Borrowing it
Nothing to install: this file belongs to FuZhiyu/superRA. 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/FuZhiyu/superRA/main/CLAUDE.mdgit clone --depth 1 https://github.com/FuZhiyu/superRAWrote 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/fuzhiyu/superra/claude-md)<a href="https://agentmods.dev/instructions/fuzhiyu/superra/claude-md"><img src="https://agentmods.dev/badge/instructions/fuzhiyu/superra/claude-md.svg" alt="Measured on agentmods" 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 | $0.04661 | $0.04661 |
| Opus 5 | $0.02330 | $0.02330 |
| Sonnet 5 | $0.00932 | $0.00932 |
| Haiku 4.5 | $0.00466 | $0.00466 |
Grade A, and why
superRA 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 3d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
superRA — Contributor Guidelines
This file is the contributor-facing entry point for superRA internals. Read README.md first for the user-facing product model; keep that overview there rather than duplicating it here.
When modifying superRA itself — skills, hooks, harness adapters, or internal docs — treat the work as skill creation. Load skill-creator before editing any skills/*/SKILL.md, and load the relevant superRA workflow skills before changing workflow behavior.
Contributor Discipline
- Read the owning files before editing. Skill and agent text changes behavior. Understand the owning skill, its references, and the call sites that load it before rewriting.
- Change one concern at a time. Keep commits focused on one design, workflow, or harness concern.
- Describe the problem. Commit messages and PR notes should explain what was broken, duplicated, rigid, or unclear.
- Verify behavior, not just prose. For skill or workflow changes, run at least one realistic harness session or script-level verification that exercises the changed path.
- Preserve user-facing/internal separation.
README.mdexplains what superRA is and why a researcher would use it. This file explains how contributors keep the internals coherent.
Local Task-Tree CLI Development
When developing this checkout, run the task-tree CLI from the live source via uv run --script on the loose entry scripts (there is no installable package; each entry script carries a PEP 723 dependency block):
uv run --script skills/task-tree/scripts/cli.py task frontier
uv run --script skills/task-tree/scripts/plan_dashboard.py dashboard
uv run --script is script-scoped: it never provisions this repo's environment and reflects source edits on the next run with no cache-bust. The core is stdlib-only (lazy pyyaml), so python3 skills/task-tree/scripts/cli.py … works as a uv-free fallback. The optional repo-local wrapper ./superRA/superra follows the same rule by resolving the task-tree source — preferring this checkout's skills/task-tree, then an installed Claude/Codex plugin, then a shallow GitHub clone — and running the resolved entry script via uv run --script (python3 fallback); the resolution chain and run-line are single-sourced in skills/task-tree/scripts/wrapper_resolver.py. To run the test suite, supply its deps with --with, e.g. uv run --with pytest --with pyyaml --with fastapi --with jinja2 --with 'uvicorn[standard]' --with watchfiles --with httpx python -m pytest skills/task-tree/scripts.
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.
- 3d ago First seen · 185 lines · 4,661 tokens per session scan A 6a50e979ebea
superRA CLAUDE.md is an instructions file published in the GitHub repository FuZhiyu/superRA (8 stars, last pushed 9d ago), licensed MIT. It adds 4,661 tokens to every session, about $0.0233 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 2026-09-04.
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.
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.