workflow-work

workflow-work is a skill for Claude Code from nabeelhyatt/coworkpowers. It costs 63 tokens per session (1,051 once invoked), scanned A, original, MIT.

A workflow for carrying out a knowledge-work plan after research, using a task list and suitable working approaches. It covers writing, analysis, decisions, meeting preparation, coaching, and general task execution.

In plain words
What is it for?
Use it to execute research-based plans, draft communications, analyse data, structure decisions, prepare meetings, coach someone, or complete defined tasks.
Why use it?
It turns a prepared plan into tracked work and checks prerequisites before execution. It also helps adapt the approach when a planned step becomes difficult.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the coworkpowers plugin — 4 skills shipped together

Good fit Use it to execute research-based plans, draft communications, analyse data, structure decisions, prepare meetings, coach someone, or complete defined tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nabeelhyatt/coworkpowers/workflow-work
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.

Any agent
npx skills add nabeelhyatt/coworkpowers --skill workflow-work
Clone the repo
git clone --depth 1 https://github.com/nabeelhyatt/coworkpowers

Made for: Claude Code.

Or install coworkpowers, the plugin that ships this one along with the rest of its 4 skills.

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 workflow-work

README.md
[![agentmods](https://agentmods.dev/badge/skills/nabeelhyatt/coworkpowers/workflow-work.svg)](https://agentmods.dev/skills/nabeelhyatt/coworkpowers/workflow-work)
Your own site
<a href="https://agentmods.dev/skills/nabeelhyatt/coworkpowers/workflow-work"><img src="https://agentmods.dev/badge/skills/nabeelhyatt/coworkpowers/workflow-work.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,051 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00063 $0.01051
Opus 5 $0.00032 $0.00526
Sonnet 5 $0.00013 $0.00210
Haiku 4.5 $0.00006 $0.00105

Measured 8d ago against content hash 435b66cf834e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

workflow-work 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 8d 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.

skills/workflow-work/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Work: Knowledge Work Execution Workflow

You are orchestrating the Work phase of the Compound Knowledge Work loop. Your job is to execute the plan systematically, producing high-quality output while staying adaptable.

The work itself should be straightforward if planning was thorough. If you find yourself struggling, the plan may need revisiting.

Process

Phase 1: Quick Start

  1. Read the plan completely. If a plan file exists, read it. If the plan was discussed in conversation, review it.
  2. Create a task list from the plan's steps using TaskCreate.
  3. Identify the right agent mindset for each step:
Work Type Primary Agent
Writing communications executive-writer
Data analysis analyst
Structuring decisions decision-architect
Meeting preparation meeting-orchestrator
Coaching conversation coach
Task execution task-executor
  1. Check prerequisites. Does any step need user input before you can proceed?

Phase 2: Execute

Work through each step in order. For each step:

  1. Mark the task as in-progress.
  2. Apply the right agent mindset for the work type.
  3. Use the context from planning. Don't re-research what was already gathered.
  4. Validate as you go:
    • Does this align with the stated goals?
    • Does this account for the stakeholder considerations?
    • Does this respect the constraints identified?
    • Would the user be surprised by anything here?
  5. Flag blockers immediately. If you need user input, ask. Don't guess on important details.
  6. Mark the task as complete when done.

Phase 3: Quality Check

Before presenting output to the user:

  1. Self-review against success criteria from the plan.
  2. Run the review agents specified in the plan (see Review workflow).
  3. Check for completeness - did you address everything in the plan?

Phase 4: Present Output

Present the completed work to the user with:

  1. The deliverable itself (email draft, analysis, decision memo, etc.)
  2. Key decisions you made during execution and why
  3. Anything that deviated from the plan and why
  4. Suggested next steps or review areas
  5. Ask if they want to run the Review workflow for comprehensive quality assurance

Read the full file on GitHub · 136 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. 8d ago First seen · 136 lines · 63 tokens per session scan A 435b66cf834e

Subscribe to this mod's changes

workflow-work is a skill published in the GitHub repository nabeelhyatt/coworkpowers (114 stars, last pushed 6mo ago), licensed MIT. It adds 63 tokens to every session and 1,051 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.