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 Epistates/sparX --skill composegit clone --depth 1 https://github.com/Epistates/sparXWrote 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/epistates/sparx/compose)<a href="https://agentmods.dev/skills/epistates/sparx/compose"><img src="https://agentmods.dev/badge/skills/epistates/sparx/compose/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/epistates/sparx/compose"><img src="https://agentmods.dev/badge/skills/epistates/sparx/compose.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 | $0.00037 | $0.01445 |
| Opus 5.5 | $0.00015 | $0.00578 |
| Sonnet 5.5 | $0.00007 | $0.00289 |
| Haiku 4.5 | $0.00004 | $0.00145 |
Grade A, and why
compose 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compose an Algorithm-Optimized X Post
You are an expert X content strategist with deep knowledge of the Phoenix algorithm. Draft a post that maximizes predicted engagement signals.
Input
The user provides either:
- A topic or idea to write about
- A rough draft to transform into an optimized post
- A product/feature announcement to frame for maximum reach
- A URL — GitHub release page, blog post, product page, README, changelog, or any web page to compose a post about
Process
Step 0 — Resolve URL Input (if applicable)
If the input contains a URL, read its content first using WebFetch. See url-reading.md for tool selection and extraction prompts.
Common URL scenarios:
- GitHub release page → Extract version, features, benchmarks → compose an announcement post
- Blog post → Extract key insight + data → compose a post highlighting the most shareable finding
- Product/landing page → Extract value prop + metrics → compose a launch post
- GitHub README → Extract what the project does + proof points → compose an introduction post
- Changelog → Extract user-facing improvements → compose a "what's new" post
After reading the URL content, proceed to Step 1 using the extracted material as your source.
Step 1 — Understand the Goal
Identify:
- What is the core message?
- Who is the target audience?
- What format fits best? (announcement, insight, question, hot take, build-in-public)
Step 2 — Read Algorithm Context
Read these files for current optimization data:
- scoring.md — for weight hierarchy
- content-formats.md — for format-specific guidance
- penalties.md — for what to avoid
Step 3 — Draft the Post
Apply these rules in order of priority:
Hook (first 8-12 words)
- Must create curiosity, tension, or promise specific value
- No jargon in the hook unless the audience expects it
- See templates.md for proven hook patterns
What ships with it
2 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 · 143 lines · 37 tokens per session scan A 029e9158ecbf
compose is a skill published in the GitHub repository Epistates/sparX (3 stars, last pushed 6mo ago), licensed MIT. It adds 37 tokens to every session and 1,445 once invoked, about $0.0001 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
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
stuck
Diagnoses a broken course setup by reading the folder, so the student never has to describe the problem in English. Takes no argument. Reports which class they are on and which files are filled, then names one blocker and one fix: Claude Code opened at the wrong level, .claude/skills/ missing, skills not loading…
wrap-up
Saves today's work session as a four-line entry (did, decided, open, next) at the top of the project's log.md, after the student confirms it, so a fresh chat can continue tomorrow with /pick-up. Writes to projects/ /log.md or career-vault/log.md, one entry per project touched, never to new-client. Use when the student…
pick-up
Reads the newest entry of a project's log.md and tells the student where they left off: what they did and decided, what is open, and the next step. Takes an optional project name. With several projects and no name, shows a menu of each project's last entry. Read only. Use when the student says pick up, where did I…
grill-me
One move you can run on anything: point grill-me at a target and it makes you defend your thinking from first principles until the true matter is clear. Point it at your working contract and it rewrites the weak lines in place. Point it at a brief and it produces a Requirements Handshake. Point it at research, an…