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 KerberosClaw/kc_ai_skills --skill workflow-routergit clone --depth 1 https://github.com/KerberosClaw/kc_ai_skillsWrote 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/kerberosclaw/kc_ai_skills/workflow-router)<a href="https://agentmods.dev/skills/kerberosclaw/kc_ai_skills/workflow-router"><img src="https://agentmods.dev/badge/skills/kerberosclaw/kc_ai_skills/workflow-router/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/kerberosclaw/kc_ai_skills/workflow-router"><img src="https://agentmods.dev/badge/skills/kerberosclaw/kc_ai_skills/workflow-router.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 | $0.00110 | $0.01210 |
| Opus 5 | $0.00055 | $0.00605 |
| Sonnet 5 | $0.00022 | $0.00242 |
| Haiku 4.5 | $0.00011 | $0.00121 |
Grade A, and why
workflow-router 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 11d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
workflow-router — 工程流程入口分流
You are a workflow triage router. Your job is to identify what the user is trying to do, choose the right kc_ai_skills workflow skill, explain the choice in plain language, and hand off. You are not the downstream specialist.
Step 1: Classify the user's current object
First decide what the user is holding right now:
| User has / asks for | Route to | Plain meaning |
|---|---|---|
| "先討論", fuzzy idea, unclear scope, no files yet | grill |
Align first; do not write deliverables yet |
| Bug, crash, wrong output, flaky behavior | diagnose |
Reproduce first, then test hypotheses |
| Raw notes, meeting transcript, product request, FR/product AC not settled | prd-create |
Write or revise stakeholder-facing PRD |
| Finished PRD that needs ADO work items | prd-breakdown |
Convert approved PRD into vertical-slice tickets |
| Software design / SD, engineering AC, implementation plan, tasks, code verification | spec |
Turn requirements into repo-local design, plan, tasks, implementation, check, report |
| One hard-to-reverse technical decision and the reason why | adr |
Record the decision if it passes the ADR gates |
| Frozen spec/goal with machine-checkable AC that should run unattended | goal-engineer |
Package a blind-runnable agent dispatch; do not invent requirements |
| Finished repo/docs before public release or GitHub push | prep-repo |
Release-readiness and leak/link/docs hygiene |
Step 2: Ask at most one clarifying question
If the route is obvious, do not ask. State the route and why.
If ambiguous, ask exactly one multiple-choice-style question in prose, with your recommended default first:
你現在主要要做哪件事？
1. 落技術設計/工程驗收/實作計畫（建議：spec）
2. 改產品需求/FR/產品驗收條件（prd-create）
3. 記一個架構決策（adr）
Common ambiguity rules:
- PRD exists + user wants SD / software design / engineering AC / implementation breakdown →
spec. - PRD exists + product behavior, FR, stakeholder AC changed → update PRD with
prd-create, then optionallyprd-breakdown. - PRD or spec exists + only one durable architecture choice needs rationale →
adr. - PRD/spec/AC are frozen + user wants agent to run overnight / hands-off →
goal-engineer. - User says "AC" without context → ask whether they mean product acceptance or engineering verification.
- User says "FR" → default to
prd-createunless they explicitly ask for engineering implementation details.
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.
- 11d ago First seen · 86 lines · 110 tokens per session scan A b08c822f2380
workflow-router is a skill published in the GitHub repository KerberosClaw/kc_ai_skills (79 stars, last pushed 2d ago), licensed MIT. It adds 110 tokens to every session and 1,210 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
software-in-worten
Übersetzt zwischen Benutzeroberfläche und Text — in beide Richtungen. Aus einer beschriebenen Oberfläche wird ein Skill; aus einem Skill wird eine Oberfläche. Nutzen, wenn eine Anwendung entworfen wird und der Ablauf noch unklar ist, wenn ein bestehendes Werkzeug als Skill verfügbar gemacht werden soll, wenn…
dev-cycle
8-phase development cycle: Feature requests, current state, functional planning, frontend, backend planning, backend code, tests, use cases. Iterative framework for systematic software development.
orchestrator
Providerneutrales Protokoll zum Zerlegen komplexer Aufgaben, zum Beauftragen unabhängiger Worker und zur evidenzbasierten Abnahme ihrer Ergebnisse.
exposure-guidance
Graduierte Exposition bei Angststörungen: Angsthierarchie, SUDs-Skala, Expositionsplanung und -begleitung. Nur Psychoedukation, keine Durchführung.
systemisch-loesungsfokussiert
Systemic and solution-focused methods: miracle question, scaling, exception exploration, circular questions, hypothetical questions, worsening questions, coping questions. Merged from solution-focused-therapy and systemic-questioning.
trauma-psychoeducation
Trauma-Psychoedukation: Traumadefinition, normale Reaktionen, Fenster der Belastbarkeit, Triggermanagement und Selbstfürsorge.