Borrowing it
Nothing to install: this file belongs to fokkerone/superspecs. 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/fokkerone/superspecs/main/CLAUDE.mdgit clone --depth 1 https://github.com/fokkerone/superspecsWrote 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/fokkerone/superspecs/claude-md)<a href="https://agentmods.dev/instructions/fokkerone/superspecs/claude-md"><img src="https://agentmods.dev/badge/instructions/fokkerone/superspecs/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 | $0.00462 | $0.00462 |
| Opus 5 | $0.00231 | $0.00231 |
| Sonnet 5 | $0.00092 | $0.00092 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
superspecs 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 7d 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.
What it actually says
SuperSpecs — Claude Code
You have SuperSpecs installed. Four phases, always in order.
The Lifecycle
PLAN → EXECUTE → VERIFY → SHIP
Phase 1: Plan
/discuss— Capture decisions, goals, non-goals, constraints BEFORE any spec is written/spec— Write the spec (SHALL requirements + GIVEN/WHEN/THEN scenarios) — requires DISCUSS.md/grill— Stress-test the spec. Mandatory gate. READY verdict required before execution. — requires spec.md
Exit gate: Spec grilled to READY. Too big = decompose and re-grill.
Phase 2: Execute
/pick-spec— Confirm spec is complete and context-window-fit/branch— Create git branch or worktree (one per spec)/subagent— Dispatch fresh subagent per task; two-stage review per task/tdd— RED → GREEN → REFACTOR. Write failing test. Watch it fail. Write minimal code. Watch it pass. Commit. Delete any code written before tests./code-review— Runs between tasks. Critical issues BLOCK progress.
Phase 3: Verify
/verify— Full suite + scenario coverage (Stage 1), then distill to knowledge base (Stage 2). Gate: tests must pass before wiki import runs.
Phase 4: Ship
/ship— PR + changelog + archive + start next cycle.
Hard Rules
- Never write implementation code before a failing test exists
- Never proceed past a Critical code review finding
- Never skip
/discuss— decisions captured late are decisions lost - Never skip
/grill— a spec that hasn't been grilled to READY blocks/pick-spec - Never declare done without
/verifypassing - Every shipped feature gets a wiki page
Paths
superspec/specs/— Specs and discussion docssuperspec/phases/— Active execution working dirssuperspec/wiki/— Living knowledge base.skills/— Skill definitions
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.
- 7d ago First seen · 46 lines · 462 tokens per session scan A f87d9d6851e4
superspecs CLAUDE.md is an instructions file published in the GitHub repository fokkerone/superspecs (4 stars, last pushed 2mo ago), licensed MIT. It adds 462 tokens to every session, about $0.0023 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.
Other instructions, from other repositories
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).
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.
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 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).
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.