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 jnPiyush/AgentX --skill cowork-skill-creatorgit clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/jnpiyush/agentx/cowork-skill-creator)<a href="https://agentmods.dev/skills/jnpiyush/agentx/cowork-skill-creator"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/cowork-skill-creator/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/jnpiyush/agentx/cowork-skill-creator"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/cowork-skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 123 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00053 | $0.01569 |
| Opus 5.5 | $0.00021 | $0.00628 |
| Sonnet 5.5 | $0.00011 | $0.00314 |
| Haiku 4.5 | $0.00005 | $0.00157 |
Grade A, and why
cowork-skill-creator 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cowork Skill Creator
WHEN: Creating, scaffolding, reviewing, or packaging a Microsoft 365 Copilot Cowork, co-work, or coworker skill for upload as a
.zipor.skillarchive.
When to Use
Use this skill when the user asks to:
- Turn a repeatable workflow into a Cowork skill
- Create or improve a Cowork
SKILL.md - Produce an upload-ready Cowork skill archive
- Package companion templates, test cases, or validation scripts with a skill
Do not use it for a one-time response that has no repeatable process or stable output contract.
Prerequisites
- A workflow with a clear purpose, trigger, inputs, process, output, boundaries, and quality checks
- PowerShell 7 or later for deterministic package validation and zip creation
- Realistic, non-sensitive test inputs
Rationalization Table
| Rationalization | Reality |
|---|---|
| "SKILL.md alone is enough." | The requested deliverable includes companion folders; populate each with material that supports the workflow. |
| "Empty folders show the intended structure." | Empty folders disappear from zip archives and provide no reusable value. |
| "The user can zip it later." | A creation request is complete only when the upload-ready archive is produced. |
| "Generic placeholder files can be refined later." | Companion files must reflect the requested workflow and contain no TODO markers. |
| "Missing details can be inferred." | Flag missing inputs and preserve uncertainty instead of inventing facts. |
| "The skill can send or publish automatically." | Consequential actions require an explicit human-review checkpoint. |
Decision Tree
Cowork skill requested?
+- One-time task with no stable method? -> Respond normally; do not create a skill.
+- Repeatable workflow?
| +- Missing purpose, trigger, or output? -> Ask only for the missing essentials.
| +- Complete enough to author? -> Create the package directory.
| | +- Deterministic helper is useful? -> Add a tailored script.
| | +- Reusable output structure exists? -> Add a tailored asset.
| | - Tests or domain detail help? -> Add a tailored reference.
| - Validate and package -> Return the zip path.
- Existing package supplied? -> Review, repair, validate, and repackage it.
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 Changed c424337aa043
- 1mo ago First seen · 144 lines · 53 tokens per session scan A 0116444d4111
cowork-skill-creator is a skill published in the GitHub repository jnPiyush/AgentX (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,569 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…