agentic-harness: Instructions file for Claude Code

CLAUDE.md

agentic-harness CLAUDE.md is an instructions file for Claude Code from frangelbarrera/agentic-harness. It costs 595 tokens per session, scanned A, original, Apache-2.0.

Additional instructions for Claude Code and Claude Desktop when contributing to Agentic Harness, a Python tool for coordinating AI agents. They cover code changes, playbooks, specialists, bug fixes, and pull-request reviews.

In plain words
What is it for?
Editing the harness, writing YAML playbooks, adding specialist agents, fixing bugs, and reviewing pull requests.
Why use it?
They provide task-specific rules that supplement the project's general contribution instructions.

Instructions file for Claude Code

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

This is frangelbarrera/agentic-harness's own configuration. It tells Claude Code how to work on agentic-harness 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 agentic-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to frangelbarrera/agentic-harness. 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/frangelbarrera/agentic-harness/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/frangelbarrera/agentic-harness

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 agentic-harness CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/frangelbarrera/agentic-harness/claude-md.svg)](https://agentmods.dev/instructions/frangelbarrera/agentic-harness/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/frangelbarrera/agentic-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/frangelbarrera/agentic-harness/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 595 This file is loaded in full into every session.
When invoked 595 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 $0.00595 $0.00595
Opus 5 $0.00298 $0.00298
Sonnet 5 $0.00119 $0.00119
Haiku 4.5 $0.00060 $0.00060

Measured 7d ago against content hash 9f1684d676ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agentic-harness 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 · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Specific guidance for Claude Code / Claude Desktop contributing to Agentic Harness

This file extends AGENTS.md with Claude-specific notes.

When You're Editing Agentic Harness Code

  • Always read MANIFESTO.md first. Every PR must respect the 10 declarations.
  • Use arnes idioms, not langchain idioms. No Runnable, Chain, Agent classes.
  • Prefer functions over classes. State lives in Thread, not in objects.
  • Use pydantic for all data that crosses a boundary. Never dataclass.
  • Use async def for all I/O. The only sync code is at the CLI boundary.

When You're Writing a Playbook

  • YAML, not Python. The whole point is declarative.
  • Use English keys (name, objective, steps, specialist) — they are canonical.
  • Quote specialist names: "@planner", not @planner (YAML quirk).
  • Test with arnes lint and arnes run --mock before committing.

When You're Adding a Specialist

  • One responsibility per specialist. If you need 2 things, make 2 specialists.
  • The system_prompt is the specialist's personality. Version it. Diff it.
  • The output_schema is the contract. Never return data that doesn't match.
  • Default model is ollama/llama3.2. Don't change unless you have a strong reason.

When You're Fixing a Bug

  • Write a test that reproduces the bug first.
  • Fix the bug.
  • Verify the test passes.
  • Don't refactor unrelated code in the same PR.

When You're Reviewing a PR

  • Check manifesto compliance first.
  • Check that no vendor-only features were introduced.
  • Check that no API keys are logged or stored.
  • Check that tests exist and pass.
  • Check that the README/docs are updated if needed.

Files to Never Touch Without Discussion

  • MANIFESTO.md — immutable. If you want to change it, open a Discussion.
  • LICENSE — Apache 2.0. Don't change.
  • SECURITY.md — only update to add new security contacts or policies.
  • pyproject.toml [project] section — only bump version, don't change metadata without release.

Read the full file on GitHub · 72 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 · 72 lines · 595 tokens per session scan A 9f1684d676ab

Subscribe to this mod's changes

agentic-harness CLAUDE.md is an instructions file published in the GitHub repository frangelbarrera/agentic-harness (7 stars, last pushed 6d ago), licensed Apache-2.0. It adds 595 tokens to every session, about $0.0030 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.

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