agentmods.dev

agentcounsel: Instructions file for Claude Code

CLAUDE.md

agentcounsel CLAUDE.md is an instructions file for Claude Code from zgbrenner/agentcounsel. It costs 786 tokens per session, scanned A, original, MIT.

A repository guide for AgentCounsel, a library that gives coding agents specialized skills and workflows. It explains how to route tasks and which parts of the library may be edited.

In plain words
What is it for?
Use it at the start of AgentCounsel work to choose between using a skill and editing the library, then consult the project indexes and required core files.
Why use it?
It helps agents load the right rules and avoid changing library internals when the task only involves using a skill.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is zgbrenner/agentcounsel's own configuration. It tells Claude Code how to work on agentcounsel itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentcounsel configures →

not rated 18repo +1 1mo ago A scan 786 tokens original MIT
View source ↗ zgbrenner/agentcounsel zgbrenner.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to zgbrenner/agentcounsel. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zgbrenner/agentcounsel/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/zgbrenner/agentcounsel

Made for: Claude Code.

Wrote 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.

agentmods badge for agentcounsel CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zgbrenner/agentcounsel/claude-md.svg)](https://agentmods.dev/instructions/zgbrenner/agentcounsel/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zgbrenner/agentcounsel/claude-md"><img src="https://agentmods.dev/badge/instructions/zgbrenner/agentcounsel/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 786 This file is loaded in full into every session.
When invoked 786 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00786 $0.00786
Opus 5 $0.00393 $0.00393
Sonnet 5 $0.00157 $0.00157
Haiku 4.5 $0.00079 $0.00079

Measured 7d ago against content hash 47b3a32a1534, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agentcounsel CLAUDE.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 7d 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.

CLAUDE.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — AgentCounsel

Claude Code's operating guide for this repository. The universal, tool-agnostic operating manual is AGENTS.md; it is imported below, so every Claude Code session loads it. Read it — everything in it applies. This file adds only what is specific to Claude Code.

@AGENTS.md

Before anything else

  • Decide your job: using a skill or editing the library (see AGENTS.md). Never edit files under skills/, core/, or adapters/ unless the task is explicitly to change the library.
  • Reload core/ every session. For any legal task, read every file in core/ before reasoning about a skill. Claude does not retain them between sessions — treat each session as a fresh start and load the rules again.

Routing efficiently

  • To find the right skill, prefer the index files — WORKFLOW_ROUTER.md, SKILLS_INDEX.md, COMMANDS.md — over broad codebase searches.
  • When a task could span several skills and you need to scan many SKILL.md files, use the Explore subagent so the routing search does not flood the main context. Then open only the single narrowest skill. Loading unrelated practice areas degrades the work — see the LLM-pitfalls table in AGENTS.md.
  • Make independent reads in parallel: gather the core/ files and the chosen SKILL.md in one batch.

Editing the library with Claude Code

When the task is explicitly to change the library:

  • Use Plan mode for anything touching more than one skill, core/, or a shared reference file — agree the plan before editing.
  • After your edits, before reporting done, run the validation suite from AGENTS.md ("Done means validation passes") and read the output.
  • Claude Code's /review and /security-review commands are useful here: run /review before opening a pull request, and /security-review for any change that adds tooling or touches scripts/.
  • Keep changes small and reviewable. A 12-line diff a maintainer can verify beats a 600-line one they cannot — the generation–verification loop from AGENTS.md, applied to library edits.

Read the full file on GitHub · 67 lines

Changes

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.

  1. 7d ago First seen · 67 lines · 786 tokens per session scan A 47b3a32a1534

Subscribe to this mod's changes

agentcounsel CLAUDE.md is an instructions file published in the GitHub repository zgbrenner/agentcounsel (18 stars, last pushed 1mo ago), licensed MIT. It adds 786 tokens to every session, about $0.0039 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.

Building agentsclaude-skillslegal operationslegal-agentslegal-researchlegal-skillslegal-workflows
Related

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens