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 markmhendrickson/ateles --skill socialgit clone --depth 1 https://github.com/markmhendrickson/atelesWrote 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/markmhendrickson/ateles/social)<a href="https://agentmods.dev/skills/markmhendrickson/ateles/social"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/social/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/markmhendrickson/ateles/social"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/social.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00114 | $0.10759 |
| Opus 5.5 | $0.00046 | $0.04304 |
| Sonnet 5.5 | $0.00023 | $0.02152 |
| Haiku 4.5 | $0.00011 | $0.01076 |
Grade A, and why
social 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 — 798 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social
Turn blog posts into platform-optimized share material: punchy drafts the author edits in 60 seconds, not fully automated content. For blog-derived work, use single-post extraction or multi-post weekly schedules. For external X posts (someone else's tweet), recommend Reply vs QT vs skip, produce reply drafts (not only QTs), and when reply-thread context exists, follow recommendations for repliers (tiered, manual follow only).
When to use
- User provides a blog post URL or text and wants social share material
- User provides an X/Twitter status URL and wants quote-tweet drafts, plain reply drafts, or both
- User wants follow recommendations for accounts that replied to a tweet (requires reply list from user paste, export, or other captured context; see below)
- User asks for tweets, threads, LinkedIn posts, or Bluesky posts derived from existing writing
- User wants a distribution schedule for a published post
- User asks to "process" or "extract" share content from a post
- User asks to generate a week of social content from their blog or recent posts
- After the
/publishskill completes for a new blog post (suggest running this skill as a follow-up)
Always include: top pick and timing
Every output from this skill must include a "Top pick and timing" section near the top of the markdown file AND in the conversational response to the user. This section must:
- Include the full verbatim text of the recommended draft(s) right at the top, ready to copy-paste. Do not make the user scroll to find the text. This is the first thing in the output after the header and source metadata.
- Name each recommended draft with its label (e.g., "QT 1", "Reply B") and give concrete timing guidance per the rules below. Include where the link goes.
- Explain in 1-3 sentences why that pick beats the alternatives (after the copy-paste text, not before it).
- Relevance gate: Before recommending a draft as top pick, verify it answers or directly engages with OP's actual question/frame. A draft that pivots to your own concern (even a valid one) instead of staying in OP's problem space is not the top pick for a QT or reply. Save tangential-but-strong drafts for standalone posts or reserves.
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 · 798 lines · 114 tokens per session scan A bbc4d6f0470e
social is a skill published in the GitHub repository markmhendrickson/ateles (5 stars, last pushed yesterday), licensed MIT. It adds 114 tokens to every session and 10,759 once invoked, about $0.0005 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
local-llm-tool
A local LLM execution tool. Requests text generation and chat from models on GPU via Ollama or vLLM. Use when: Use when: on-premise inference, calling Ollama endpoints, or needing summaries and generation with local models.
understand-codebase
Understand an unfamiliar codebase or plan a change safely, using Spine's deterministic knowledge-graph MCP tools. Reach for this before answering structural questions about a repo you don't know, before editing code, or when debugging — it hands you engineering decisions (what a change breaks, what's untested, where a…
continue
Autonomous work — find and execute ready tasks.
tasks
A task-breakdown tool that turns a plan, specification, feature brief, bug report, technical-debt item, or chore into small TASK-NNN work items. Technical debt means postponed cleanup or design work in a codebase.
review-pr
A pull-request review skill for evaluating proposed code changes and posting a quality verdict. A pull request is a request to merge changes into a shared codebase.
prd
A Product Requirements Document (PRD) writer for large software initiatives. A PRD records the problem, goals, requirements, assumptions, and evidence before implementation begins.