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/habib0x0/spec-driven-plugin/claude-mdgit clone --depth 1 https://github.com/Habib0x0/spec-driven-pluginWrote 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/habib0x0/spec-driven-plugin/claude-md)<a href="https://agentmods.dev/instructions/habib0x0/spec-driven-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/habib0x0/spec-driven-plugin/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 | $0.02414 | $0.02414 |
| Opus 5 | $0.01207 | $0.01207 |
| Sonnet 5 | $0.00483 | $0.00483 |
| Haiku 4.5 | $0.00241 | $0.00241 |
Grade A, and why
spec-driven-plugin 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 4d 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 — 213 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.
Overview
This is a Claude Code plugin that provides spec-driven development workflows. It guides feature development through three phases: Requirements (EARS notation), Design (architecture), and Tasks (trackable implementation items).
Plugin Structure
.claude-plugin/plugin.json - Plugin manifest (name, version, metadata)
commands/ - Slash command definitions
scripts/ - Standalone execution scripts (spec-exec, spec-loop)
skills/spec-workflow/ - Main skill with reference docs
agents/ - Subagent definitions
templates/ - Document scaffolding for specs
Commands
| Command | Purpose |
|---|---|
/spec-brainstorm |
Brainstorm a feature idea before spec creation |
/spec <name> |
Start new spec with 3-phase workflow |
/spec-refine |
Update existing requirements/design |
/spec-tasks |
Regenerate tasks from spec |
/spec-status |
Show progress and task completion |
/spec-validate |
Validate completeness and consistency |
/spec-exec |
Run one autonomous implementation iteration |
/spec-loop |
Loop implementation until all tasks complete |
/spec-accept |
Run user acceptance testing for formal sign-off |
/spec-docs |
Generate documentation from spec and implementation |
/spec-release |
Generate release notes, changelog, and deployment checklist |
/spec-verify |
Run post-deployment smoke tests against a live environment |
/spec-retro |
Run a retrospective to capture lessons learned |
/research |
Deep research before planning — parallel agents search docs, web, and codebase |
/zoom-out |
Step up a layer of abstraction and map modules, interfaces, and callers |
/ubiquitous-language |
Extract domain terms into a canonical glossary with flagged ambiguities |
Model Routing
The plugin routes each agent to a capability tier rather than a specific model. Three tiers cover the range of work:
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.
- 4d ago First seen · 213 lines · 2,414 tokens per session scan A 2cf372cd78ea
spec-driven-plugin CLAUDE.md is an instructions file published in the GitHub repository Habib0x0/spec-driven-plugin (10 stars, last pushed 3mo ago), licensed MIT. It adds 2,414 tokens to every session, about $0.0121 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
architecture-cowork-plugin AGENTS.md
AGENTS.md instructions for navraj007in/architecture-cowork-plugin, covering archon plugin — global rules, request routing — when to use commands vs. handle directly, output file splitting, read strategy for large outputs and reading sdl — single-file and multi-file format.
wyx CLAUDE.md
Instructions for jlifyio/wyx, covering claude.md, project overview, architecture, skills and hooks.
capstone GEMINI.md
Instructions for GentBajko/capstone: @./skills/core/references/dispatcher.md.
archlint CLAUDE.md
Claude Code instructions for MKanhan/archlint, covering archlint-public and venture.
Coding-Agent-Guidelines-Radiotherapy AGENTS.md
Instructions for MustafaKadhim/Coding-Agent-Guidelines-Radiotherapy, covering codex coding instructions, 1. operating principles, think before coding, simplicity first and surgical changes.
Orient CLAUDE.md
Claude Code instructions for Chaitanya299/Orient, covering project docs — read on demand, never import, workflow and build rules for this repo.