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 legendtkl/agentic-skill-router --skill skill-006git clone --depth 1 https://github.com/legendtkl/agentic-skill-routerWrote 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/legendtkl/agentic-skill-router/skill-006)<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/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/legendtkl/agentic-skill-router/skill-006"><img src="https://agentmods.dev/badge/skills/legendtkl/agentic-skill-router/skill-006.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00021 | $0.01825 |
| Opus 5.5 | $0.00008 | $0.00730 |
| Sonnet 5.5 | $0.00004 | $0.00365 |
| Haiku 4.5 | $0.00002 | $0.00183 |
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 1mo 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 — 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.
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.
- 1mo ago First seen · 194 lines · 21 tokens per session scan A 8acb9a924991
skill-006 is a skill published in the GitHub repository legendtkl/agentic-skill-router (6 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 1,825 once invoked, about $0.0001 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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…