Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/sanmak/specops/claude-mdgit clone --depth 1 https://github.com/sanmak/specopsWhat 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 | $0.01576 | $0.01576 |
| Opus 5 | $0.00788 | $0.00788 |
| Sonnet 5 | $0.00315 | $0.00315 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
specops 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What is SpecOps
SpecOps is a spec-driven development workflow for AI coding assistants. It transforms ideas into structured specifications (requirements, design, tasks) before implementation, following a 4-phase workflow: Understand, Spec, Implement, Complete. It supports five platforms (Claude Code, Cursor, Codex, Copilot, Google Antigravity) from a single source of truth.
Build & Validate Commands
# Run all tests (single command)
bash scripts/run-tests.sh
# Generate all platform outputs (required after changing core/, generator/templates/, or platform.json)
python3 generator/generate.py --all
# Generate for a single platform
python3 generator/generate.py --platform claude
# Validate generated outputs (200+ checks)
python3 generator/validate.py
# Lint shell scripts
shellcheck setup.sh verify.sh scripts/*.sh platforms/*/install.sh hooks/pre-commit hooks/pre-push
# Lint markdown (matches CI scope)
npx markdownlint-cli2 "core/**/*.md" "docs/**/*.md" ".claude/commands/**/*.md" "README.md" "CLAUDE.md" "QUICKSTART.md" "CONTRIBUTING.md" "CHANGELOG.md"
# Verify file integrity
shasum -a 256 -c CHECKSUMS.sha256
# Run individual test files
python3 tests/test_build.py
python3 tests/test_platform_consistency.py
python3 tests/test_schema_validation.py # requires: pip install jsonschema
python3 tests/test_schema_constraints.py
python3 tests/test_spec_schema.py
python3 tests/test_initiative_schema.py
python3 tests/check_schema_sync.py
# Version bumping
bash scripts/bump-version.sh <new-version> --checksums
Three-Tier Architecture
Tier 1 -- Core Modules (core/*.md): Platform-agnostic workflow logic using abstract operations (READ_FILE, WRITE_FILE, RUN_COMMAND, etc. defined in core/tool-abstraction.md). Never use platform-specific tool names here. Key modules include core/workflow.md (4-phase workflow), core/decomposition.md (scope assessment, split detection, initiative model, cross-spec dependencies), core/initiative-orchestration.md (autonomous multi-spec execution), core/dispatcher.md (context-aware mode routing and enforcement gates), core/evaluation.md (adversarial evaluation with scored quality gates), core/dependency-introduction.md (dependency introduction gate), and core/learnings.md (production learnings capture and retrieval).
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 · 97 lines · 1,576 tokens per session scan A ffa1004f119e
specops CLAUDE.md is an instructions file published in the GitHub repository sanmak/specops (49 stars, last pushed 1mo ago), licensed MIT. It adds 1,576 tokens to every session, about $0.0079 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.
Other instructions, from other repositories
memorix CLAUDE.md
Instructions for AVIDS2/memorix, covering memorix - agent instructions for claude code, using memorix memory tools, when to search memory, when to store memory and when to resolve memory.
memorix GEMINI.md
Instructions for AVIDS2/memorix, covering memorix - cross-agent memory rules, session start - bind project, then load context, during session - capture important context, architecture & decisions and bug fixes & problem solving.
Ctxo CLAUDE.md
Instructions for alperhankendi/Ctxo, covering claude.md — ctxo, project overview, quick reference, dev (pnpm workspace) and usage (consumer).
draft CLAUDE.md
Instructions for drafthq/draft, covering claude.md, repository overview, build & test commands, run a single test and etc. — any test in tests/ is independently executable.
Ctxo copilot-instructions.md
Instructions for alperhankendi/Ctxo, covering ctxo mcp tool usage (mandatory), before any code modification, before starting a task, before reviewing a pr or diff and when exploring or searching code.
Overture CLAUDE.md
Instructions for SixHq/Overture, covering claude.md, project overview, monorepo structure, build & development commands and install dependencies (from root).