Borrowing it
Nothing to install: this file belongs to RaNDoM6913/claude-code-superkit. 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/RaNDoM6913/claude-code-superkit/main/CLAUDE.mdgit clone --depth 1 https://github.com/RaNDoM6913/claude-code-superkitWrote 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/random6913/claude-code-superkit/claude-md)<a href="https://agentmods.dev/instructions/random6913/claude-code-superkit/claude-md"><img src="https://agentmods.dev/badge/instructions/random6913/claude-code-superkit/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.
<a href="https://agentmods.dev/instructions/random6913/claude-code-superkit/claude-md"><img src="https://agentmods.dev/badge/instructions/random6913/claude-code-superkit/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.04843 | $0.04843 |
| Opus 5.5 | $0.01937 | $0.01937 |
| Sonnet 5.5 | $0.00969 | $0.00969 |
| Haiku 4.5 | $0.00484 | $0.00484 |
Grade A, and why
claude-code-superkit 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 14d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-code-superkit
Production-tested agents (56), commands (16), hooks (42), skills (22), and rules (19) for Claude Code; 82 skills and 2 native hook handlers for Codex. Claude prompts hardened by Claude Fable 5; GPT role sources authored by Astra.
Contributor Working Agreement
For work on Superkit itself, read docs/WORKING_AGREEMENT.md once per session. It defines the owner-approved scope, parallel implementation, risk-based review, verification, and token-economy rules. Preserve mandatory project checks and current task authorization boundaries.
GPT backend/data/delivery/language reviews use project-specific schema, query, toolchain, Go lifecycle/performance/telemetry and rollout evidence; Core UI, six frontend-ui aliases and frontend-3d reviewers retain distinct scopes; UI source, rendered and interaction evidence remain distinct; Optional GAN sources live separately in packages/gan/skills and are not ordinary installer entries. Bot and nudge source acceptance does not authorize messaging or scheduling; source acceptance does not qualify live behavior. For current Codex-only delivery scope and remaining installation/compatibility work, use the active delivery plan.
Project Structure
Codex architecture/output support distinguishes unconfigured references from observed project facts and measures completeness within the authorized change. Source review does not claim empirically measured model quality.
Codex authoring guides preserve role-specific verdicts and scoped review/workflow authority, require evidence-backed findings and truthful verification coverage, and use conditional project examples. Native workflow/support sources resolve installed tools and dependencies, preserve migration/commit authority and retain unavailable evidence. The native hook mapping rejects recognized static destructive Git and checks tracked/staged whitespace at Stop in filter-free repositories; configured clean/process filters, including unused/global Git LFS, skip both diffs with UNVERIFIED after a keys-only config check. It grants no permission/trust and does not prove tests/builds or native firing. Hook assets use pristine updates/backups; existing active hooks/config stay preserved. Review definition and script updates separately through the documented trust flow. POSIX wiring is not qualified for Windows/cloud.
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.
- 14d ago Changed · +16 lines · +659 tokens per session 0ad39a78b72c
- 2mo ago First seen · 244 lines · 4,184 tokens per session scan A 80b1edc21e87
claude-code-superkit CLAUDE.md is an instructions file published in the GitHub repository RaNDoM6913/claude-code-superkit (3 stars, last pushed 14d ago), licensed MIT. It adds 4,843 tokens to every session, about $0.0194 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.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.