Harness-Creator: Instructions file for Claude Code

CLAUDE.md

Harness-Creator CLAUDE.md is an instructions file for Claude Code from tjdwls101010/Harness-Creator. It costs 596 tokens per session, scanned A, original, MIT.

Repository instructions for developing Harness-Creator, a tool that designs and checks Claude Code setup files such as rules, skills, hooks, permissions, and workflows.

In plain words
What is it for?
Use them when modifying Harness-Creator, its documentation, scripts, or tests, especially when checking which plan is current and where files belong.
Why use it?
They give coding agents a shared map of the repository and its current implementation decisions, reducing guesswork and misplaced changes.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is tjdwls101010/Harness-Creator's own configuration. It tells Claude Code how to work on Harness-Creator 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 Harness-Creator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tjdwls101010/Harness-Creator. 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/tjdwls101010/Harness-Creator/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/tjdwls101010/Harness-Creator

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 Harness-Creator CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tjdwls101010/harness-creator/claude-md/github.svg)](https://agentmods.dev/instructions/tjdwls101010/harness-creator/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/tjdwls101010/harness-creator/claude-md"><img src="https://agentmods.dev/badge/instructions/tjdwls101010/harness-creator/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Harness-Creator CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tjdwls101010/harness-creator/claude-md"><img src="https://agentmods.dev/badge/instructions/tjdwls101010/harness-creator/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 596 This file is loaded in full into every session.
When invoked 596 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 $0.00596 $0.00596
Opus 5 $0.00298 $0.00298
Sonnet 5 $0.00119 $0.00119
Haiku 4.5 $0.00060 $0.00060

Measured 10d ago against content hash c790c6ff184d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

Harness-Creator 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 10d 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 · 18 lines

How it starts

The opening of the file, as written. The whole thing — 18 lines — stays where its author put it; the contents beside it link to each section on GitHub.

harness-creator

This repo builds harness-creator, a meta-skill that designs, generates, and validates Claude Code harnesses (CLAUDE.md, rules, skills, hooks, permissions, agents, workflows) for other projects through a structured interview.

Where things live

  • The skill itself: .claude/skills/harness-creator/SKILL.md is the orchestrator, references/ holds per-component authoring guides, scripts/ holds the Python CLIs it calls.
  • The binding implementation spec: docs/plan/, one directory per generation with the newest last — start at the highest-numbered one's 00-overview.md, which carries that generation's decision log and says which earlier decisions it revises. Earlier generations stay as written; they are the citation record, not a live spec. If you change a decision, edit the newest generation's plan and record why.
  • Self-test fixtures for the scripts: tests/fixtures/ at the repo root, not inside the skill — anything under the skill directory ships to plugin users, so dev-only fixtures stay outside it.
  • Local reference snapshots the plan was researched against: .tmp/docs_claude/ and .tmp/skill-creator/ — gitignored, not part of this repo's own history.

Working on this repo

  • This repo is dogfooding its own output shape: .claude/skills/harness-creator/ is simultaneously (a) a project skill for this repo and (b) the plugin's skill component (.claude-plugin/plugin.json's skills field points here). Don't duplicate the skill elsewhere.
  • Daily development loop is the symlink, not the plugin install: ~/.claude/skills/harness-creator → this repo's skill directory. Edits are reflected immediately in a fresh session. Only install the plugin via the local marketplace when smoke-testing the distribution path itself, and uninstall it afterward — running both at once double-registers the skill under two different names (bare harness-creator vs. harness-creator:harness-creator).
  • No mid-sentence hard line-wraps in any markdown written here (SKILL.md, references, this file, generated harness output). Line breaks only at sentence/list/paragraph boundaries — hard wraps break Edit-tool string matching and pollute diffs, and renderers soft-wrap anyway.
  • Every claim the skill makes about Claude Code mechanics (hook exit codes, matcher syntax, CLAUDE.md loading semantics, etc.) must be checked against .tmp/docs_claude/ or docs/plan/research/ before being written into a reference file — this skill's entire value is gotcha density, and a wrong gotcha is worse than no gotcha.

Read the full file on GitHub · 18 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. 10d ago First seen · 18 lines · 596 tokens per session scan A c790c6ff184d

Subscribe to this mod's changes

Harness-Creator CLAUDE.md is an instructions file published in the GitHub repository tjdwls101010/Harness-Creator (4 stars, last pushed 2d ago), licensed MIT. It adds 596 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

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

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 · 5,153 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

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

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

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