Borrowing it
Nothing to install: this file belongs to jcwleo/oh-no-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.
curl -O https://raw.githubusercontent.com/jcwleo/oh-no-harness/main/CLAUDE.mdgit clone --depth 1 https://github.com/jcwleo/oh-no-harnessWrote 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/jcwleo/oh-no-harness/claude-md)<a href="https://agentmods.dev/instructions/jcwleo/oh-no-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/jcwleo/oh-no-harness/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.
<a href="https://agentmods.dev/instructions/jcwleo/oh-no-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/jcwleo/oh-no-harness/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.03561 | $0.03561 |
| Opus 5 | $0.01781 | $0.01781 |
| Sonnet 5 | $0.00712 | $0.00712 |
| Haiku 4.5 | $0.00356 | $0.00356 |
Grade A, and why
oh-no-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 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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Read this first
Two AGENTS.md files are authoritative and constrain almost every change here. Read them before editing:
AGENTS.md— the repo root is a marketplace wrapper only.plugins/oh-no-harness/AGENTS.md— rules for the plugin itself (public skill surface, source-vs-generated layers, regeneration).
Contributor workflow detail lives in plugins/oh-no-harness/CONTRIBUTING.md.
Never register this checkout as a live marketplace source
Do not register this development checkout as a directory-source marketplace for daily use (claude plugin marketplace add <this checkout> or a directory entry in extraKnownMarketplaces). When the marketplace points at the checkout, Claude Code loads skills/agents directly from the working tree, which causes two recurring failure modes:
configure-subagentsrefuses to run against a Git checkout (generator-owned agents), so subagent model/effort preferences silently never apply — agents run on the generator defaults committed inagents/*.md.- Uncommitted working-tree edits leak into live sessions, and debugging "which file is actually loaded" wastes time (cache vs. checkout confusion).
The supported Claude Code setup: install from the GitHub marketplace (jcwleo/oh-no-harness) so the runtime loads from the plugin cache, and test local changes with the sandboxed smoke scripts (scripts/test-claude-plugin.sh, scripts/test-codex-plugin.sh, scripts/test-opencode-plugin.sh, scripts/test-opencode-package.sh). The Claude smoke script fails closed rather than register a marketplace from a local source into your real ~/.claude; run it with --isolated-config (a throwaway config home the script creates and cleans up) so the checkout never becomes your daily-use registration. Only use a directory marketplace registration temporarily, and remove it afterwards. OpenCode installs the public oh-no-harness npm plugin through its native package loader; package tests use disposable roots.
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.
- 10d ago First seen · 140 lines · 3,561 tokens per session scan A 467c114477a7
oh-no-harness CLAUDE.md is an instructions file published in the GitHub repository jcwleo/oh-no-harness (11 stars, last pushed 1mo ago), licensed MIT. It adds 3,561 tokens to every session, about $0.0178 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
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.
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 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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.