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/epicsagas/velith/book-initnpx skills add epicsagas/Velith --skill book-initgit clone --depth 1 https://github.com/epicsagas/VelithWrote 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/epicsagas/velith/book-init)<a href="https://agentmods.dev/skills/epicsagas/velith/book-init"><img src="https://agentmods.dev/badge/skills/epicsagas/velith/book-init.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 | $0.00032 | $0.00332 |
| Opus 5 | $0.00016 | $0.00166 |
| Sonnet 5 | $0.00006 | $0.00066 |
| Haiku 4.5 | $0.00003 | $0.00033 |
Grade A, and why
book-init 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.
What it actually says
Phase 0: Onboarding
Max 3 questions per round, max 3 rounds.
R1 — Genre (fiction/non-fiction/technical) · Audience (1-2 personas) · Language R2 — Scale (5-15 chapters, word count) · Timeline · Existing materials R3 — Voice (conversational/academic/narrative) · Tone · Special requirements
Source scan if materials confirmed: find vault + alcove search_project_docs/search_vault in parallel.
Outputs:
PRD.md— genre, language, reader, scale, timeline, source map, success criteriaSTYLE.md— voice/tone, language rules, formatting, prohibited patternsdrafts/edits/publish/sources/directories
Gate: PRD.md + STYLE.md exist, source map has 3+ items.
Poetry note: For poetry/poetry-essay genres, STYLE.md line targets per poem should be 20-80 lines (not the default 10-30). Word/character targets in PRD.md should reflect total poem count × average length rather than a flat word count.
Post-Completion
Update the project dashboard status:
node {PLUGIN_ROOT}/velith.mjs scan [project-dir] --plugin-root={PLUGIN_ROOT}
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 · 33 lines · 32 tokens per session scan A b47f018a0b31
book-init is a skill published in the GitHub repository epicsagas/Velith (33 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 332 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 2026-08-30.
Other skills, from other repositories
company-finder
Translates an ICP definition into a step-by-step guide for identifying target companies in lemlist using signals, triggers, and firmographic filters. Use when asked "find me companies to target", "how do I find accounts in lemlist", "build a company list", "which companies match my ICP", "how to use lemlist signals to…
people-finder
Translates an ICP and persona definition into a step-by-step guide for configuring lemlist's people database search to find the right contacts. Use when asked "find me contacts", "who do I search for in lemlist", "how do I find the right person to email", "build a contact list in lemlist", "search for [role] in…
offer-definer
Transform product descriptions and feature lists into compelling, outcome-focused offers for cold outreach. Use when asked "how to frame my offer", "what should I say in cold emails", "how to pitch my product", "make my offer clearer", "value proposition for outreach", "how do I explain what we do", "turn features…
icp-definer
Define and prioritize narrow Ideal Customer Profiles (ICPs) for outbound targeting. Use when asked "who should we target", "define ICP", "best customers for X", "outbound targeting", "who gets most value", "segment customers", "narrow audience", "prioritize accounts", "who should we reach out to", or "build me an…
persona-definer
Identify and prioritize buyer personas at the contact level for outbound targeting. Use when asked "who should I email", "define buyer persona", "what role to target", "who is the decision maker", "who has this pain", "which title to reach out to", "should I target VPs or Directors", or "contact-level targeting". Use…
epic-definition
Define an epic with strategic context, feature breakdown, milestones, and success metrics. Use when scoping a large body of work for planning and tracking.