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.
npx skills add OutlineDriven/odin-claude-plugin --skill planning-and-task-breakdowngit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/planning-and-task-breakdown)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/planning-and-task-breakdown"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/planning-and-task-breakdown/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.
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/planning-and-task-breakdown"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/planning-and-task-breakdown.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00062 | $0.00925 |
| Opus 5 | $0.00031 | $0.00463 |
| Sonnet 5 | $0.00012 | $0.00185 |
| Haiku 4.5 | $0.00006 | $0.00093 |
Grade A, and why
planning-and-task-breakdown 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.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning and task breakdown
Contract
| Field | Bound contract |
|---|---|
| Trigger | User asks to break down a high-level goal into actionable, dependency-ordered tasks before implementation. |
| Authority | Read-only regarding the filesystem; the plan is returned in chat, not written to files. No file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | Plan or task list returned in chat; no repo mutation. |
| Done | Every task carries a checkable acceptance criterion and dependency order, the plan fits its complexity budget, and the user explicitly approves or requests revision. |
Inputs
Required: the user's description of the goal or feature to be planned. Optional: any existing tasks/plan.md or tasks/todo.md content, the project's spec or requirements, and the codebase's conventions and structure.
Procedure
- Parse the goal and extract constraints. Read the user's goal, any existing spec or requirements, and the relevant codebase sections. Identify existing patterns and conventions. If scope is unclear, ask clarifying questions before proceeding. Do not write or modify any file. Done when: the goal is parsed, constraints are extracted, and scope is clear enough to derive acceptance criteria.
- Identify the dependency graph and slice work vertically. Determine what each component depends on. Group work into end-to-end feature paths rather than horizontal layers; each vertical slice delivers one complete, testable feature. Implementation proceeds bottom-up from the deepest dependency. Done when: the dependency graph is determined and work is grouped into vertical, testable feature slices.
- Formulate tasks with acceptance criteria, dependency labels, and a size bound. Write each task with a short descriptive title, one-paragraph description, one to four specific testable acceptance criteria, named dependencies on other task numbers (or "none"), and an explicit scope estimate: XS (1 file), S (1-2 files), M (3-5 files), L (5-8 files; must be subdivided if it spans more than one focused session). If a task touches two or more independent subsystems or its title contains "and", split it. Done when: every task has title, description, acceptance criteria, dependencies, and scope estimate.
- Order tasks bottom-up, inserting checkpoints. Order so dependencies are satisfied before their dependents, each task leaves the system in a working state, and a checkpoint appears after every two to three tasks. Flag high-risk tasks for early execution. Done when: tasks are ordered with dependencies satisfied, working-state checkpoints, and high-risk flags.
- Present the breakdown in chat and require explicit user approval or revision before exiting. Include: an ordered task list with acceptance criteria and scope, dependency order, checkpoints, identified risks, and open questions. Keep the task list in the report rather than writing files. Before presenting, if an unchecked
tasks/plan.mdortasks/todo.mdexists, stop and describe the conflict to the user; do not overwrite, delete, or bulk-close existing items without explicit confirmation. Done when: the user explicitly approves the plan or requests revision, and the report is presented with all required parts.
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.
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.
- 6d ago First seen · 40 lines · 62 tokens per session scan A 41aeeadda726
planning-and-task-breakdown is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), licensed Apache-2.0. It adds 62 tokens to every session and 925 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 2026-09-04.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…