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/clawdi-ai/clawdi/agents-mdgit clone --depth 1 https://github.com/Clawdi-AI/clawdiWrote 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/clawdi-ai/clawdi/agents-md)<a href="https://agentmods.dev/instructions/clawdi-ai/clawdi/agents-md"><img src="https://agentmods.dev/badge/instructions/clawdi-ai/clawdi/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 | $0.01598 | $0.01598 |
| Opus 5 | $0.00799 | $0.00799 |
| Sonnet 5 | $0.00320 | $0.00320 |
| Haiku 4.5 | $0.00160 | $0.00160 |
Grade A, and why
clawdi AGENTS.md scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Done: `curl -sS http://localhost:8000/health` returns `{"status":"ok"}`. How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clawdi
The best home for all your AI agents. Run them in the cloud or connect your own—with their context and tools in one place. This repository contains the CLI, FastAPI backend, TanStack dashboard, shared types, agent adapters, channels, and sync.
Maintain agent-facing repository docs with
docs/agent-docs-guide.md.
OSS Boundary
Hosted infrastructure is owned outside this repo by first-party hosted control planes. Do not add hosted service runbooks, private addresses, or internal deployment details here.
Repository Map
apps/web/ TanStack Start dashboard
backend/ FastAPI backend, async PostgreSQL, Alembic
packages/cli/ TypeScript/Bun CLI, adapters, MCP stdio server
packages/shared/ Shared types, constants, generated API client
packages/whatsapp-baileys-sidecar/ WhatsApp Baileys sidecar package
docs/ Contributor docs, ADRs, plans, scenarios
For architecture and ownership, read docs/architecture.md.
Local End-to-End
Install dependencies once:
bun install
Terminal 1, backend:
docker compose up -d postgres
cd backend
cp .env.example .env
uv sync
python3 - <<'PY'
import secrets
for name in ("VAULT_ENCRYPTION_KEY", "ENCRYPTION_KEY", "ADMIN_API_KEY"):
print(f"{name}={secrets.token_hex(32)}")
PY
Set those three generated values in backend/.env. Also set:
DEV_AUTH_BYPASS=true
DEV_AUTH_TOKEN=dev-bypass
Run backend:
pdm migrate
pdm dev
Done: curl -sS http://localhost:8000/health returns {"status":"ok"}.
Terminal 2, web:
cd apps/web
cp .env.example .env.local
Set:
VITE_CLAWDI_API_URL=http://localhost:8000
VITE_DEV_AUTH_BYPASS=true
VITE_DEV_AUTH_TOKEN=dev-bypass
Run:
bun run dev
Done: http://localhost:3000 opens the dashboard without Clerk login.
Terminal 3, CLI:
export ADMIN_API_KEY="<value-from-backend-env>"
curl -sS -X POST http://localhost:8000/v1/admin/auth/keys \
-H "X-Admin-Key: ${ADMIN_API_KEY}" \
-H "Content-Type: application/json" \
-d '{"target_clerk_id":"dev_browser","label":"local-cli"}' \
| jq -r .raw_key
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 · 218 lines · 1,598 tokens per session scan A 56f1f9b62b97
clawdi AGENTS.md is an instructions file published in the GitHub repository Clawdi-AI/clawdi (103 stars, last pushed yesterday), licensed MIT. It adds 1,598 tokens to every session, about $0.0080 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
BootAgent AGENTS.md
AGENTS.md instructions for MaimoryLab/BootAgent, covering bootagent 开发约定, 目录, 本地命令, codegraph and 代码边界.
hermes-webui AGENTS.md
AGENTS.md instructions for nesquena/hermes-webui, covering agent instructions for hermes webui, read first, onboarding and reinstall support, contribution style and before you open a pr — the change guidelines.
zeroclaw CLAUDE.md
Claude Code instructions for zeroclaw-labs/zeroclaw, covering claude.md — zeroclaw (claude code), claude code settings, hooks and slash commands.
rosclaw CLAUDE.md
Claude Code instructions for ros-claw/rosclaw, covering claude.md — rosclaw project onboarding, rosclaw runtime boundary (managed), safety contract (p0), robot integration setup and capability apps.
lobu AGENTS.md
Instructions for lobu-ai/lobu, covering repo map, unrecoverable — never do these, facts you cannot derive, ship a change and how to work.
OpenPersona AGENTS.md
Instructions for acnlabs/OpenPersona, covering agents.md, project overview, setup, project structure and architecture rules.