task-planning

task-planning is a skill for Claude Code, Codex from davidYichengWei/Agency. It costs 44 tokens per session (599 once invoked), scanned A, original, MIT.

A planning tool that turns an approved software design document into a step-by-step task list. Each task includes dependencies, relevant code context, and checks for completion.

In plain words
What is it for?
Use it to create tasks.md from spec.md, identify affected files and callers, check task dependencies, and ensure every part of the design has an implementation task.
Why use it?
It prevents important design decisions or code relationships from being missed when work is divided among implementers. It also keeps replacement work safe by requiring new code before old code is removed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

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.

agentmods
npx agentmods add skills/davidyichengwei/agency/task-planning
Any agent
npx skills add davidYichengWei/Agency --skill task-planning
Clone the repo
git clone --depth 1 https://github.com/davidYichengWei/Agency

Made for: Claude Code, Codex.

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 task-planning

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidyichengwei/agency/task-planning.svg)](https://agentmods.dev/skills/davidyichengwei/agency/task-planning)
Your own site
<a href="https://agentmods.dev/skills/davidyichengwei/agency/task-planning"><img src="https://agentmods.dev/badge/skills/davidyichengwei/agency/task-planning.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 599 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 $0.00044 $0.00599
Opus 5 $0.00022 $0.00300
Sonnet 5 $0.00009 $0.00120
Haiku 4.5 $0.00004 $0.00060

Measured 6d ago against content hash 31878edc2a56, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

task-planning 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.

shared/skills/task-planning/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Planning

Prerequisite

spec.md must be complete (sections 1-7 filled or marked N/A) and approved at Gate: Solution Design. If not, invoke system-design first.

Core Principle

Each task is a work unit for the implementer subagent. Since the implementer starts with a fresh context, the task must include everything it needs: what to change, what files to read for context (upstream callers + downstream consumers), and how to verify it's done.

Workflow

  1. Read spec.md fully — identify all design decisions and deliverables
  2. Use researcher subagent to investigate: which files/functions need to change, who calls them, who consumes their output
  3. Break into tasks using the template in assets/tasks-template.md, write to .agent/<task-name>/tasks.md
  4. Verify: dependency DAG has no cycles, every spec section maps to at least one task

Key Principles

Build → Migrate → Delete: When replacing existing code, always create the new implementation first, then migrate callers, then remove the old code. Never delete before the replacement is ready — every intermediate state must compile.

Each task must compile: After completing any single task, the codebase must compile. Use stubs for not-yet-implemented functions if needed.

Context is critical: Each task's context field lists the files and functions the implementer needs to read to understand the task. Include not just the files being modified, but upstream callers (who passes data in) and downstream consumers (who uses the output). Be specific — function-level, not just file-level.

Flag parallelism: After building the dependency DAG, derive parallel groups — sets of tasks with no dependency between them that can be dispatched to separate implementer subagents simultaneously. List these explicitly in the "并行组" section of tasks.md. The coordinator uses this to maximize parallelism during execution.

Spec coverage: Every design section in the spec must map to at least one task. The coverage mapping table at the bottom catches gaps.

Read the full file on GitHub · 44 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 44 lines · 0 tokens per session scan A 31878edc2a56

Subscribe to this mod's changes

task-planning is a skill published in the GitHub repository davidYichengWei/Agency (5 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 599 once invoked, about $0.0002 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

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