spec-work

spec-work is a skill for Claude Code from blue03183/spec-tools-mcp. It costs 96 tokens per session (10,861 once invoked), scanned A, original, no licence file.

A workflow skill for completing todo items through written plans and progress records. It follows a sequence of writing a plan, getting approval, implementing the work, recording an update, and reporting completion.

In plain words
What is it for?
Use it to process items in todo.md, create plan.md, request approval, implement approved work, and record results in update.md.
Why use it?
It gives multi-step development work a defined review point and a written progress trail. TDD is not mentioned, so this is a planning workflow rather than a testing method.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the spec-tools-mcp plugin — 3 skills, 1 MCP server shipped together

Good fit Use it to process items in todo.md, create plan.md, request approval, implement approved work, and record results in update.md.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/blue03183/spec-tools-mcp/spec-work
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.

Any agent
npx skills add blue03183/spec-tools-mcp --skill spec-work
Clone the repo
git clone --depth 1 https://github.com/blue03183/spec-tools-mcp

Made for: Claude Code.

Or install spec-tools-mcp, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

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 spec-work

README.md
[![agentmods](https://agentmods.dev/badge/skills/blue03183/spec-tools-mcp/spec-work.svg)](https://agentmods.dev/skills/blue03183/spec-tools-mcp/spec-work)
Your own site
<a href="https://agentmods.dev/skills/blue03183/spec-tools-mcp/spec-work"><img src="https://agentmods.dev/badge/skills/blue03183/spec-tools-mcp/spec-work.svg" alt="Measured on agentmods" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,861 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 unknown 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 $0.00096 $0.10861
Opus 5 $0.00048 $0.05431
Sonnet 5 $0.00019 $0.02172
Haiku 4.5 $0.00010 $0.01086

Measured 4d ago against content hash ecdd87408c32, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

spec-work 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.

skills/spec-work/SKILL.md · 512 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 4d ago Changed · +198 lines · +29 tokens per session ecdd87408c32
  2. 7d ago First seen · 314 lines · 67 tokens per session scan A f651d7a17df2

Subscribe to this mod's changes

spec-work is a skill published in the GitHub repository blue03183/spec-tools-mcp (1 stars, last pushed 4d ago), with no licence file. It adds 96 tokens to every session and 10,861 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

prompt-optimization

Improves LLM-facing context while preserving intent, execution boundaries, and proportional work. Use when creating or reviewing prompts, agent definitions, skill definitions, or other instructions for an LLM.

shinpr/rashomon · 42 tokens

recipe-eval-prompt

Compares original and optimized prompts through repeated blind paired execution in git worktrees. Use when evaluating prompt improvement effects or learning prompt engineering through concrete examples.

shinpr/rashomon · 36 tokens

knowledge-base

Retrieves and updates project-specific prompt knowledge from comparison evidence and user feedback. Use only for prompt analysis or post-comparison learning within a Rashomon evaluation.

shinpr/rashomon · 34 tokens

skill-crafting

Create, fix, and validate skills for AI agents. Use when user says 'create a skill', 'build a skill', 'fix my skill', 'skill not working', 'analyze my skill', 'validate skill', 'audit my skills', 'check character budget', 'create a skill from this session', 'turn this into a skill', 'make this reusable', 'can this…

arvindand/agent-skills · 122 tokens

worktree-execution

Creates, pins, and cleans isolated Git worktree pairs for comparison trials. Use only when a Rashomon prompt or skill evaluation needs paired execution environments or orphan recovery.

shinpr/rashomon · 38 tokens

interview-me

Deep-dive spec interviewer. Reads a file, GitHub issue, or requirement, analyzes it against the codebase, then conducts a rigorous 1-on-1 interview using AskUserQuestion to produce a comprehensive, opinionated specification document. Acts as a collaborative architect with active pushback. Also runs --verify to detect…

Sorbh/interview-me · 79 tokens