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.
curl -O https://raw.githubusercontent.com/akapet00/dotclaude/main/.claude/skills/to-tasks/SKILL.mdgit clone --depth 1 https://github.com/akapet00/dotclaudeWrote 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/skills/akapet00/dotclaude/to-tasks)<a href="https://agentmods.dev/skills/akapet00/dotclaude/to-tasks"><img src="https://agentmods.dev/badge/skills/akapet00/dotclaude/to-tasks.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 5.1 | $0.00056 | $0.01803 |
| Opus 5 | $0.00028 | $0.00901 |
| Sonnet 5 | $0.00011 | $0.00361 |
| Haiku 4.5 | $0.00006 | $0.00180 |
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 7d 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 — 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
- Locate inputs:
PLAN.md(required),RESEARCH.md(optional). - Study them end to end.
- Ask only the critical clarifying questions if real ambiguity remains.
- Discover project commands and conventions. Ask only if undiscoverable.
- Write
TASKS.mdto 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:
CLAUDE.mdorAGENTS.mdin the project root — authoritative if present.- Project config files:
pyproject.toml—[tool.ruff],[tool.pytest],[project.scripts]package.json— thescriptssectionMakefile— targets likelint,test,check,runCargo.toml,go.mod, or other language-specific configs.github/workflows/*.yml— CI steps often reveal canonical commandsREADME.md— frequently documents run/test/lint
- Ask me if commands cannot be determined from the above. If I answer verbally and no
AGENTS.mdexists, suggest I add one for future sessions.
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.
- 7d ago First seen · 211 lines · 56 tokens per session scan A d71f67f2e25f
to-tasks is a skill published in the GitHub repository akapet00/dotclaude (2 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 1,803 once invoked, about $0.0003 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…