claude-superdev-harness: Instructions file for Claude Code

CLAUDE.md

claude-superdev-harness CLAUDE.md is an instructions file for Claude Code from will-pagane/claude-superdev-harness. It costs 1,264 tokens per session, scanned A, original, MIT.

A project instruction file that sets working rules for Claude Code, an AI coding assistant, across a software repository. It covers language, naming, and Git branch and worktree conventions.

In plain words
What is it for?
Use it to guide repository-wide agent behavior, choose branch names, keep code and configuration naming consistent, and manage one worktree per session.
Why use it?
It gives coding agents consistent project rules so different sessions do not use conflicting names, languages, or Git layouts. A worktree is a separate working copy of a repository.

Instructions file for Claude Code

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

This is will-pagane/claude-superdev-harness's own configuration. It tells Claude Code how to work on claude-superdev-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 claude-superdev-harness configures →

Reuse

Borrowing it

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

README.md
[![agentmods](https://agentmods.dev/badge/instructions/will-pagane/claude-superdev-harness/claude-md.svg)](https://agentmods.dev/instructions/will-pagane/claude-superdev-harness/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/will-pagane/claude-superdev-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/will-pagane/claude-superdev-harness/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,264 This file is loaded in full into every session.
When invoked 1,264 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 $0.01264 $0.01264
Opus 5 $0.00632 $0.00632
Sonnet 5 $0.00253 $0.00253
Haiku 4.5 $0.00126 $0.00126

Measured 6d ago against content hash 1fe768eef5fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

claude-superdev-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 6d 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 · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Global CLAUDE.md — Mandatory Rules for All Projects

This file is law, not recommendation. Follow every rule exact.

Language

  • Respond and comment code in Brazilian Portuguese, unless context need other language
  • CLAUDE.md, code, memory files: always English

Naming Conventions

  • Match existing project patterns first — codebase use camelCase for JSON keys → don't switch to snake_case
  • Never mix conventions in same file/module
  • Renaming → update all references across codebase, not just definition

Git branches & worktrees (per session)

Name every branch/worktree for what session doing + timestamp. NEVER keep tool auto-generated random name (e.g. claude/magical-jones-8c99, worktree-foo, perf-review) — rename or recreate to this scheme so concurrent sessions legible + sortable.

  • Branch: <type>/<task-slug>-<YYYYMMDD>
    • <type> = dominant work: feat | fix | refactor | perf | security | chore | docs | test | remediation | review.
    • <task-slug> = 2–5 kebab-case words naming task (e.g. dup-correctness-remediation, anon-rpc-hardening).
    • <YYYYMMDD> = date branch started; append -HHMM only to break same-day collision.
  • Worktree dir: .claude/worktrees/<task-slug>-<YYYYMMDD> — mirror branch slug+timestamp (drop <type>/ prefix; dir already isolated). Harness native worktree tool force own prefix (e.g. worktree-) → keep <task-slug>-<YYYYMMDD> core intact so stay descriptive + sortable.
  • Concurrency (mandatory): each concurrent session on same repo get own branch + worktree under this scheme — never share working dir across sessions, and verify git branch --show-current before any commit/push.
  • Cleanup: once merged, delete both branch and worktree (git worktree remove <dir> + git branch -d <branch>). Branch fully reachable from main = redundant — remove it.
  • Native worktree tool mangle branch name. EnterWorktree with chore/my-task-20260729 produce branch worktree-chore+my-task-20260729. Rename immediately: git branch -m <type>/<task-slug>-<YYYYMMDD>, verify with git branch --show-current before first commit.

Read the full file on GitHub · 78 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. 6d ago First seen · 78 lines · 1,264 tokens per session scan A 1fe768eef5fb

Subscribe to this mod's changes

claude-superdev-harness CLAUDE.md is an instructions file published in the GitHub repository will-pagane/claude-superdev-harness (4 stars, last pushed 4d ago), licensed MIT. It adds 1,264 tokens to every session, about $0.0063 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 · 5,182 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

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

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