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/openclaw/clawdinators/agents-mdgit clone --depth 1 https://github.com/openclaw/clawdinatorsWhat 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 | $0.02033 | $0.02033 |
| Opus 5 | $0.01017 | $0.01017 |
| Sonnet 5 | $0.00407 | $0.00407 |
| Haiku 4.5 | $0.00203 | $0.00203 |
Grade C, and why
clawdinators AGENTS.md scanned grade C with 1 finding 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- Agenix identity is `~/.ssh/id_ed25519` (primary SSH key). How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAWDINATOR Agent Notes
Read these before acting:
- docs/PHILOSOPHY.md
- docs/ARCHITECTURE.md
- docs/SHARED_MEMORY.md
- docs/SECRETS.md
- docs/POC.md
- BOOTSTRAP.md
- IDENTITY.md
- SOUL.md
- TOOLS.md
- USER.md
Memory references:
- For project goals, read memory/project.md
- For architecture decisions, read memory/architecture.md
- For ops runbook, read memory/ops.md
- For Discord context, also read memory/discord.md
Repo rule: no inline scripting languages (Python/Node/etc.) in Nix or shell blocks; put logic in script files and call them.
System ownership (3 repos):
openclaw: upstream runtime and behavior.nix-openclaw: packaging/build fixes for clawbot.clawdinators: infra, NixOS config, secrets wiring, deployment flow.
Maintainer role:
- Monitor issues + PRs and keep an inventory of what needs human attention.
- Surface priorities and context; do not file issues or modify code unless asked.
- Track running versions (openclaw/nix-openclaw/clawdinators) and note them in
memory/ops.md.
Toolchain workflow (repo source of truth):
- Add/remove tools in
nix/tools/clawdinator-tools.nix(packages + descriptions). - Tools list is rendered into
/etc/clawdinator/tools.mdby Nix and appended to workspaceTOOLS.mdat seed time. - Keep
clawdinator/workspace/TOOLS.mdaligned with upstream template; do not hardcode tool lists there. - When you add a new tool, verify it appears in
/etc/clawdinator/tools.mdand in the workspaceTOOLS.mdafter seed.
The Zen of Python Moltbot, by shamelessly stolen from Tim Peters:
- Beautiful is better than ugly.
- Explicit is better than implicit.
- Simple is better than complex.
- Complex is better than complicated.
- Flat is better than nested.
- Sparse is better than dense.
- Readability counts.
- Special cases aren't special enough to break the rules.
- Although practicality beats purity.
- Errors should never pass silently.
- Unless explicitly silenced.
- In the face of ambiguity, refuse the temptation to guess.
- There should be one-- and preferably only one --obvious way to do it.
- Although that way may not be obvious at first unless you're Dutch.
- Now is better than never.
- Although never is often better than right now.
- If the implementation is hard to explain, it's a bad idea.
- If the implementation is easy to explain, it may be a good idea.
- Namespaces are one honking great idea -- let's do more of those!
Deploy flow (automation-first):
- Use
devenv.nixfor tooling (nixos-generators, awscli2). - Build a bootstrap NixOS image with nixos-generators (raw) and upload it to S3.
- Use
nix/hosts/clawdinator-1-image.nixfor image builds.
- Use
- The old CI AMI/update/release workflows are intentionally disabled under
.github/workflows-disabled/; AMI builds and deploys now require an explicit code change or a local operator run. - Image history is bounded on purpose: raw
clawdinator-nixos-*uploads expire automatically, and old CLAWDINATOR AMIs/snapshots are pruned after successful builds while keeping the live fleet AMI plus a short rollback window. - Resume AMI pipeline work immediately if it stalls; do not use rsync as a workaround. Host edits are allowed but must be committed and baked into a new AMI to persist.
- CI must provide
CLAWDINATOR_AGE_KEYto build + upload the runtime bootstrap bundle to S3. - Bootstrap bundle location:
s3://${S3_BUCKET}/bootstrap/<instance>/(secrets + repo seeds). - Bootstrap S3 bucket + scoped IAM user + VM Import role with
infra/opentofu/aws(use homelab-admin creds). - Bootstrap AWS instances from the AMI with
infra/opentofu/aws(setTF_VAR_ami_id). - Import the image into AWS as an AMI (snapshot import + register image).
- Ensure secrets are encrypted to the baked agenix key (see
../nix/nix-secrets/secrets.nix). - Ensure required secrets exist:
clawdinator-github-app.pem,clawdinator-discord-token-<n>,clawdinator-control-token,clawdinator-control-aws-*,clawdinator-anthropic-api-key. - Update
nix/hosts/<host>.nix(Discord allowlist, GitHub App installationId, identity name). - Discord must use
messages.queue.byChannel.discord = "interrupt";queuedelays replies to heartbeat and makes the bot appear dead. - Ensure
/var/lib/clawd/repos/clawdinatorscontains this repo (self-update requires it). - Verify systemd services:
clawdinator;clawdinator-github-app-tokenonly on hosts that explicitly enable GitHub App auth. - Commit and push changes; repo is the source of truth.
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 · 126 lines · 2,033 tokens per session scan C 2ebf11000423
clawdinators AGENTS.md is an instructions file published in the GitHub repository openclaw/clawdinators (158 stars, last pushed 22d ago), licensed MIT. It adds 2,033 tokens to every session, about $0.0102 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). 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.