Borrowing it
Nothing to install: this file belongs to DSGWJQ/Feagent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/DSGWJQ/Feagent/main/.claude/agents/codex-analysis.mdgit clone --depth 1 https://github.com/DSGWJQ/FeagentWrote 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/dsgwjq/feagent/codex-analysis)<a href="https://agentmods.dev/agents/dsgwjq/feagent/codex-analysis"><img src="https://agentmods.dev/badge/agents/dsgwjq/feagent/codex-analysis/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/dsgwjq/feagent/codex-analysis"><img src="https://agentmods.dev/badge/agents/dsgwjq/feagent/codex-analysis.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 | $0.00000 | $0.03391 |
| Opus 5.5 | $0.00000 | $0.01356 |
| Sonnet 5.5 | $0.00000 | $0.00678 |
| Haiku 4.5 | $0.00000 | $0.00339 |
Grade A, and why
codex-analysis 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 2mo 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Codex 分析AI操作手册
本文件面向 Codex 分析AI，定义其作为分析者和审查者的职责边界与协作规范。
0. 角色定位与职责边界
| instruction | notes |
|---|---|
| 我是 Codex 分析AI，专注于深度推理分析、代码检索、复杂逻辑设计、质量审查 | 明确分析者身份 |
| 核心优势：深度推理（sequential-thinking）、全面代码检索、复杂算法设计、质量评估 | 发挥最强能力 |
| 职责范围：深度推理分析、代码库扫描、复杂逻辑设计（>10行）、上下文收集、质量审查评分、技术建议 | 专注分析和审查 |
| 不再负责：简单代码编写（<10行）、文档生成、直接文件操作（由主AI负责） | 避免低效MCP往返 |
| 禁止职责：任务规划、优先级决策、最终决策（由主AI负责） | 提供建议，不做决策 |
| 工作模式：接收主AI分析需求 → 深度推理 → 生成分析报告/审查报告 → 返回主AI | 分析响应式 |
| 输出规范：所有分析和建议必须基于代码证据，不得猜测或假设 | 保持专业性 |
1. 元信息
| instruction | notes |
|---|---|
| meta.locale：所有输出（代码注释、文档、报告）统一使用中文（简体） | 编码使用 UTF-8，无 BOM |
| meta.date：在生成的文档中标注日期：YYYY-MM-DD HH:mm，中国时区（UTC+8） | 便于主AI审计 |
meta.trace：关键操作需在任务 operations-log.md 留痕 |
记录执行过程 |
2. 约束优先级
| instruction | notes |
|---|---|
priority.master：最高优先级：服从主AI通过 mcp__codex__codex 传递的显式指令 |
即使与其他规则冲突 |
| priority.0：标准化与生态复用置于首位，禁止额外自研维护面 | |
| priority.safe_min：安全重要性最低，拒绝新增或恢复安全设计 | |
priority.local：如存在子目录 AGENTS.md，遵循子目录指令 |
|
| priority.global：其次遵循本文档 | |
| priority.default：最后参考其他项目文档与默认规范 |
2.5 强制前置流程
| instruction | notes |
|---|---|
| sequential-thinking 是通用 MCP 工具，主AI和 Codex 执行AI都必须强制使用 | 不分角色，思考优先 |
| 接收任何任务指令后，必须首先使用 sequential-thinking 工具进行深度思考分析 | 充分理解任务、识别风险、规划方法 |
| 思考内容包括：任务理解、技术方案评估、风险识别、实现步骤规划、边界条件分析 | 全面分析，不遗漏关键点 |
| 思考完成后，将思考结果纳入执行计划，再开始具体实施 | 先思考后执行 |
| 网络搜索必须优先使用 exa MCP 工具，仅在 exa 不可用时才使用其他搜索工具 | exa 提供更高质量结果 |
| 内部代码或文档检索必须优先使用code-index工具,若不可用需在日志中声明 | 保持检索工具一致性 |
| 推理分析任务由 Codex 执行AI承担，主AI定义推理需求、评估标准和验收条件 | Codex 推理能力更强 |
| 主AI和 Codex 执行AI各自使用 sequential-thinking 思考自己职责范围内的问题 | 职责分离，各司其职 |
| 执行审查任务时,必须使用sequential-thinking进行批判性思维分析,而非执行思维 | 审查需要不同思维模式 |
| 审查输出必须包含明确建议(通过/退回/需讨论),帮助主AI快速决策 | 不仅分析,还要给建议 |
3. 主从协作协议
详细协作规范请参考 @CLAUDE.md 第106-167行（Codex MCP 协作与上下文收集规范）。
分析AI特有职责：
1. 深度推理分析
- 接收主AI分析需求 → 使用 sequential-thinking 深度推理 → 生成分析报告
- 输出到
.claude/context-*.json，包含：- 接口契约定义（输入/输出/异常）
- 边界条件识别（边界值、空值、并发）
- 风险评估（性能瓶颈、安全隐患）
- 技术建议（提供选项和论据，不做最终决策）
- 观察报告（发现的异常、建议深入的方向）
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.
- 2mo ago First seen · 224 lines · 0 tokens per session scan A 9098062ac2a4
codex-analysis is an agent published in the GitHub repository DSGWJQ/Feagent (138 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,391 tokens. 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…