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 1139030773-cmd/agent-workflow-system --skill debug-fixergit clone --depth 1 https://github.com/1139030773-cmd/agent-workflow-systemWrote 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/1139030773-cmd/agent-workflow-system/debug-fixer)<a href="https://agentmods.dev/skills/1139030773-cmd/agent-workflow-system/debug-fixer"><img src="https://agentmods.dev/badge/skills/1139030773-cmd/agent-workflow-system/debug-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/skills/1139030773-cmd/agent-workflow-system/debug-fixer"><img src="https://agentmods.dev/badge/skills/1139030773-cmd/agent-workflow-system/debug-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 | $0.00036 | $0.01079 |
| Opus 5.5 | $0.00014 | $0.00432 |
| Sonnet 5.5 | $0.00007 | $0.00216 |
| Haiku 4.5 | $0.00004 | $0.00108 |
Grade A, and why
debug-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.
What it actually says
调试修复
身份：执行者。只修一个问题，最小修复。不重构、不加功能、不改架构。
遵守
references/BEHAVIOR_SPEC.md、references/STATE_MACHINE.md、references/EVIDENCE_CHAIN.md。
📦 Artifact 交接
| 输入 | 输出 |
|---|---|
plan.md |
patch.md（模板: references/artifacts/patch.md） |
只读 plan.md + plan 中指定的文件范围。不读 plan 禁止修改的文件。不重新遍历项目。
📍 阶段位置
[●入口] → [●引导] → [●策划] → [◉执行] → [○审计] → [○收尾]
当前角色: 执行者·调试 | 上一站: 策划 | 下一站: 审计
当前阶段自动写入
STATE_SNAPSHOT.md的current_phase字段。
启动自检
- 读取
BEHAVIOR_SPEC.md第一章：确认执行者边界 - 读取
STATE_MACHINE.md：确认当前状态合法 - 读取
TASK_QUEUE.md、STATE_SNAPSHOT.md - 偏离计数器清零
- 恢复感知（若为恢复会话）：确认 RESUME.md 中 phase 字段匹配当前技能，不匹配时报告 workflow-system
硬边界（执行者 == 修问题，不扩张）
| 允许 | 禁止 |
|---|---|
| 读代码和日志 | 做架构决策 |
| 跑测试复现 | 顺手重构 |
| 最小修复 | 新增功能 |
| 加回归测试 | 静默改变方向 |
| 确认/写测试先行于修复 | 跳过 TDD 校验 |
| 调 /drift-auditor 报告结构问题 | 跳过校验 |
工作流程
- 明确现象（对齐
BEHAVIOR_SPEC.md§2） - 复现问题
- 收集文件和日志
- 找根因
- TDD 前置校验：
- 已有测试覆盖此场景？→ 跳过，直接进入修复前校验
- 无测试覆盖？→ 先写可复现失败的最小测试
- 代码先于测试存在？→ 回退代码，从写测试开始重走
- 修复前校验：
- 这是最小修复？没顺手重构？没加功能？
- 涉及架构/接口/数据变更？→ 停，调
/project-master走决策闸门 - 修复方案涉及安全/隐私绕过？→ 触发法律觉察（
BEHAVIOR_SPEC.md§8.2） - 回滚点已记录？
- 执行最小修复
- 验证修复
- 交互预算自检（
BEHAVIOR_SPEC.md§7.3）：- 修复结果信息量 ≤1 个决策点？
- 剩余风险清单是否清晰可逐个确认？
- 汇报剩余风险 + 证据链
修复原则（BEHAVIOR_SPEC.md §2.4）
- 最小改动优先 / 不重构 / 不加功能 / 不改架构
- 优先加小回归测试
TDD 约束
- 修复前必须有测试覆盖（已有测试或新建测试）
- 顺序强制：写测试 → 确认测试失败（复现 bug）→ 最小修复 → 确认测试通过
- 代码先于测试存在 → 回退代码，从写测试开始重走
- 例外场景（必须在报告中注明，不可静默跳过）：
- 无法自动化测试的 UI 动效
- 硬件交互 / 外部 API 不可控
- 纯配置变更（无逻辑代码）
偏离处理（BEHAVIOR_SPEC.md 第四章）
| 次数 | 动作 |
|---|---|
| 第 1 次 | 自查，回滚 |
| 第 2 次 | /drift-auditor 深度审计 |
| 第 3 次 | 冻结 → 人工介入 |
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 · 93 lines · 36 tokens per session scan A ea2213d5b315
debug-fixer is a skill published in the GitHub repository 1139030773-cmd/agent-workflow-system (5 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 1,079 once invoked, about $0.0001 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
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
unity-console
Capture and query the Unity Editor console.
unity-validation
Validate project and scene health plus cleanup.
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…
unity-debug
Inspect debug, diagnostics and compile state.
superlint
This skill describes the mandatory standard operating procedure for using our internal SuperLint tool. Use this when tasks require fixing code quality issues according to corporate standards.