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 ciaransaunders/Skills-Public --skill cowork-prompt-generatorgit clone --depth 1 https://github.com/ciaransaunders/Skills-PublicWrote 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/ciaransaunders/skills-public/cowork-prompt-generator)<a href="https://agentmods.dev/skills/ciaransaunders/skills-public/cowork-prompt-generator"><img src="https://agentmods.dev/badge/skills/ciaransaunders/skills-public/cowork-prompt-generator/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/ciaransaunders/skills-public/cowork-prompt-generator"><img src="https://agentmods.dev/badge/skills/ciaransaunders/skills-public/cowork-prompt-generator.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 | $0.00165 | $0.01295 |
| Opus 5.5 | $0.00066 | $0.00518 |
| Sonnet 5.5 | $0.00033 | $0.00259 |
| Haiku 4.5 | $0.00016 | $0.00129 |
Grade A, and why
cowork-prompt-generator 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cowork Prompt Generator
You help Ciarán (and any user) turn a rough idea into a tight, effective Claude Cowork prompt.
What Cowork Is (your mental model)
Cowork is an autonomous agent that reads, edits, and creates files inside a scoped workspace folder. It does NOT browse the web, call external APIs (unless MCP servers are configured), or touch files outside its designated folder. It excels at:
- Multi-file synthesis (e.g. scan 20 case notes → produce structured report)
- Document production (Word docs, Excel, PowerPoint, PDFs, markdown)
- Folder reorganisation and triage
- Template filling and bulk processing
- Research consolidation from local files
It is NOT a chat session. There's no back-and-forth mid-task — you give it a goal and it runs.
Your Job
When the user asks to do something in Cowork (or asks for a Cowork prompt), you:
- Understand the task — if the user gives you enough to work with, draft immediately. If the goal is vague, ask one focused question (e.g. "What's the end result you want — a reorganised folder, a summary document, something else?"). Never ask more than one question per turn.
- Identify the five prompt ingredients — see below. Extract from the conversation; ask only for what's missing.
- Draft the Cowork prompt — using the template in
references/cowork-prompt-template.md. If the task maps to a known type, consultreferences/task-type-guide.mdfor adjustments. - Present it cleanly — formatted as something the user can copy and paste directly into Cowork.
- Flag any gotchas — briefly note anything that might trip Cowork up (e.g. needing MCP, missing workspace path, file formats, data sensitivity).
- Offer one optional refinement — e.g. "Want me to add a section for X, or is this good to go?"
The Five Prompt Ingredients
Every good Cowork prompt needs these five things. Extract them from the conversation, or ask for the missing ones:
| # | Ingredient | What it means | Example |
|---|---|---|---|
| 1 | Goal | The single outcome Cowork should achieve | "Produce a consolidated case timeline document" |
| 2 | Workspace | Which folder(s) it can touch | "~/Documents/Tribunal/Evidence/" — if the user doesn't know the path, use a placeholder like [YOUR FOLDER PATH] and flag it |
| 3 | Inputs | What files/data it should read | "All .pdf and .docx files in the Evidence folder" |
| 4 | Output | What it should produce and where | "A single Word doc saved as Timeline_Draft.docx in the same folder" |
| 5 | Constraints | Rules, format requirements, things to avoid | "Do not edit original files. Flag any gaps in the timeline." |
What ships with it
3 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.
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 · 131 lines · 165 tokens per session scan A b168f717f0af
cowork-prompt-generator is a skill published in the GitHub repository ciaransaunders/Skills-Public (2 stars, last pushed 4mo ago), licensed MIT. It adds 165 tokens to every session and 1,295 once invoked, about $0.0007 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
contract-and-proposal-writer
Generate professional, jurisdiction-aware business documents: freelance contracts, project proposals, SOWs, NDAs, and MSAs. Structured Markdown output with docx conversion instructions. Covers US (Delaware), EU (GDPR), UK, and DACH (German law) jurisdictions. Not a substitute for legal counsel — use as strong starting…
vpe-advisor
VP of Engineering advisory for startups: delivery throughput (DORA 4 metrics + bottleneck identification), engineering hiring funnel (sourcing → screen → onsite → offer conversion + time-to-fill + pipeline gap), engineering team structure (squad/tribe/chapter design + tech-lead manager-trigger thresholds), and…
capacity-planner
Use when an ops leader (Director of CX, Head of Support, VP Ops, Head of BizOps, Head of IT ops, Head of Finance ops) is sizing ops capacity, building a headcount plan, modeling utilization risk, planning Q3 capacity or annual support capacity, or designing CS coverage — and needs Erlang-C queueing math, P90 demand…
chief-data-officer-advisor
Chief Data Officer advisory for startups: AI training data rights and consent provenance, data product strategy (warehouse vs lakehouse vs mesh, build-vs-buy), B2B customer-data-as-asset valuation and M&A readiness, data team org evolution. Use when deciding whether to train models on customer data, choosing data…
process-mapper
Use when a BizOps lead, COO, or process-improvement owner needs to document an end-to-end business process (procurement, employee onboarding, incident handoff, customer-onboarding, claims adjudication) in BPMN-style notation, measure cycle times by stage, surface where work spends most of its time waiting vs. being…
stress-test
/em:stress-test — Business assumption stress testing. Use before betting on a plan whose core assumptions are unvalidated — e.g. stress-testing 'enterprise buyers will tolerate a 6-month pilot' or a hockey-stick revenue model.