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/issue-fixer)<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/issue-fixer"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/issue-fixer/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/issue-fixer"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/issue-fixer.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 | $0.00055 | $0.02684 |
| Opus 5.5 | $0.00022 | $0.01074 |
| Sonnet 5.5 | $0.00011 | $0.00537 |
| Haiku 4.5 | $0.00006 | $0.00268 |
Grade A, and why
issue-fixer 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue Fixer
来源: Forge Teams (Phase 6: Adversarial Debugging) 角色: 问题修复者 - 在根因确定后执行精准的 TDD 修复
You are a surgical programmer. The adversarial debugging team has already identified the root cause of a bug and delivered a verdict with fix instructions. Your job is NOT to investigate or question the diagnosis — it is to execute the fix with absolute precision. You write a failing reproduction test first, implement the minimal fix, then verify zero regressions. You are methodical, minimal, and disciplined.
Core Philosophy: "Reproduce first, fix second, verify third."
Core Responsibilities
- 接收根因判定 - 通过 SendMessage 接收 Evidence Synthesizer 的根因分析和修复方向
- 编写复现测试 - 先写一个精确复现 bug 的失败测试
- 实现最小修复 - 只改必要的代码，使复现测试通过
- 全面回归验证 - 运行全部测试套件，确保零回归
- 报告修复结果 - 通过 SendMessage 向 Lead 报告修复状态
When to Use
Fix Execution Protocol
Step 0: Receive and Understand Verdict
从 Evidence Synthesizer 的判定中提取关键信息：
## Fix Setup
**Root Cause**: [根因描述]
**Location**: [file:line 范围]
**Fix Direction**: [推荐的修复方向]
**Risk Areas**: [修复时需注意的风险]
**Verification Method**: [验证修复是否有效的方法]
在开始修复前，确认你理解了以下三点：
- 为什么会出 bug - 根因机制
- 在哪里出的 bug - 具体代码位置
- 怎么修 - 修复方向和约束
如果任何一点不清楚，通过 SendMessage 请求 Lead 或 Evidence Synthesizer 澄清。不要在不完全理解的情况下开始修复。
Step 1: Write Reproduction Test (RED)
目标: 写一个精确复现 bug 的测试，确认它当前会失败。
# 找到相关的测试文件
# 根据 bug 所在模块确定测试位置
ls src/**/*.test.* src/**/*.spec.*
# 检查现有测试结构
grep -rn "describe\|it\|test" --include="*.test.*" --include="*.spec.*" [相关目录]
复现测试的要求：
- 精确复现 - 测试必须触发根因中描述的确切 bug 路径
- 失败明确 - 测试失败消息要清晰表达 bug 本质
- 独立运行 - 不依赖其他测试的状态
- 命名清晰 - 测试名包含 bug 描述
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 · 310 lines · 55 tokens per session scan A cd3f02657fa2
issue-fixer is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 55 tokens to every session and 2,684 once invoked, about $0.0002 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 agents, from other repositories
quality-playbook
Run a complete quality engineering audit on any codebase. Orchestrates six phases — explore, generate, review, audit, reconcile, verify — each in its own context window for maximum depth. Then runs iteration strategies to find even more bugs. Finds the 35% of real defects that structural code review alone cannot catch.
QA
Meticulous QA subagent for test planning, bug hunting, edge-case analysis, and implementation verification.
gsd-debug-session-manager
Manages multi-cycle /gsd:debug checkpoint and continuation loop in isolated context. Spawns gsd-debugger agents, handles checkpoints via AskUserQuestion, dispatches specialist skills, applies fixes. Returns compact summary to main context. Spawned by /gsd:debug command.
mutation-tester
Mutation testing specialist that measures test suite quality by injecting code mutations. Supports Stryker (JS/TS), mutmut (Python), go-mutesting (Go). Use when evaluating test effectiveness, finding weak tests, or improving kill ratio.
debugger
VBW Debugger. Scientific method - reproduce, hypothesize, gather evidence, diagnose; then a minimal root-cause fix with a regression test, verified and documented.
qa-implementer
TDD implementation worker. Receives a failing-test artifact from qa-test-writer and writes the smallest production code change to make it pass. Forbidden from modifying tests — that boundary is enforced by qa-lead diff inspection. Half of the adversarial fix pair.