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/zgbrenner/agentcounsel/agents-mdgit clone --depth 1 https://github.com/zgbrenner/agentcounselWrote 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/zgbrenner/agentcounsel/agents-md)<a href="https://agentmods.dev/instructions/zgbrenner/agentcounsel/agents-md"><img src="https://agentmods.dev/badge/instructions/zgbrenner/agentcounsel/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 | $0.02571 | $0.02571 |
| Opus 5 | $0.01286 | $0.01286 |
| Sonnet 5 | $0.00514 | $0.00514 |
| Haiku 4.5 | $0.00257 | $0.00257 |
Grade A, and why
agentcounsel 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — AgentCounsel
This file tells an AI agent how to operate in this repository. It is the
universal, tool-agnostic operating manual. CLAUDE.md, GEMINI.md, and the
files under adapters/ layer environment-specific guidance on top of it. If
your environment does not read AGENTS.md, read this file anyway.
What this repository is
AgentCounsel is a Markdown-native library of legal skills. Each skill is a structured workflow that helps produce draft legal work product for attorney review — never legal advice, never a final answer, never an opinion. The library supplies process and structure; a qualified, licensed legal professional reviews and adopts every output.
The canonical legal library is plain Markdown. Standard-library tooling validates and packages it, and an optional local MCP/CLI layer provides typed routing, selective context, and matter-plan inspection. No hosted backend is required.
First, decide which job you are doing
Every task here is one of two jobs. Decide which before you act.
- Using a skill — running a legal workflow to produce a draft deliverable.
This is most tasks. Do not edit any file under
skills/,core/, oradapters/. - Editing the library — adding or improving a skill, template, adapter, or
doc. Only when the task is explicitly to change the library. Follow
CONTRIBUTING.md.
If you are unsure which job you are doing, ask. Do not edit the library by accident.
Job 1 — Using a skill
- Read
core/first. The files incore/are the operating rules every skill inherits. They always apply. Read them before reasoning about any skill. - Route the task. Use
WORKFLOW_ROUTER.mdto map "I need to do X" to a skill; browseSKILLS_INDEX.md;COMMANDS.mdlists slash-style shorthands.CONTEXT.mddefines the repository's vocabulary — use terms like "skill," "template," and "canonical" precisely. - For a supported multi-step matter, inspect the matter plan. Use
matter-plans/orscripts/matter_plan_cli.pywhen you need typed dependencies, artifact handoffs, parallel lanes, and attorney gates. A plan organizes work; it does not execute legal analysis or approve a gate. - Open the single narrowest relevant skill. Read its
SKILL.mdand any file in itstemplates/folder. Do not load unrelated practice areas — extra context degrades the work (see "Why this discipline exists"). - Follow the skill exactly. Satisfy its Required Inputs gate before substantive work. Follow its Workflow and Output Format. Do not improvise steps or invent a workflow.
- Hand off for review. Deliver with the skill's Attorney Verification Checklist, unchecked. The agent never checks the boxes — the reviewing attorney does.
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 · 194 lines · 2,571 tokens per session scan A 1ccedc3411d8
agentcounsel AGENTS.md is an instructions file published in the GitHub repository zgbrenner/agentcounsel (18 stars, last pushed 1mo ago), licensed MIT. It adds 2,571 tokens to every session, about $0.0129 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
fedlex-mcp CLAUDE.md
Claude Code instructions for malkreide/fedlex-mcp, covering claude.md, teil 1 — portfolio-konventionen, vor der arbeit, tests and wenn etwas rot ist.
legal-case-research AGENTS.md
AGENTS.md instructions for silvrblt/legal-case-research, covering agents.md —— 给 ai 智能体的运行指南（工具无关）, 这个项目是什么, 数据从哪来（两种，二选一）, 一个智能体应当怎么跑 and 哪些 ai 能跑完这套工作流.
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).