What is superRA CLAUDE.md?

A project instruction file for contributors to superRA, a system built from coding-agent skills, hooks, and workflows. It sets rules for reading owning files, making focused changes, and checking that workflow edits behave correctly.

Use it when modifying superRA skills, hooks, adapters, workflows, or internal documentation.

It helps contributors avoid changing agent behaviour without understanding its callers, related guidance, and real execution path.

How FuZhiyu/superRA configures Claude Code

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/FuZhiyu/superRA/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/FuZhiyu/superRA

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/fuzhiyu/superra/claude-md/github.svg)](https://agentmods.dev/instructions/fuzhiyu/superra/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/fuzhiyu/superra/claude-md"><img src="https://agentmods.dev/badge/instructions/fuzhiyu/superra/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/fuzhiyu/superra/claude-md"><img src="https://agentmods.dev/badge/instructions/fuzhiyu/superra/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,336 This file is loaded in full into every session.

When invoked 2,336 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.

Model	Per session	Once invoked
Fable 5.1	$0.02336	$0.02336
Opus 5.5	$0.00934	$0.00934
Sonnet 5.5	$0.00467	$0.00467
Haiku 4.5	$0.00234	$0.00234

Measured 3d ago against content hash ddb18bfa03ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

CLAUDE.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

superRA — Contributor Guidelines

How contributors keep superRA's skills, hooks, harness adapters, and internal docs coherent. README.md owns the user-facing product model; read it first and keep that explanation there.

Contributor Discipline

Treat skill edits as skill creation. Load skill-creator before editing any skills/*/SKILL.md; load the relevant superRA workflow skills before changing workflow behavior.
Change one concern at a time. One design, workflow, or harness concern per commit.
Describe the problem. Commit messages and PR notes say what was broken, duplicated, rigid, or unclear.
Verify behavior, not just prose. For a skill or workflow change, run at least one realistic harness session or script-level check that exercises the changed path.

Developing Locally

Run the task-tree CLI from live source; each entry script carries a PEP 723 dependency block, so edits apply on the next run:

uv run --script skills/task-tree/scripts/cli.py task frontier
uv run --script skills/task-tree/scripts/plan_dashboard.py dashboard
uv run --with pytest --with pyyaml --with fastapi --with jinja2 --with 'uvicorn[standard]' --with watchfiles --with httpx python -m pytest skills/task-tree/scripts

uv-free fallback: python3 skills/task-tree/scripts/cli.py … — the core is stdlib-only.
./superRA/superra wrapper: prefers this checkout's skills/task-tree, then an installed plugin, then a GitHub clone. The resolution chain lives in skills/task-tree/scripts/wrapper_resolver.py.

Releasing

Bump with scripts/bump-version.sh X.Y.Z — it updates every manifest listed in .version-bump.json; --check reports drift.
Move the ## [Unreleased] notes in RELEASE-NOTES.md into ## [X.Y.Z] - YYYY-MM-DD, directly below an empty ## [Unreleased]. Pushing the bump to main creates the vX.Y.Z GitHub release from that section.

Design Principles

superRA gives agents mechanisms they assemble for the current research situation, not a scenario tree for every contingency.

Read the full file on GitHub · 114 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.

3d ago Changed · -11 lines · -218 tokens per session ddb18bfa03ac
29d ago Changed · -92 lines · -3,037 tokens per session 159cfc61e4a4
1mo ago Changed · +32 lines · +930 tokens per session cb6ef1be8761
2mo ago First seen · 185 lines · 4,661 tokens per session scan A 6a50e979ebea

Subscribe to this mod's changes

superRA CLAUDE.md is an instructions file published in the GitHub repository FuZhiyu/superRA (12 stars, last pushed 4d ago), licensed MIT. It adds 2,336 tokens to every session, about $0.0093 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 2026-09-04.

Building agents

superRA CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
superRA CLAUDE.mdFuZhiyu/superRA	Instructions file	12	4d ago	MIT	A	2,336	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

superRA: Instructions file for Claude Code