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 instructions/cheolwanpark/codex-client/agents-mdgit clone --depth 1 https://github.com/cheolwanpark/codex-clientWhat 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 | $0.00354 | $0.00354 |
| Opus 5 | $0.00177 | $0.00177 |
| Sonnet 5 | $0.00071 | $0.00071 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
codex-client AGENTS.md 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 2d 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
Repo Agent Notes
- Read DESIGN.md before changing protocol-facing code.
schema/is the source of truth for wire shapes.DESIGN.mdis the source of truth for shared layering and lifecycle rules.- Keep bindings parallel where practical. Treat
python/as the behavioral reference when building outtypescript/. - Build the TypeScript binding bottom-up: messages/errors -> codec -> transport -> connection -> typed client -> runtime.
- The TypeScript package now includes all 3 layers. Preserve the separation between generated protocol surface and handwritten client/runtime logic.
- If protocol-facing TypeScript types or wrapper methods change, update the codegen source and regenerate the checked-in files in
typescript/src/generated*.ts. - Keep new TypeScript helpers limited to parity-oriented payload builders and documented runtime ergonomics. Do not add higher-level workflow helpers unless the task explicitly asks for them.
- Prefer parity tests against the Python low-level behavior before introducing TypeScript-only abstractions.
- Keep the TypeScript package Node-focused until a task explicitly asks for additional runtimes or transports.
- When repo docs mention available bindings or TypeScript support level, keep them accurate now that the runtime layer exists.
- Run TypeScript examples through the checked-in
pnpm example:*scripts.pnpm examples:buildcompilessrc/andexamples/intotypescript/.examples-dist/for local example execution. - If a commit is requested, follow the existing Conventional Commit pattern from
git logsuch asfeat: ...,fix: ...,docs: ..., orrefactor: ....
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.
- 2d ago First seen · 15 lines · 354 tokens per session scan A 1bfa83dab117
codex-client AGENTS.md is an instructions file published in the GitHub repository cheolwanpark/codex-client (7 stars, last pushed 5mo ago), licensed MIT. It adds 354 tokens to every session, about $0.0018 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 2026-08-31.
Other instructions, from other repositories
open-agents AGENTS.md
AGENTS.md instructions for vercel-labs/open-agents, covering agents.md, quick links, authentication, database & migrations and environment isolation.
relay AGENTS.md
Instructions for AgentWorkforce/relay, covering git workflow rules, never push directly to main, correct workflow, ... do work .. and stop here - let user merge.
axonhub AGENTS.md
AGENTS.md instructions for looplj/axonhub, covering agents.md, global rules, configuration, project overview and technology stack.
axonhub CLAUDE.md
Claude Code instructions for looplj/axonhub: @AGENTS.md read and follow its instructions.
neeko AGENTS.md
Instructions for tincopper/neeko, covering neeko — repository guidelines, 项目概览, 目录结构, 前端（feature-based 架构） and 后端（domain-driven 模块化架构）.
codex-acp-bridge AGENTS.md
Instructions for normahq/codex-acp-bridge, covering codex-acp-bridge — agents.md, development standards, quality gates (required), logging policy and bridge guardrails.