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/hoolc/codex-feishu-bot/agents-mdgit clone --depth 1 https://github.com/HOOLC/codex-feishu-botWhat 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 | $0.00585 | $0.00585 |
| Opus 5 | $0.00293 | $0.00293 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
codex-feishu-bot 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repository is designed for a Codex-operated bootstrap flow.
Primary Goal
Set up and deploy a Feishu bot backed by codex app-server with as little manual work as possible. The intended operator is another Codex session running on the user's machine.
Required Execution Order
- Read
README.md. - Read
docs/codex-bootstrap-playbook.md. - Read
docs/feishu-console-automation.md. - Run
pnpm install. - Run
pnpm bootstrap:env. - Run
pnpm chrome:debug. - Use browser automation through Chrome CDP to configure Feishu Open Platform.
- Persist discovered values into
.env.real. - Start Docker deployment with
pnpm docker:up. - Verify with
pnpm docker:smoke.
Browser Automation Rules
- Prefer Chrome DevTools Protocol automation over telling the user to click around manually.
- If
agent-browseris available, prefer it. Otherwise use any browser/CDP capability available in Codex. - Reuse an existing Feishu app when it is clearly the intended app; otherwise create a new enterprise self-built app.
- Drive the UI by visible labels and user goals, not brittle CSS selectors.
What Still Requires the User
- Logging into Feishu Open Platform in the browser.
- Logging into OpenAI/Codex if the local
~/.codexstate is missing. - Approving tenant-admin prompts if the organization requires them.
Only stop for those checkpoints. Do not push routine console clicking back onto the user.
Deployment Rules
- Use the Docker path for setup and validation. Do not default to
pnpm start. - Use the single-container Docker path. Do not reintroduce a
codex-app-serversidecar deployment mode. - Keep runtime secrets in
.env.real. - Keep Codex runtime work under the mounted
/workspaceonly. Do not treat the repository checkout as the runtime workspace. - Prefer
CODEX_HOME_SOURCE=/absolute/path/to/~/.codexwhen local Codex auth already exists; only fall back toOPENAI_API_KEYwhen it does not. - Keep generated user-facing files under
CODEX_ARTIFACTS_DIRunless the user explicitly asks to write into the repository itself. - Never commit
.env.realor local browser profile data. - Prefer
pnpm docker:*commands for validation and debugging.
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 · 57 lines · 585 tokens per session scan A dffe9d14279c
codex-feishu-bot AGENTS.md is an instructions file published in the GitHub repository HOOLC/codex-feishu-bot (11 stars, last pushed 5mo ago), licensed MIT. It adds 585 tokens to every session, about $0.0029 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.