, implement a focused fix, and prove behavior with targeted tests and recordings.
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
nw-bugfix
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD.
genotoxic
Graph-informed mutation testing triage. Parses codebases with Trailmark, runs mutation testing and necessist, then uses survived mutants, unnecessary test statements, and call graph data to identify false positives, missing test coverage, and fuzzing targets. Use when triaging survived mutants, analyzing mutation…