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 surfmind-space/awesome-surfmind --skill hook-generatorgit clone --depth 1 https://github.com/surfmind-space/awesome-surfmindWrote 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/surfmind-space/awesome-surfmind/hook-generator)<a href="https://agentmods.dev/skills/surfmind-space/awesome-surfmind/hook-generator"><img src="https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/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 5.1 | $0.00069 | $0.00611 |
| Opus 5 | $0.00034 | $0.00305 |
| Sonnet 5 | $0.00014 | $0.00122 |
| Haiku 4.5 | $0.00007 | $0.00061 |
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 7d 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hook Generator
Generates several strong opening lines for your topic or page, each taking a different angle, while staying honest to the source instead of reaching for clickbait.
- Identify the audience, promise, tension, novelty, and concrete subject from the selection, request, and source.
- Generate hooks using different angles such as problem, surprise, contrarian, story, benefit, data point, or question. Put the key specifics (the figure, name, or result) inside the hook line itself, not only in your commentary around it.
- Cross-check every hook against the source. Before you use any number, name, or claim, re-read the exact sentence it comes from and keep its scope: a figure that holds only for some cases (a team size, a date range, a single cohort) carries that qualifier with it, and a number means only what the source says it means — never repurpose "70% of the gain came from X" into "a 70% improvement." Never introduce a percentage, statistic, or figure that is not in the source.
- Always finish with a "Proof needed" pass that names the weakest hook and the evidence it would take to publish it safely. Dropping a caveat counts as an unsupported claim, so flag it. "Nothing to flag" is allowed only when every hook restates a fact stated verbatim in the source — and even then, say so explicitly rather than staying silent.
Return the hook options labeled by angle, then call out the best fit and the proof still needed. Be specific without overclaiming, preserve important names, numbers, and links, avoid unverifiable numbers, and do not create clickbait the content cannot satisfy. If the visible context is insufficient, say what is missing and give the best supported next step.
Example
For a blog post about a team that cut its build time from 20 minutes to 90 seconds:
- Problem: "Every push meant a 20-minute coffee break no one asked for."
- Data point: "We took our CI from 20 minutes to 90 seconds — here's the one change that did most of the work."
- Contrarian: "Faster builds didn't come from a bigger machine. They came from deleting code."
- Best fit: Data point — it leads with the concrete result the post delivers.
- Proof needed: The "one change" claim — confirm the post attributes the bulk of the gain to a single fix before publishing.
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.
- 7d ago First seen · 33 lines · 69 tokens per session scan A 77a3563bea57
hook-generator is a skill published in the GitHub repository surfmind-space/awesome-surfmind (5 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 611 once invoked, about $0.0003 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
uiux-master
UI/UX expert for design systems, accessibility, and avoiding generic AI-generated design patterns.
cs-master
Expert computer scientist for algorithms, complexity analysis, and distributed systems.
data-science
ML engineering expert for feature engineering, model debugging, and production pipelines.
network-devops
Network performance expert for latency optimization, packet analysis, and infrastructure tuning.
quant-finance
Quantitative finance expert for trading strategies, risk management, and portfolio optimization.
rust-master
Rust expert for async systems, unsafe code, and zero-cost abstractions.