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/epistates/sparx/hooksnpx skills add Epistates/sparX --skill hooksgit clone --depth 1 https://github.com/Epistates/sparXWhat 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 | $0.00035 | $0.00797 |
| Opus 5 | $0.00017 | $0.00398 |
| Sonnet 5 | $0.00007 | $0.00159 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
hooks 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 3d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Scroll-Stopping Hooks
The first 8-12 words of an X post determine whether anyone reads the rest. Generate multiple high-impact hook options optimized for the Phoenix algorithm's dwell time signal.
Input
The user provides:
- A topic they're posting about
- A rough idea of the post content
- An existing hook they want alternatives for
- A URL — read the content via WebFetch to understand the subject, then generate hooks based on the actual material (see ../../../reference/url-reading.md)
Process
Step 1 — Understand the Content
What is the core message? Who is the audience? What emotion should the hook trigger?
Step 2 — Read Hook Patterns
Read patterns.md for the full hook pattern library.
Step 3 — Generate 7-10 Hooks
Generate hooks across multiple pattern categories:
- Curiosity Gap — Creates an information gap the reader must fill
- Specific Number — Leads with a concrete, impressive metric
- Contrarian — Challenges conventional wisdom
- Pain Point — Names a frustration the audience feels
- Before/After — Shows transformation in minimal words
- Social Proof — Leads with credibility markers
- Question — Poses something the reader can't ignore
For each hook:
- Keep to 8-12 words (the visible preview before truncation)
- Test: Would this stop YOUR scroll?
- Ensure it's honest — don't promise what the post doesn't deliver
Step 4 — Rank and Annotate
Rank all hooks by predicted effectiveness and annotate:
- Best for dwell — which hook will make people read the full post?
- Best for replies — which hook triggers an urge to respond?
- Best for bookmarks — which hook signals "save-worthy" content?
- Safest — which hook has lowest negative signal risk?
- Boldest — which hook has highest ceiling but more risk?
Step 5 — Output
Present all hooks in a scored table, ranked by Phoenix Score. The score represents what a full post would score with that hook (assuming a solid body + CTA):
What ships with it
1 file 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.
- 3d ago First seen · 78 lines · 35 tokens per session scan A b95fa410dfb0
hooks is a skill published in the GitHub repository Epistates/sparX (3 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 797 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
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
opencli-usage
Use at the start of any OpenCLI session — this is the top-level map of what opencli can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?".
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
opencli-browser-sitemap
Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state signatures, and mark stale sitemap entries without trusting them over live…