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/lexq-io/lexq-cli/agents-mdgit clone --depth 1 https://github.com/lexq-io/lexq-cliWhat 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 | $0.02052 | $0.02052 |
| Opus 5 | $0.01026 | $0.01026 |
| Sonnet 5 | $0.00410 | $0.00410 |
| Haiku 4.5 | $0.00205 | $0.00205 |
Grade A, and why
lexq-cli 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 yesterday.
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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — LexQ CLI Agent Guide
For AI Agents and AI-powered IDEs (Claude Code, Cursor, Windsurf, Cline, Gemini CLI, Copilot, and others).
What is this?
LexQ CLI (@lexq/cli, binary: lexq) manages a policy execution engine. Policies are business rules (if-then) that
evaluate input facts and produce actions (discounts, blocks, notifications, etc.).
The CLI also doubles as an MCP server — run lexq serve --mcp to expose the full command inventory as MCP tools to
any MCP-compatible AI client.
This file tells you how to use the CLI as an AI agent.
Quick Start
# 1. Install
npm install -g @lexq/cli
# or: npx @lexq/cli
# 2. Authenticate
lexq auth login
# Enter API key when prompted
# 3. Verify
lexq auth whoami
Skills
Detailed documentation lives in the skills/ directory. Read the relevant skill before executing commands.
| Skill | File | What it covers |
|---|---|---|
| Shared | skills/lexq-shared/SKILL.md |
Core concepts, auth, workflow, error codes. Read first. |
| Groups | skills/lexq-groups/SKILL.md |
Policy groups, conflict resolution, A/B testing |
| Rules | skills/lexq-rules/SKILL.md |
Condition syntax, action types, mutex, examples |
| Simulation | skills/lexq-simulation/SKILL.md |
Dry run, Impact Simulation, compare |
| Execution | skills/lexq-execution/SKILL.md |
History, stats, failure logs, provenance, replay, latency profile, deployment monitoring |
| Recipes | skills/lexq-recipes/SKILL.md |
End-to-end workflows (copy-paste ready) |
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.
- yesterday First seen · 183 lines · 2,052 tokens per session scan A 58384e0766b6
lexq-cli AGENTS.md is an instructions file published in the GitHub repository lexq-io/lexq-cli (0 stars, last pushed 4d ago), licensed Apache-2.0. It adds 2,052 tokens to every session, about $0.0103 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 2026-08-31.
Other instructions, from other repositories
liteflow CLAUDE.md
Instructions for dromara/liteflow, covering claude.md, 概述, 命令, 构建 and 构建整个项目（模块集由 jdk 版本自动选择 —— 见下方说明）.
liteflow AGENTS.md
Instructions for dromara/liteflow, covering agents.md, commands, build, build with tests and build specific module.
steward AGENTS.md
Instructions for Steward-Fi/steward, covering repository operating guide, setup, validation, generated files and database migrations.
FeatherlaneAI AGENTS.md
Instructions for ducnguyen67201/FeatherlaneAI, covering repository agent instructions, skills, architecture: rust backend is the source of truth, page integration expectations and implementation checklist.
ActPlane CLAUDE.md
Instructions for eunomia-bpf/ActPlane, covering claude.md, agent behavioral constraints (actplane-applied), oss change workflow, build & test commands and individual components.
steward CLAUDE.md
Instructions for Steward-Fi/steward: Follow the repository-wide instructions in AGENTS.md.