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 agentmods add skills/hashgraph-online/awesome-codex-plugins/agent-debug-fixernpx skills add hashgraph-online/awesome-codex-plugins --skill agent-debug-fixergit clone --depth 1 https://github.com/hashgraph-online/awesome-codex-pluginsWhat 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 | $0.00071 | $0.00948 |
| Opus 5 | $0.00036 | $0.00474 |
| Sonnet 5 | $0.00014 | $0.00190 |
| Haiku 4.5 | $0.00007 | $0.00095 |
Grade A, and why
agent-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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- agent-debug-fixer — 100% identical, 0 lines differ
What it actually says
Codex 调试修复
身份：执行者。只修一个问题，先找根因，最小修复。不重构、不加功能、不改架构。
遵守统一行为规范（职能隔离 / 动作校验 / 状态机 / 五级纠错 / 回滚 / 证据链）。
📍 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。
硬边界
| 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 | 静默改变项目方向 |
| 确认/写测试先行于修复 | 跳过 TDD 校验 |
| 调用 agent-drift-auditor 报告结构问题 | 跳过校验直接修改 |
工作流程
- 明确现象（范围检查）
- 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
agent-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
- 回滚点已记录？
- 执行最小修复
- 验证修复
- 交互预算自检：
- 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
- 最小改动优先 / 不重构 / 不加功能
- 不改架构（需决策闸门）/ 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）：
- 无法自动化测试的 UI 动效 / 硬件交互 / 纯配置变更
偏离处理
| 级别 | 动作 |
|---|---|
| 第 1 级 | 自查纠正，记录证据链 |
| 第 2 级 | 审计者轻量诊断，输出纠正建议 |
| 第 3 级 | 深度检查 + 回滚到上一合法状态，暂停前进 |
| 第 4 级 | 冻结任务队列 + 完整偏离报告，标记人工介入 |
| 第 5 级 | 强制人工介入，系统锁定 |
| ≥5 级 | 等待人工解锁，停止所有自动动作 |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 77 lines · 71 tokens per session scan A fa515d47e961
agent-debug-fixer is a skill published in the GitHub repository hashgraph-online/awesome-codex-plugins (859 stars, last pushed 3d ago), licensed Apache-2.0. It adds 71 tokens to every session and 948 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
search
Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.
preview-verdicts
Generate the interactive keep/drop verdict preview (HTML page with per-row feedback controls) whenever a prune sweep, batch entry edit, or restructure needs maintainer review before touching README.md — and process the feedback JSON the maintainer pastes back.
sprr
Single PR reviewer for awesome-quant. Use when the user asks to review, validate, comment on, label, close, or merge one specific pull request that adds README.md entries. Triggers include "sprr", "review PR", "check PR", and "validate contribution".
bprr
Bulk PR reviewer for awesome-quant. Use when the user asks to review all open PRs, review unreviewed PRs, bulk review, or mentions "bprr". Reviews open PRs lacking the reviewed label and presents a summary before any merge/comment/label action.
check-mcp-json
Safely review, triage, repair, and merge ToolSDK MCP Registry package JSON pull requests. Use when an agent needs to validate files under packages/, detect duplicate registry keys, classify community PRs, make authorized fixes on contributor branches, close invalid or duplicate PRs, or squash-merge approved PRs.
awesome-web-security
Looks up curated web security learning resources (XSS, SQLi, CSRF, SSRF, OAuth/JWT, deserialization, SAML, recon, evasion, defensive tooling, CTF). Filters by topic, difficulty, language, and resource type. Returns top references with archive fallbacks. Defensive and educational use only.