spec-to-todo

spec-to-todo is a skill for Claude Code from WolframResearch/AgentTools. It costs 122 tokens per session (1,111 once invoked), scanned A, original, MIT.

A workflow for turning a design specification into a Markdown task list with checkboxes. It reads the specification and checks the codebase to distinguish completed, partial, and missing work.

In plain words
What is it for?
Use it to create a TODO file in the TODO directory covering required source changes, tooling, generated files, documentation, tests, and directories.
Why use it?
It turns a broad feature description into concrete work units and exposes differences between the specification and the current code.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Not installable on its own: it reads a path above its own folder, which only exists inside its repository. The line is Tasks for implementing the [<Feature> specification](../Specs/<SpecName>.md)..

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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 spec-to-todo

README.md
[![agentmods](https://agentmods.dev/badge/skills/wolframresearch/agenttools/spec-to-todo.svg)](https://agentmods.dev/skills/wolframresearch/agenttools/spec-to-todo)
Your own site
<a href="https://agentmods.dev/skills/wolframresearch/agenttools/spec-to-todo"><img src="https://agentmods.dev/badge/skills/wolframresearch/agenttools/spec-to-todo.svg" alt="Measured on agentmods" height="20"></a>
Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,111 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 5.1 $0.00122 $0.01111
Opus 5 $0.00061 $0.00556
Sonnet 5 $0.00024 $0.00222
Haiku 4.5 $0.00012 $0.00111

Measured 6d ago against content hash 77c748c1d28f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

spec-to-todo 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 6d 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/spec-to-todo/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate TODO from Specification

Read a design specification and produce a TODO task list that captures everything needed to fully implement it, organized into logical work units.

Spec to process: $ARGUMENTS

If no specific spec is given, ask the user which spec in Specs/ they'd like to turn into a task list.

Process

1. Read the Spec

Read the full spec file from Specs/. Identify every deliverable it describes:

  • Source files to create or modify
  • Build scripts or tooling
  • Generated artifacts (scripts, config files, packages)
  • Hand-authored content (documentation, reference files, skill definitions)
  • Tests and evals
  • Directory structures that must exist

2. Explore Current State

Launch parallel Explore agents to understand what already exists. Focus on:

  • What's implemented: Files that exist and have real content matching the spec.
  • What's partial: Files that exist but are stubs/placeholders (e.g., contain only "TODO").
  • What's missing: Files or directories the spec requires that don't exist at all.
  • Discrepancies: Differences between the spec and reality (e.g., a manifest missing an entry, wrong directory structure, mismatched names).

Key areas to check:

  • The directories and files the spec references directly
  • Scripts/ for any build scripts mentioned
  • Kernel/ for source code the spec depends on (tool definitions, parameters, etc.)
  • Tests/ for any existing test coverage
  • Notes/ for implementation hints or reference code
  • docs/ for related developer documentation

3. Gap Analysis

Compare spec requirements against exploration results. For each deliverable, classify it:

  • Done: Fully implemented, matches spec. Don't create a task for it.
  • Partial: Exists but incomplete. Create a task describing what remains.
  • Missing: Doesn't exist. Create a task for the full implementation.
  • Discrepancy: Exists but doesn't match spec. Create a task to fix it.

4. Organize into Tasks

Group related work into logical units, where each task represents roughly one coding session. Guidelines:

Read the full file on GitHub · 113 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. 6d ago First seen · 113 lines · 122 tokens per session scan A 77c748c1d28f

Subscribe to this mod's changes

spec-to-todo is a skill published in the GitHub repository WolframResearch/AgentTools (85 stars, last pushed yesterday), licensed MIT. It adds 122 tokens to every session and 1,111 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens