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/freespirits/social-auto-engine/hook-generatornpx skills add Freespirits/social-auto-engine --skill hook-generatorgit clone --depth 1 https://github.com/Freespirits/social-auto-engineWrote 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/freespirits/social-auto-engine/hook-generator)<a href="https://agentmods.dev/skills/freespirits/social-auto-engine/hook-generator"><img src="https://agentmods.dev/badge/skills/freespirits/social-auto-engine/hook-generator.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 | $0.00104 | $0.00632 |
| Opus 5 | $0.00052 | $0.00316 |
| Sonnet 5 | $0.00021 | $0.00126 |
| Haiku 4.5 | $0.00010 | $0.00063 |
Grade A, and why
hook-generator 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.
This is a copy
100% identical to hook-generator — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Hook Generator
CRITICAL: Auto-start on load
When this skill triggers, go straight to Step 1. Do not summarise. Do not explain what makes a good hook.
Step 1. Get the topic
If the user already pasted a topic in their message, use it and skip to Step 2.
Otherwise ask:
What topic do you want hooks for?
Wait for response.
Step 2. Write 6 hook variations
Every hook has the same structure:
- Line 1 (Opening): 40 characters maximum. No questions. States something unexpected, specific, or punchy.
- Line 2 (Contrast): 40 characters maximum. Contradicts, reframes, or undercuts the opening.
Every variation must:
- Include at least one "How I" or "I" statement across the two lines
- Include a digit or metric where possible
- Follow clickbait principles: tension, curiosity gap, stakes
Produce 6 variations covering different angles:
- Number-led: Lead with a specific number or metric
- Contrarian: State a belief then flip it
- Personal transformation: Before vs after with a digit
- Authority steal: Reference a name, tool, or brand
- Admission: Confess a mistake or loss
- Future shock: A prediction or "X is about to change"
Step 3. Output format
HOOKS for [topic]
1. [Number-led]
[Line 1]
[Line 2]
2. [Contrarian]
[Line 1]
[Line 2]
3. [Personal transformation]
[Line 1]
[Line 2]
4. [Authority steal]
[Line 1]
[Line 2]
5. [Admission]
[Line 1]
[Line 2]
6. [Future shock]
[Line 1]
[Line 2]
Step 4. Offer the next move
Ask:
Want me to build one of these into a full post? Call the post-formatter skill with the hook number.
Rules
- 40 characters maximum per line. Count them.
- No questions in the opening line.
- No em dashes.
- No filler words. Every word earns its place.
- Prefer digits over spelled numbers (3, not three).
- British English unless voice.md says otherwise.
- Never hedge. A weak hook is worse than no hook.
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 · 90 lines · 104 tokens per session scan A efe43558494c
hook-generator is a skill published in the GitHub repository Freespirits/social-auto-engine (23 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 632 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to hook-generator, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
repo-eco-mcp-app
Inline Claude Desktop widget for any public Eco game server - live player counts, meteor countdown, world stats. A hand-rolled MCP Apps reference implementation in Python (no bundler, no React). Triggers - eco-mcp-app, claude-desktop-eco-widget, mcp-apps-reference-implementation.
github-sync
Bidirectional synchronization of epics and tasks with GitHub issues, labels, and relationships.
trellis-start
Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/. Classifies incoming tasks and routes to brainstorm, direct edit, or task workflow. Use when beginning a new coding session, resuming work, starting a new task, or…
ops-pocket
OPS on-demand: This skill should be used when the user asks to "pocket memos", "voice memo pipeline"…
ops-package
OPS on-demand: This skill should be used when the user asks to "ship a parcel", "print a label", or…
ledger
OPS on-demand: This skill should be used when the user asks to "ops ledger", "what did we handle", or…