Antfarm is a workflow tool for OpenClaw that coordinates specialized AI agents, such as planners, developers, testers, verifiers, and reviewers, to complete software tasks together. It is used for repeatable feature development, security audits, and bug fixes that produce tested pull requests. The catalogue add-on provides Antfarm-related agent instructions and skills.
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/snarktank/antfarm/agents-mdgit clone --depth 1 https://github.com/snarktank/antfarmWrote 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/snarktank/antfarm/agents-md)<a href="https://agentmods.dev/instructions/snarktank/antfarm/agents-md"><img src="https://agentmods.dev/badge/instructions/snarktank/antfarm/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 | $0.00582 | $0.00582 |
| Opus 5 | $0.00291 | $0.00291 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
antfarm 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 5d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Antfarm Agents
Antfarm provisions multi-agent workflows for OpenClaw. It installs workflow agent workspaces, wires agents into the OpenClaw config, and keeps a run record per task.
Installing Antfarm
Prerequisites: Node.js >= 22, OpenClaw v2026.2.9+, gh CLI (for PR steps).
Do NOT run
npm install antfarm. There is an unrelated package on npm with that name. Antfarm is installed from GitHub only.
Steps
-
Clone the repo into the OpenClaw workspace:
git clone https://github.com/snarktank/antfarm.git ~/.openclaw/workspace/antfarm -
Build:
cd ~/.openclaw/workspace/antfarm npm install npm run build -
Link the CLI (makes
antfarmavailable globally):npm link -
Install workflows (provisions agents, cron jobs, and DB):
antfarm install -
Verify: Run
antfarm workflow list— you should see the available workflows.
If antfarm fails with a node:sqlite error, your node binary may be Bun's wrapper instead of real Node.js 22+. Check with node -e "require('node:sqlite')". See #54 for workarounds.
Why Antfarm
- Repeatable workflow execution: Start the same set of agents with a consistent prompt and workspace every time.
- Structured collaboration: Each workflow defines roles (lead, developer, verifier, reviewer) and how they hand off work.
- Traceable runs: Runs are stored by task title so you can check status without hunting through logs.
- Clean lifecycle: Install, update, or uninstall workflows without manual cleanup.
What It Changes in OpenClaw
- Adds workflow agents to
openclaw.json(your main agent stays default). - Creates workflow workspaces under
~/.openclaw/workspaces/workflows. - Stores workflow definitions and run state under
~/.openclaw/antfarm. - Inserts an Antfarm guidance block into the main agent's
AGENTS.mdandTOOLS.md.
Uninstalling
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.
- 5d ago First seen · 59 lines · 582 tokens per session scan A 1936fd662d32
antfarm AGENTS.md is an instructions file published in the GitHub repository snarktank/antfarm (2,499 stars, last pushed 6mo ago), licensed MIT. It adds 582 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.
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.