Harness-devkit: Instructions file for Claude Code

CLAUDE.md

Harness-devkit CLAUDE.md is an instructions file for Claude Code from LuisFelipeMoro/Harness-devkit. It costs 200 tokens per session, scanned A, original, MIT.

Repository instructions for claude-devkit, a toolkit for working with Claude Code. They keep the project's engineering standards in one shared file so different copies do not drift apart.

In plain words
What is it for?
Use it when changing the claude-devkit repository and when checking which engineering rules apply. It also identifies the file installed globally for other projects.
Why use it?
Without one source of truth, contributors and coding agents may follow different rules as the project changes. These instructions point work back to the canonical standards file.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md.

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

Reuse

Borrowing it

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

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-devkit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/luisfelipemoro/harness-devkit/claude-md/github.svg)](https://agentmods.dev/instructions/luisfelipemoro/harness-devkit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/luisfelipemoro/harness-devkit/claude-md"><img src="https://agentmods.dev/badge/instructions/luisfelipemoro/harness-devkit/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-devkit CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/luisfelipemoro/harness-devkit/claude-md"><img src="https://agentmods.dev/badge/instructions/luisfelipemoro/harness-devkit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 200 This file is loaded in full into every session.
When invoked 200 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 $0.00200 $0.00200
Opus 5.5 $0.00080 $0.00080
Sonnet 5.5 $0.00040 $0.00040
Haiku 4.5 $0.00020 $0.00020

Measured 2mo ago against content hash 626c4c7af58c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Harness-devkit 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 2mo 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 · 14 lines

What it actually says

claude-devkit — Project Memory

This repository is the claude-devkit. The engineering standards live in exactly one file — plugins/coding-pipeline/CLAUDE.md — which is what scripts/install-global.sh ships to ~/.claude/devkit/CLAUDE.md.

They are deliberately not @-imported here. Anyone who installed the devkit already has that same file imported globally, so importing it again would load ~6.5k tokens of identical content twice in every session spent working on the devkit itself — and the standards' own first rule is that an addition must earn its tokens.

If you are contributing here without the devkit installed, install it (bash install.sh) or read plugins/coding-pipeline/CLAUDE.md directly — it is the contract this repo is built to.

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. 2mo ago Changed · +5 lines · +96 tokens per session 626c4c7af58c
  2. 2mo ago First seen · 9 lines · 104 tokens per session scan A 7d7107413826

Subscribe to this mod's changes

Harness-devkit CLAUDE.md is an instructions file published in the GitHub repository LuisFelipeMoro/Harness-devkit (13 stars, last pushed 3d ago), licensed MIT. It adds 200 tokens to every session, about $0.0008 per session on Opus 5.5. 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

Harness-devkit CLAUDE.md compared with instructions from other repositories

Harness-devkit CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Harness-devkit CLAUDE.mdLuisFelipeMoro/Harness-devkitInstructions file133d agoMITA200Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA1,907GitHub Copilot