skill-006

skill-006 is a skill for Claude Code, Codex from legendtkl/agentic-skill-router. It costs 21 tokens per session (1,825 once invoked), scanned A, original, MIT.

A method for breaking personal or work tasks into smaller, manageable steps, with time-management and focus techniques for people with ADHD. ADHD is a condition that can make planning, starting, and sustaining attention on tasks difficult.

In plain words
What is it for?
It is for planning coding tasks, debugging, feature work, projects, events, errands, and other activities in smaller steps.
Why use it?
It addresses the difficulty of turning a large or unclear task into a concrete starting point. It also provides guidance for handling technical tasks, everyday activities, and focused work periods.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/legendtkl/agentic-skill-router/skill-006
Any agent
npx skills add legendtkl/agentic-skill-router --skill skill-006
Clone the repo
git clone --depth 1 https://github.com/legendtkl/agentic-skill-router

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 skill-006

README.md
[![agentmods](https://agentmods.dev/badge/skills/legendtkl/agentic-skill-router/skill-006.svg)](https://agentmods.dev/skills/legendtkl/agentic-skill-router/skill-006)
Your own site
<a href="https://agentmods.dev/skills/legendtkl/agentic-skill-router/skill-006"><img src="https://agentmods.dev/badge/skills/legendtkl/agentic-skill-router/skill-006.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,825 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 $0.00021 $0.01825
Opus 5 $0.00010 $0.00912
Sonnet 5 $0.00004 $0.00365
Haiku 4.5 $0.00002 $0.00183

Measured 6d ago against content hash 8acb9a924991, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

skill-006 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.

experiments/dci-compare/skillrouter-skills/skill-006/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PURPOSE

Break down personal tasks into ADHD-friendly manageable steps using structured time management and focus techniques.

LOADING STRATEGY

Technical Task Breakdown

Load technical task guidance:

  • IF task involves code, debugging, features -> Load @references/adhd-technical-task-breakdowns.md

Real-World Task Breakdown

Load real-world task guidance:

  • IF task involves projects, events, errands -> Load @references/adhd-real-world-task-breakdowns.md

Universal Strategies

ALWAYS load:

  • @references/adhd-task-strategies.md (applies to all task types)

ROUTING LOGIC

Task Type Routing

  • IF request involves code, debugging, features, technical changes -> READ FILE: @references/adhd-technical-task-breakdowns.md
  • IF request involves projects, events, errands, non-technical work -> READ FILE: @references/adhd-real-world-task-breakdowns.md

Universal Strategy Loading

  • ALWAYS READ FILE: @references/adhd-task-strategies.md (Pomodoro, done criteria, focus locks)

EXECUTION PROTOCOL

Phase 1: Clarification

Check task type, context, constraints. IF task type unclear -> Ask "Technical coding task or real-world task?" -> Wait(User_Input). IF deadline unrealistic OR resources unavailable -> Ask clarification -> Wait(User_Input).

Phase 2: Planning

Classify task type -> Load appropriate reference file -> Propose breakdown plan. Constraint: Personal use only - YOUR task execution, NOT team guidance. IF complexity > Low -> Wait(User_Confirm).

Phase 3: Execution

Execute atomic subtasks. Validate result after EACH step. Apply ADHD strategies from reference files. Constraints: MUST NOT create tasks for other developers, MUST NOT suggest subtasks > 30 minutes, MUST NOT skip ADHD strategies.

Phase 4: Validation

Final_Checklist: [Subtask time limits, Done criteria concreteness, ADHD strategies applied]. IF Fail -> Self_Correct. Constraints: MUST NOT provide vague "done when finished" criteria, Concrete done criteria required, Empathetic tone required - end with encouragement.

Read the full file on GitHub · 194 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 · 194 lines · 21 tokens per session scan A 8acb9a924991

Subscribe to this mod's changes

skill-006 is a skill published in the GitHub repository legendtkl/agentic-skill-router (5 stars, last pushed 3mo ago), licensed MIT. It adds 21 tokens to every session and 1,825 once invoked, about $0.0001 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.