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/danielsmithdevelopment/clawql/agents-mdgit clone --depth 1 https://github.com/danielsmithdevelopment/ClawQLWhat 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 | $0.00500 | $0.00500 |
| Opus 5 | $0.00250 | $0.00250 |
| Sonnet 5 | $0.00100 | $0.00100 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
ClawQL 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 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.
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
Agent behavior (MCP + enterprise proxy)
Use this file when an MCP client (Cursor, IDE agents, or automation) talks to ClawQL through an intercepting proxy that enforces JWT ATR or similar policy (see #272 and docs/security/mcp-proxy-jwt-atr.md).
Effect-TS (hard rule)
Production code that can be Effect-based must be — there is no "pure sync is fine" carve-out. Never ship domain IO, orchestration, policy, or even sync helpers (URL/HTML builders, sync crypto, env flag readers) as bare async/Promise/plain-value APIs when an Effect Context.Tag + Layer or Effect.sync is possible. Forced Promise edges (Express / MCP SDK) stay thin façades over run*Effect; run Effect.runSync only at those absolute host boundaries. Only types-only modules are exempt. Details: .cursor/rules/effect-ts-everywhere.mdc.
Blocked or denied tool calls
- Stop and report. If the proxy or server returns an error (including HTTP 403, JSON-RPC error, or an explicit “blocked by policy” body), tell the human operator what failed and why, using the response payload when available.
- No silent retry loops. Do not assume transient failure and hammer the same tool call. At most one deliberate retry is acceptable after the user confirms a fix (token refresh, scope change, outage cleared).
- No fabricated success. Do not pretend a tool ran or invent results when the MCP layer returned an error.
Related docs
- Defense-in-depth narrative (Panguard / ATR / synchronous blocking):
docs/security/clawql-comprehensive-defense-in-depth-mcp-k3s-may-2026.md(especially §9) - Chokepoint ordering and Helm/mesh notes:
docs/security/mcp-proxy-jwt-atr.md
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 · 19 lines · 500 tokens per session scan A 5164f520ada5
ClawQL AGENTS.md is an instructions file published in the GitHub repository danielsmithdevelopment/ClawQL (12 stars, last pushed 3d ago), licensed Apache-2.0. It adds 500 tokens to every session, about $0.0025 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
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.
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).
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.