speckit CLAUDE.md

speckit CLAUDE.md is an instructions file for coding agents from jmanhype/speckit. It costs 4,289 tokens per session, scanned B, original, MIT.

Instructions for a specification-driven development workflow in Claude Code. They cover turning an idea into a specification, plan, task list, implementation, and review.

In plain words
What is it for?
Use them to define features, clarify open questions, create technical plans, generate tasks, implement changes, and validate the resulting documents.
Why use it?
They give an agent a clear process for resolving unclear requirements and keeping planning and implementation connected.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/jmanhype/speckit/claude-md
Clone the repo
git clone --depth 1 https://github.com/jmanhype/speckit

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.

agentmods badge for speckit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jmanhype/speckit/claude-md.svg)](https://agentmods.dev/instructions/jmanhype/speckit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jmanhype/speckit/claude-md"><img src="https://agentmods.dev/badge/instructions/jmanhype/speckit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,289 This file is loaded in full into every session.
When invoked 4,289 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.04289 $0.04289
Opus 5 $0.02145 $0.02145
Sonnet 5 $0.00858 $0.00858
Haiku 4.5 $0.00429 $0.00429

Measured 3d ago against content hash afef2aa84785, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

speckit CLAUDE.md scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cp /path/to/speckit/.claude/settings.json ./.claude/
CLAUDE.md · 514 lines

How it starts

The opening of the file, as written. The whole thing — 514 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This repository contains the Spec Kit Workflow System - a specification-driven development framework for Claude Code.

Repository Structure

This repository provides a framework that can be integrated into any software project. It is NOT a standalone application, but rather a set of tools, templates, and workflows.

Directory Layout

.
├── .claude/
│   ├── settings.json          # Claude Code hooks (Beads integration)
│   ├── README.md              # Configuration documentation
│   ├── commands/              # Slash command definitions for Claude Code
│   │   ├── speckit.specify.md    # Create feature specifications
│   │   ├── speckit.clarify.md    # Resolve ambiguities
│   │   ├── speckit.plan.md       # Create technical plans
│   │   ├── speckit.tasks.md      # Generate task lists
│   │   ├── speckit.implement.md  # Execute implementation
│   │   ├── speckit.analyze.md    # Cross-artifact validation
│   │   ├── speckit.checklist.md  # Quality checklists
│   │   ├── speckit.constitution.md   # Project principles
│   │   ├── speckit.fix.md        # Quick fixes (bypasses full workflow)
│   │   ├── speckit.taskstoissues.md  # Convert tasks to GitHub issues
│   │   ├── speckit-workflow-v2.md    # Full workflow orchestration
│   │   └── speckit-orchestrate.md    # Quick workflow
│   ├── agents/                # Specialized sub-agent definitions
│   │   ├── openapi-spec-author.md    # API design and contract validation
│   │   ├── backend-api-engineer.md   # Backend TDD implementation
│   │   ├── frontend-react-engineer.md # Frontend React/TypeScript
│   │   ├── integration-tester.md     # E2E and integration testing
│   │   ├── spec-validator.md         # Spec quality validation
│   │   ├── consistency-checker.md    # Cross-artifact consistency
│   │   └── beads-sync.md             # Beads synchronization
│   └── skills/                # On-demand context skills
│       ├── spec-kit-workflow/    # Workflow phase guidance
│       ├── beads-integration/    # Persistent memory patterns
│       ├── spec-validation/      # Spec quality validation
│       └── project-standards/    # Constitution principles (on-demand)
├── .specify/
│   ├── memory/
│   │   └── constitution.md    # Template for project architectural principles
│   ├── scripts/bash/          # Automation scripts
│   │   ├── common.sh              # Shared utilities
│   │   ├── check-prerequisites.sh # Validate workflow state
│   │   ├── create-new-feature.sh  # Initialize feature branches
│   │   ├── create-beads-epic.sh   # Create Pivotal-style Beads epics
│   │   ├── create-beads-issues.sh # Bulk import tasks with dependencies
│   │   ├── setup-plan.sh          # Initialize planning artifacts
│   │   └── update-agent-context.sh # Update context files
│   └── templates/             # Document templates
│       ├── spec-template.md       # Feature specification structure
│       ├── plan-template.md       # Technical plan structure
│       ├── tasks-template.md      # Task list format
│       ├── checklist-template.md  # Quality checklist format
│       └── agent-file-template.md # Agent context file
├── README.md                  # Framework documentation
└── LICENSE                    # MIT License

Read the full file on GitHub · 514 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.

  1. 3d ago First seen · 514 lines · 4,289 tokens per session scan B afef2aa84785

Subscribe to this mod's changes

speckit CLAUDE.md is an instructions file published in the GitHub repository jmanhype/speckit (26 stars, last pushed 5mo ago), licensed MIT. It adds 4,289 tokens to every session, about $0.0214 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.