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/endgame-labs/goated/agents-mdgit clone --depth 1 https://github.com/Endgame-Labs/goatedWrote 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/instructions/endgame-labs/goated/agents-md)<a href="https://agentmods.dev/instructions/endgame-labs/goated/agents-md"><img src="https://agentmods.dev/badge/instructions/endgame-labs/goated/agents-md.svg" alt="Measured on agentmods" 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 | $0.00477 | $0.00477 |
| Opus 5 | $0.00238 | $0.00238 |
| Sonnet 5 | $0.00095 | $0.00095 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
goated 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 4d 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
AGENTS.md — Developer guide for AI agents
For codebase architecture, project structure, and how the system works, see CODEBASE.md. For agent runtime instructions (responding to users, memory, identity), see workspace/AGENTS.md.
Building
If this machine is missing Go or other prerequisites, run:
scripts/setup_machine.sh doctor
Always use build.sh — never go build directly.
./build.sh # builds both binaries
Two binaries are produced:
./goated— control CLI + daemon./workspace/goat— agent CLI (used by Claude inside workspace)
Running the daemon
./build_all_and_run_daemon.sh # builds everything, then starts daemon
Or if already built:
./goated daemon run # self-daemonizes, logs to logs/goated_daemon.log
The daemon self-backgrounds. No nohup & needed.
Restarting the daemon
Use the daemon management command — it waits for in-flight messages to flush:
./goated daemon restart --reason "deployed new build"
Verifying changes compile
gofmt -w . # format Go files before committing
go build ./... # quick compile check
go vet ./... # static analysis check before committing
./build.sh # full build
No automated tests yet. Test manually by sending messages through the gateway.
Machine setup
Goated expects:
- Go matching
go.mod tmux- one runtime CLI on
PATH:claudeorcodex
Useful commands:
scripts/setup_machine.sh doctor
scripts/setup_machine.sh install-system
scripts/setup_machine.sh install-go
Daemon watchdog
A cron watchdog ensures the daemon is always running (auto-starts it if it dies):
# Install (runs every 2 minutes):
(crontab -l 2>/dev/null; echo '*/2 * * * * /path/to/goated/scripts/watchdog.sh') | crontab -
Logs to logs/watchdog.log.
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.
- 4d ago First seen · 81 lines · 477 tokens per session scan A a415b89339e9
goated AGENTS.md is an instructions file published in the GitHub repository Endgame-Labs/goated (43 stars, last pushed 11d ago), licensed MIT. It adds 477 tokens to every session, about $0.0024 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.