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 agentmods add skills/cocorof/geny/blog_writenpx skills add CocoRoF/Geny --skill blog_writegit clone --depth 1 https://github.com/CocoRoF/GenyWrote 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/cocorof/geny/blog_write)<a href="https://agentmods.dev/skills/cocorof/geny/blog_write"><img src="https://agentmods.dev/badge/skills/cocorof/geny/blog_write.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.00896 |
| Opus 5 | $0.00015 | $0.00448 |
| Sonnet 5 | $0.00006 | $0.00179 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
blog-write 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 4d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blog Write — Delegate writing to the blog AI
You handle the user's blog writing / editing / management requests. Do not write the post yourself. Delegate to the external blog AI Agent, which has its own permissions on the blog (image upload / post creation / editing), and you do only these 4 things:
- Briefly confirm the user's intent once (only when needed — if it's obvious, delegate right away).
- Start the task with
blog_agent_delegate(task=..., task_summary=...). - When the user asks about progress, check with
blog_agent_status(task_id)and paraphrase it in 1–2 sentences — don't expose the JSON / task_id as-is. - When the user wants to cancel, call
blog_agent_cancel(task_id)once.
A. Delegating a new post
- The user says "write a post about X".
- If it's ambiguous, confirm once ("the tech category, right?"). If it's clear, skip this.
- Call:
blog_agent_delegate( task="<the delegation instruction to give the blog AI — including the category / tags / style guidance>", task_summary="<a one-liner to tell the user, 5 words or fewer. e.g. 'LangGraph workflow post draft'>" ) - To the user: just something like "I've handed it off. Hang tight."
- At this point your turn ends. The work proceeds in the background.
- When it's done, it arrives in the inbox automatically — in a new turn you'll see an
[EXTERNAL_TASK_RESULT]message. At that point, tell the user the result in 1–3 sentences. If there's a slug / URL, show it clearly.
B. Responding to progress questions
When the user asks something like "how far along is it?", "how much is left?", "is it going okay?":
- Call
blog_agent_status(task_id). (If you don't know the task_id, call it with no arguments → the list of all in-progress tasks for the current session.) - Look at the result's
progress_hint+elapsed_s+last_event_age_s+tool_activityand answer in natural language.- If
last_event_age_s > 30: "It seems to have paused for a moment. Let me check again." - If
status == "done": an inbox message will arrive soon, so "almost there, one sec." - If
status == "error": a one-line summary of the error + a suggestion to retry.
- If
- Don't expose the JSON / task_id to the user as-is. The user isn't interested in internal identifiers.
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.
- 4d ago First seen · 69 lines · 31 tokens per session scan A 89b0a0cc3d3e
blog-write is a skill published in the GitHub repository CocoRoF/Geny (10 stars, last pushed 5d ago), licensed Apache-2.0. It adds 31 tokens to every session and 896 once invoked, about $0.0002 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.
Other skills, from other repositories
agent_management
This Skill provides a complete management guide for OpenSquad Agents, covering the full workflow of creation, configuration, deployment, and troubleshooting.
Collaboration Management
Complete guide to multi-agent collaboration card management, including starting collaborations, joining teams, and creating custom collaboration cards.
collaboration-workflow
Complete guide to the OpenSquad multi-agent collaboration system with user authorization gates. Use this skill when starting a collaboration session, coordinating multiple agents, managing the collaboration board, or when you need to understand how to use boardupdate, boardlist, and other collaboration tools. Triggers…
mcp_auto_deploy
Allows the agent to self-configure and deploy MCP servers. Covers central config, per-agent sync, web UI visibility, registration diagnostics, and validation.
external-im-integration
Connect OpenSquad agents to external IM platforms (Feishu/Lark, QQ, Telegram). Covers plugin service setup, adapter processes, Gateway auth, workspace path fixes, and troubleshooting. Uses Feishu as the reference example.
opensquad_intro
When you need to understand how to use OpenSquad, its architectural design, or its features, load this skill to get a system overview and documentation navigation guide.