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/coder/agentapi/agents-mdgit clone --depth 1 https://github.com/coder/agentapiWhat 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 | $0.00812 | $0.00812 |
| Opus 5 | $0.00406 | $0.00406 |
| Sonnet 5 | $0.00162 | $0.00162 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
agentapi 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 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI agents working with code in this repository.
Build Commands
make build- Build the binary toout/agentapi(includes chat UI build)make embed- Build the chat UI and embed it into Gogo build -o out/agentapi main.go- Direct Go build without chat UIgo generate ./...- Generate OpenAPI schema and version info
Testing
go test ./...- Run all Go tests- Tests are located alongside source files (e.g.,
lib/httpapi/server_test.go)
Development Commands
agentapi server -- claude- Start server with Claude Code agentagentapi server -- aider --model sonnet- Start server with Aider agentagentapi server -- goose- Start server with Goose agentagentapi server --type=codex -- codex- Start server with Codex (requires explicit type)agentapi server --type=gemini -- gemini- Start server with Gemini (requires explicit type)agentapi attach --url localhost:3284- Attach to running agent terminal- Server runs on port 3284 by default
- Chat UI available at http://localhost:3284/chat
- API documentation at http://localhost:3284/docs
Architecture
This is a Go HTTP API server that controls coding agents (Claude Code, Aider, Goose, etc.) through terminal emulation.
Core Components:
main.go- Entry point using cobra CLI frameworkcmd/- CLI command definitions (server, attach)lib/httpapi/- HTTP server, routes, and OpenAPI schemalib/screentracker/- Terminal output parsing and message splittinglib/termexec/- Terminal process execution and managementlib/msgfmt/- Message formatting for different agent types (claude, goose, aider, codex, gemini, amp, cursor-agent, cursor, auggie, custom)chat/- Next.js web UI (embedded into Go binary)
Key Architecture:
- Runs agents in an in-memory terminal emulator
- Translates API calls to terminal keystrokes
- Parses terminal output into structured messages
- Supports multiple agent types with different message formats
- Embeds Next.js chat UI as static assets in Go binary
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 · 86 lines · 812 tokens per session scan A fcee578e30bf
agentapi AGENTS.md is an instructions file published in the GitHub repository coder/agentapi (1,490 stars, last pushed 3mo ago), licensed MIT. It adds 812 tokens to every session, about $0.0041 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
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.