cowork

cowork is a skill for Claude Code, Codex from alessiomarcone/agent-fieldbook. It costs 69 tokens per session (465 once invoked), scanned A, original, MIT.

A workflow guide for Cowork, a work-automation tool that can use folders, connected services, reusable instructions, schedules, and approval steps. It helps turn an operational goal into a reviewable process.

In plain words
What is it for?
Use it to design recurring briefs and multi-source workflows for legal, sales, marketing, finance, or other operations, with human approval before consequential actions.
Why use it?
It reduces the risk of automating work without clear sources, boundaries, freshness rules, or human checks. It also helps choose between Cowork, regular chat, shared projects, and Claude Code.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions Claude Code; mentions Codex.

Part of the knowledge-pack plugin — 10 skills shipped together

Good fit Use it to design recurring briefs and multi-source workflows for legal, sales, marketing, finance, or other operations, with human approval before consequential actions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alessiomarcone/agent-fieldbook/cowork
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 alessiomarcone/agent-fieldbook --skill cowork
Clone the repo
git clone --depth 1 https://github.com/alessiomarcone/agent-fieldbook

Made for: Claude Code, Codex.

Or install knowledge-pack, the plugin that ships this one along with the rest of its 10 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 cowork

README.md
[![agentmods](https://agentmods.dev/badge/skills/alessiomarcone/agent-fieldbook/cowork/github.svg)](https://agentmods.dev/skills/alessiomarcone/agent-fieldbook/cowork)
Your own site
<a href="https://agentmods.dev/skills/alessiomarcone/agent-fieldbook/cowork"><img src="https://agentmods.dev/badge/skills/alessiomarcone/agent-fieldbook/cowork/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.

agentmods 80×15 button for cowork

Your own site · 80×15
<a href="https://agentmods.dev/skills/alessiomarcone/agent-fieldbook/cowork"><img src="https://agentmods.dev/badge/skills/alessiomarcone/agent-fieldbook/cowork.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 465 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 $0.00069 $0.00465
Opus 5 $0.00034 $0.00233
Sonnet 5 $0.00014 $0.00093
Haiku 4.5 $0.00007 $0.00047

Measured 11d ago against content hash cb5f82789cc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

cowork 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.

plugins/knowledge-pack/skills/cowork/SKILL.md · 44 lines

What it actually says

Cowork

Turn an operational objective into a Cowork workflow that stays reviewable and under human control.

References

  • Always read references/knowledge-base.md for product selection.
  • Read references/sources.md before making a time-sensitive product claim.
  • Read references/cowork.md and references/desktop-app.md for delegated desktop workflows.
  • Read references/claude-code-estensioni.md for Claude Code extensions.
  • Read references/plugin-building.md only for customization or distribution.

Procedure

  1. Resolve the outcome, source context, cadence, collaborators, risk, and required external systems.
  2. Confirm Cowork is the right surface: use normal Chat/Projects for conversation and shared knowledge, and Claude Code for repository engineering.
  3. Define the one-time setup: working folder, connected sources, stable instructions, and any reusable skill.
  4. Write the brief with expected output, freshness window, missing-data behavior, boundaries, and success checks.
  5. Add approval gates before messages, publishing, sensitive edits, purchases, or irreversible actions.
  6. Require source-linked verification and a human first-run review for consequential workflows.
  7. Verify current plans, UI paths, connectors, scheduling, and availability before stating them as current.

Output contract

Return:

  1. Fit — why Cowork is the right surface.
  2. Setup — folders, permissions, connectors, and reusable guidance.
  3. Ready brief — the exact on-demand or scheduled request.
  4. Approval and verification — required human gates and checks.
  5. Reuse — what should become persistent instructions, a skill, or a plugin.

Boundaries

  • Do not assume unconnected data is accessible.
  • Do not send, publish, approve, or schedule external work without authority.
  • Do not transfer Codex configuration into Claude products.
  • Answer in the user's language.
Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 44 lines · 69 tokens per session scan A cb5f82789cc2

Subscribe to this mod's changes

cowork is a skill published in the GitHub repository alessiomarcone/agent-fieldbook (5 stars, last pushed 3d ago), licensed MIT. It adds 69 tokens to every session and 465 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 2026-08-31.

Related

Other skills, from other repositories

flashcard-generator

Generate educational flashcards from topics, documents, notes, or study materials. Produces structured JSON data and can create polished Tailwind CSS HTML flashcard review pages with interactive card flipping, progress, tags, and difficulty labels.

mingchen666/Reviva · 49 tokens

manim-animation-maker

Create educational explainer videos with a Manim plus FFmpeg workflow. Use when the user asks for Manim animation, math/physics/geometry/algorithm visualization, formula derivation, concept explainer video, scene planning, MP4 rendering, preview frames, or video quality checks.

mingchen666/Reviva · 62 tokens

knowledge-organize

A tool for turning books, lecture notes, slides, and other documents into organised knowledge summaries. It can produce outlines, key points, knowledge maps, checklists, and mind maps.

mingchen666/Reviva · 135 tokens

bili-note

A tool for turning already registered and parsed Bilibili videos or Bilibili posts into Markdown learning notes linked to supporting evidence. Bilibili is a Chinese video and content-sharing platform.

mingchen666/Reviva · 122 tokens

worksheet-skill

A resource for creating classroom worksheets and other printable learning materials.

mingchen666/Reviva · 113 tokens

image-to-code

Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…

frankxai/claude-skills-library · 116 tokens