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/mikemanifold/codex-unified/code-review-contextnpx skills add MikeManifold/codex-unified --skill code-review-contextgit clone --depth 1 https://github.com/MikeManifold/codex-unifiedWhat 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 | $0.00007 | $0.00142 |
| Opus 5 | $0.00003 | $0.00071 |
| Sonnet 5 | $0.00001 | $0.00028 |
| Haiku 4.5 | $0.00001 | $0.00014 |
Grade A, and why
code-review-context 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.
This is a copy
100% identical to code-review-context — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Codex maintains a context (history of messages) that is sent to the model in inference requests.
- No history rewrite - the context must be built up incrementally.
- Avoid frequent changes to context that cause cache misses.
- No unbounded items - everything injected in the model context must have a bounded size and a hard cap.
- No items larger than 10K tokens.
- Highlight new individual items that can cross >1k tokens as P0. These need an additional manual review.
- All injected fragments must be defined as structs in
core/contextand implement ContextualUserFragment trait
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 · 13 lines · 7 tokens per session scan A 0af80b6388cc
code-review-context is a skill published in the GitHub repository MikeManifold/codex-unified (2 stars, last pushed 11d ago), licensed Apache-2.0. It adds 7 tokens to every session and 142 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to code-review-context, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
add-pattern
Use this skill when you learn one or more design pattern(s) in the Langroid (multi) agent framework, and want to make a note for future reference for yourself. Use this either autonomously, or when asked by the user to record a new pattern.
patterns
Design patterns for the Langroid multi-agent LLM framework. Covers agent configuration, tools, task control, and integrations.
antfu
Anthony Fu's opinionated tooling and conventions for JavaScript/TypeScript projects. Use when setting up new projects, configuring ESLint/Prettier alternatives, monorepos, library publishing, or when the user mentions Anthony Fu's preferences.
conventional-commits
Conventional Commits specification for consistent, machine-readable git commit messages. Use when crafting commit messages, enforcing commitlint rules, or generating changelogs/releases.
chatbot-mvp-distillation
Distill the chatgpt-vue3-light-mvp project into reusable architecture for building similar ChatGPT-style web products in other repositories. Use when designing or implementing streaming chatbot UIs, SSE/fetch response pipelines, model adapter contracts, typewriter rendering, Markdown/code/KaTeX/Mermaid rendering…
chatbot-mvp-distillation-zh
将 chatgpt-vue3-light-mvp 项目蒸馏为可迁移到其他项目的中文架构指南。适用于设计或实现类似 ChatGPT 的 Web 对话产品，包括 SSE/fetch 流式响应、模型适配器契约、打字机渲染、Markdown/代码/KaTeX/Mermaid 渲染、推理过程展示，以及从本 Vue 3 MVP 迁移到其他项目的方案规划。.