rockie-claude: Instructions file for Claude Code

CLAUDE.md

rockie-claude CLAUDE.md is an instructions file for Claude Code from Rockielab/rockie-claude. It costs 853 tokens per session, scanned A, original, Apache-2.0.

Development instructions for a local overlay that customizes the official Claude command-line program inside per-tenant Fly machines.

In plain words
What is it for?
Use them to orient yourself before changing the overlay, its harnesses, Claude instructions, skills, or synchronization with the canonical platform repository.
Why use it?
They clarify which files are only a local copy and where the real source lives, helping developers avoid editing the wrong repository.

Instructions file for Claude Code

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

This is Rockielab/rockie-claude's own configuration. It tells Claude Code how to work on rockie-claude 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 rockie-claude configures →

Reuse

Borrowing it

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

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 rockie-claude CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rockielab/rockie-claude/claude-md"><img src="https://agentmods.dev/badge/instructions/rockielab/rockie-claude/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 853 This file is loaded in full into every session.
When invoked 853 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 $0.00853 $0.00853
Opus 5 $0.00426 $0.00426
Sonnet 5 $0.00171 $0.00171
Haiku 4.5 $0.00085 $0.00085

Measured 11d ago against content hash 8006915c09d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

rockie-claude 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 11d 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 · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

How to work in rockie-claude

Local overlay for the official claude binary. Customizes the runtime in a per-tenant Fly machine when MODE=subscription and BINARY=claude.

For what this repo does for you as a researcher, see README.md. For cross-repo orientation (the four-harness model + alignment agent), see ../docs/architecture.md in the workspace meta-repo.

First reads (after the workspace docs/ reads)

  1. README.md — researcher-facing overview of the four jobs (taste corpus, adversarial subagents, autopilot, [LEARN] codification).
  2. project-harness/ — repo-installed harness layer.
  3. user-harness/ — user-global harness layer.
  4. claude-md/ — CLAUDE.md templates that get rendered into tenant projects.

⚠️ This repo is a LOCAL OVERLAY, not the canonical source

Skills, hooks, memory schema, scripts → canonical source is ../platform-skills/.

The runtime image's assemble-skills.sh pulls from platform-skills/ (NOT from this repo) and writes to ~/.claude/skills/ inside the per-tenant machine. This repo is a local copy used for development reference.

The Phase 6 alignment agent propagates changes from platform-skills/ into this repo's mirror copies. Don't edit skills here directly — edit them in platform-skills/ and let the alignment agent push.

The exceptions are intentional divergences (in .claude/skills/align-overlays/intentional-divergences.yaml in the meta-repo): claude-side conventions like claude-md/ templates and slash-command invocation style (vs codex's agents-md/ and natural-language invocation).

Process for changes here

  1. Is this a skill/hook/memory change? Edit platform-skills/ instead. Don't fork here.
  2. Is this a claude-md template change? Edit claude-md/ here. The alignment agent will mirror to rockie-codex/agents-md/ with translation (CLAUDE.md ↔ AGENTS.md, slash commands ↔ NL invocation).
  3. Is this a structural change to project-harness/ or user-harness/? Likely affects rockie-codex too — flag in the PR description so the alignment agent or Sam can port.
  4. Tests: pnpm test runs the smoke + lint suite (.github/workflows/smoke.yml).
  5. Commit: Sam Larson author, no AI trailers, Conventional Commits.

Read the full file on GitHub · 49 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. 11d ago First seen · 49 lines · 853 tokens per session scan A 8006915c09d7

Subscribe to this mod's changes

rockie-claude CLAUDE.md is an instructions file published in the GitHub repository Rockielab/rockie-claude (21 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 853 tokens to every session, about $0.0043 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.

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