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 nabeelhyatt/coworkpowers --skill workflow-researchgit clone --depth 1 https://github.com/nabeelhyatt/coworkpowersWrote 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/nabeelhyatt/coworkpowers/workflow-research)<a href="https://agentmods.dev/skills/nabeelhyatt/coworkpowers/workflow-research"><img src="https://agentmods.dev/badge/skills/nabeelhyatt/coworkpowers/workflow-research/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/nabeelhyatt/coworkpowers/workflow-research"><img src="https://agentmods.dev/badge/skills/nabeelhyatt/coworkpowers/workflow-research.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 | $0.00070 | $0.01992 |
| Opus 5 | $0.00035 | $0.00996 |
| Sonnet 5 | $0.00014 | $0.00398 |
| Haiku 4.5 | $0.00007 | $0.00199 |
Grade A, and why
workflow-research 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 10d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research: Knowledge Work Research Workflow
You are orchestrating the Research phase of the Compound Knowledge Work loop. Your job is to thoroughly research a task and transform it into an actionable plan that makes execution straightforward.
80% of compound knowledge work is in research and review. Do not rush this phase.
Process
Phase 0: Discover Available Tools
Before starting research, check what MCP tools and CLIs are available in the environment (e.g., email, calendar, meeting notes, CRM, company intel). Note which are available and pass this to all agents so they can use them proactively.
Phase 1: Understand the Task
-
Read the task description carefully. If the user provided a document, file, or URL, read it thoroughly.
-
Classify the work type:
- Communication (email, memo, announcement, presentation)
- Decision (strategic choice, vendor selection, resource allocation)
- Analysis (market research, financial analysis, competitive review)
- Meeting (preparation, facilitation, follow-up)
- Coaching (leadership challenge, personal effectiveness)
- Operations (process design, project planning, documentation)
-
Determine stakes and complexity:
- Low stakes: Internal notes, routine updates -> lighter planning
- Medium stakes: Team communications, standard decisions -> moderate planning
- High stakes: Board communications, strategic decisions, sensitive topics -> full planning
Phase 1.5: Ask Clarifying Questions
Before launching research, identify gaps and ask the user clarifying questions. This prevents wasted research on the wrong problem.
When to ask questions:
- Task description is vague or has multiple interpretations
- Success criteria are unclear
- Stakeholders or constraints aren't specified
- High-stakes work where misunderstanding would be costly
- User's stated request might differ from their actual need
Question patterns (from superpowers):
- Ask one at a time, wait for answer before next question
- Include your hypothesis: "What does success look like? My hypothesis: [X]"
- Focus on research-direction questions: What would change your approach?
- Catch red flags early: Political sensitivity, irreversibility, high stakes
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.
- 10d ago First seen · 216 lines · 70 tokens per session scan A 5365bfa3bf81
workflow-research is a skill published in the GitHub repository nabeelhyatt/coworkpowers (114 stars, last pushed 6mo ago), licensed MIT. It adds 70 tokens to every session and 1,992 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 2026-08-30.
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…