SpecPilot: Skill for Claude Code

.claude/skills/specpilot-project/SKILL.md

specpilot-project is a skill for Claude Code from girishr/SpecPilot. It costs 28 tokens per session (677 once invoked), scanned A, original, MIT.

Project context for SpecPilot, a command-line tool built around Specification-Driven Development, where written requirements and design documents guide implementation. Its project information is stored in a .specs folder.

In plain words
What is it for?
Understanding the project before making changes, checking specifications and tasks, following the documented architecture, and recording development decisions.
Why use it?
It tells an agent where to find the project's requirements, architecture, plans, quality rules, and development history.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is girishr/SpecPilot's own configuration. It tells Claude Code how to work on SpecPilot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything SpecPilot configures →

Reuse

Borrowing it

Nothing to install: this file belongs to girishr/SpecPilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/girishr/SpecPilot/main/.claude/skills/specpilot-project/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/girishr/SpecPilot

Made for: Claude Code.

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 specpilot-project

README.md
[![agentmods](https://agentmods.dev/badge/skills/girishr/specpilot/specpilot-project/github.svg)](https://agentmods.dev/skills/girishr/specpilot/specpilot-project)
Your own site
<a href="https://agentmods.dev/skills/girishr/specpilot/specpilot-project"><img src="https://agentmods.dev/badge/skills/girishr/specpilot/specpilot-project/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.

agentmods 80×15 button for specpilot-project

Your own site · 80×15
<a href="https://agentmods.dev/skills/girishr/specpilot/specpilot-project"><img src="https://agentmods.dev/badge/skills/girishr/specpilot/specpilot-project.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 677 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00028 $0.00677
Opus 5 $0.00014 $0.00338
Sonnet 5 $0.00006 $0.00135
Haiku 4.5 $0.00003 $0.00068

Measured 9d ago against content hash 74d2d1e8948d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

specpilot-project 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 9d 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.

.claude/skills/specpilot-project/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SpecPilot Project Context

This Skill provides context about the SpecPilot SDD CLI project structure, specifications, and development practices.

Quick Start

The project uses Specification-Driven Development (SDD). All context lives in the .specs/ folder:

  • .specs/project/ - Project metadata and requirements
  • .specs/architecture/ - System design and API specifications
  • .specs/planning/ - Tasks, roadmap, and project management
  • .specs/quality/ - Testing strategies and quality guidelines
  • .specs/development/ - AI prompts, context, and development logs

Key Files to Reference

  1. .specs/project/project.yaml - Project configuration, rules, and tech stack
  2. .specs/project/requirements.md - Functional and non-functional requirements
  3. .specs/architecture/architecture.md - System architecture and design decisions
  4. .specs/planning/tasks.md - Current tasks, sprints, and priorities
  5. .specs/development/prompts.md - AI interaction history and onboarding guide

Project Rules

  • Update .specs/ files when making changes
  • Maintain .specs/ as single source of truth
  • Never modify .specs/ folder structure or file names
  • Document decisions in context.md
  • Update prompts.md with AI interactions
  • Follow stable ID conventions (REQ-###, TASK-###, ARCH-###)

Architecture Overview

  • Project: SpecPilot SDD CLI
  • Language: TypeScript
  • Framework: Node.js / Commander.js
  • Key modules: specFileGenerator, ideConfigGenerator, agentConfigGenerator, specBackfiller, specArchiver, specValidator

Development Process

  1. Review requirements in .specs/project/requirements.md
  2. Check tasks in .specs/planning/tasks.md
  3. Reference architecture in .specs/architecture/architecture.md
  4. Update specs after major changes
  5. Document decisions and context

AI Onboarding

For full AI onboarding instructions, see .specs/development/prompts.md.

Code Philosophy — Write Only What Needed

  1. Need exist? No → skip. Say why.
  2. Already in codebase? → reuse. Not rewrite.
  3. Stdlib do it? → use it.
  4. Native or installed dep cover it? → use. No new deps.
  5. One line do it? → write that.
  6. Only then: minimum code that work.
  7. Never cut: validation, error handling, security, explicit requirement.

Read the full file on GitHub · 75 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. 9d ago First seen · 75 lines · 28 tokens per session scan A 74d2d1e8948d

Subscribe to this mod's changes

specpilot-project is a skill published in the GitHub repository girishr/SpecPilot (37 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 677 once invoked, about $0.0001 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.