agentmods.dev

dotclaude: Skill for Claude Code

.claude/skills/to-tasks/SKILL.md

to-tasks is a skill for Claude Code from akapet00/dotclaude. It costs 56 tokens per session (1,803 once invoked), scanned A, original, MIT.

A planning tool that turns PLAN.md, and optionally RESEARCH.md, into TASKS.md, a step-by-step task list for an autonomous coding loop.

In plain words
What is it for?
Use it after creating a project plan to produce an implementation checklist, while checking the available project commands and existing task files first.
Why use it?
It separates planning from implementation so the coding agent receives clear, manageable tasks instead of a broad project description. It only runs when explicitly requested with /to-tasks or to-tasks.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is akapet00/dotclaude's own configuration. It tells Claude Code how to work on dotclaude 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 dotclaude configures →

not rated 2repo 4mo ago A scan 56 tokens original MIT
View source ↗ akapet00/dotclaude
Reuse

Borrowing it

Nothing to install: this file belongs to akapet00/dotclaude. 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/akapet00/dotclaude/main/.claude/skills/to-tasks/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/akapet00/dotclaude

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 to-tasks

README.md
[![agentmods](https://agentmods.dev/badge/skills/akapet00/dotclaude/to-tasks/github.svg)](https://agentmods.dev/skills/akapet00/dotclaude/to-tasks)
Your own site
<a href="https://agentmods.dev/skills/akapet00/dotclaude/to-tasks"><img src="https://agentmods.dev/badge/skills/akapet00/dotclaude/to-tasks/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 to-tasks

Your own site · 80×15
<a href="https://agentmods.dev/skills/akapet00/dotclaude/to-tasks"><img src="https://agentmods.dev/badge/skills/akapet00/dotclaude/to-tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,803 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 $0.00056 $0.01803
Opus 5.5 $0.00022 $0.00721
Sonnet 5.5 $0.00011 $0.00361
Haiku 4.5 $0.00006 $0.00180

Measured 2mo ago against content hash d71f67f2e25f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

to-tasks 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 2mo 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/to-tasks/SKILL.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TO-TASKS

Turn PLAN.md (and optional RESEARCH.md) into a TASKS.md the autonomous loop can execute one task at a time.

Do not implement anything in this phase. Do not write PRD-style narrative — this is a task list. Stay agent-agnostic: refer to "the coding agent" or "the autonomous loop", never a specific assistant.

High-level overview

  1. Locate inputs: PLAN.md (required), RESEARCH.md (optional).
  2. Study them end to end.
  3. Ask only the critical clarifying questions if real ambiguity remains.
  4. Discover project commands and conventions. Ask only if undiscoverable.
  5. Write TASKS.md to the project root unless I specify otherwise. Include only sections with real content.

Step 1 — Locate inputs

Look for PLAN.md and RESEARCH.md in the project root or the location I specified.

If PLAN.md is missing, stop and ask me to create it. If TASKS.md already exists, see Existing TASKS.md below — never overwrite silently.

Step 2 — Minimal clarification

Read both inputs end to end. Ask questions only if one of these is genuinely unclear:

  • Objective — what problem this solves
  • Work type — feature, refactor, research, migration, etc.
  • Constraints — time, compute, scope
  • Verification — how "done" is checked

One round of questions, max. If everything is clear, skip questions and proceed.

Step 3 — Discover commands and conventions

Determine lint, type-check, test, and run commands plus the tech stack. Use this priority order:

  1. CLAUDE.md or AGENTS.md in the project root — authoritative if present.
  2. Project config files:
    • pyproject.toml — [tool.ruff], [tool.pytest], [project.scripts]
    • package.json — the scripts section
    • Makefile — targets like lint, test, check, run
    • Cargo.toml, go.mod, or other language-specific configs
    • .github/workflows/*.yml — CI steps often reveal canonical commands
    • README.md — frequently documents run/test/lint
  3. Ask me if commands cannot be determined from the above. If I answer verbally and no AGENTS.md exists, suggest I add one for future sessions.

Read the full file on GitHub · 211 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. 2mo ago First seen · 211 lines · 56 tokens per session scan A d71f67f2e25f

Subscribe to this mod's changes

to-tasks is a skill published in the GitHub repository akapet00/dotclaude (2 stars, last pushed 4mo ago), licensed MIT. It adds 56 tokens to every session and 1,803 once invoked, about $0.0002 per session on Opus 5.5. 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.

Planning
Related

to-tasks compared with skills from other repositories

to-tasks next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
to-tasksakapet00/dotclaudeSkill24mo agoMITA56Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code