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 instructions/epicsagas/velith/agents-mdgit clone --depth 1 https://github.com/epicsagas/VelithWhat 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 | $0.01923 | $0.01923 |
| Opus 5 | $0.00962 | $0.00962 |
| Sonnet 5 | $0.00385 | $0.00385 |
| Haiku 4.5 | $0.00192 | $0.00192 |
Grade A, and why
Velith AGENTS.md 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What is Velith
A Claude Code plugin for AI-native book publishing. 6-phase pipeline (Onboarding → Ideation → Outlining → Drafting → Editing → Publishing) with 16 skills, 7 agents, and 7 genre systems. Ships as a plugin with an optional Svelte dashboard.
Architecture
Plugin structure
skills/{skill-name}/SKILL.md — Skills (slash commands): frontmatter (name, description) + prompt
agents/{agent-name}.md — Agents: frontmatter (name, description, tools[]) + prompt
velith.mjs — Unified CLI + HTTP server (scan/agents/stats/words/list/migrate/serve)
vendor/sql.js/sql-wasm.js/wasm — Vendored SQLite WASM binary (no npm install required)
.claude-plugin/plugin.json — Plugin manifest (skills path, agent list)
Skills are the user-facing entry points (/book-init, /book-draft, etc.). Agents are specialized subagents invoked by skills during pipeline phases. The loom skill is the router that detects project state and routes to the correct phase.
Skill → Agent mapping
| Phase | Skill | Agent(s) used |
|---|---|---|
| 0 | /book-init |
— |
| 1 | /book-ideation |
— |
| 2 | /book-outline |
book-architect |
| 3 | /book-draft |
chapter-writer, scene-generator (fiction), continuity-editor |
| 4 | /book-edit |
style-doctor, continuity-editor |
| 5 | /book-publish |
cover-designer, marketing-expert |
Agent tool constraints
- Each agent has minimal tool access by design (e.g., style-doctor has Read/Edit/Glob/Grep/Bash but no Write)
Genre system
8 genre skills provide genre-specific templates and validation rules: book-fiction, book-nonfiction, book-technical, book-screenplay, book-poetry, book-game, book-academic, book-genre-creator (meta-skill for custom genres).
Genres are string-based (no typed enum) — branching happens via conditional logic in skills and agents. Adding a new genre requires creating skills/book-{genre}/SKILL.md and updating the genre lists in skills/loom/SKILL.md, README.md, dashboard HelpView.svelte, and i18n files.
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 · 135 lines · 1,923 tokens per session scan A 6849ec5d8559
Velith AGENTS.md is an instructions file published in the GitHub repository epicsagas/Velith (33 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,923 tokens to every session, about $0.0096 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 instructions, from other repositories
open-ontologies CLAUDE.md
Instructions for fabio-rovai/open-ontologies, covering open ontologies, ontology engineering workflow, generate, validate and load and reason.
knowns GEMINI.md
Instructions for knowns-dev/knowns, covering gemini, canonical guidance, minimum rules and quick reference.
kin GEMINI.md
Instructions for firelock-ai/kin, covering kin: read the repository from the graph, pick the tool by what you know, trust the envelope, not the emptiness, if the tools have no graph and a working order.
kin AGENTS.md
Instructions for firelock-ai/kin, covering agents.md and this repo's role.
seo-page-creator-agent AGENTS.md
Instructions for aiapplications001-art/seo-page-creator-agent, covering seo page creator agent, agent operating notes and useful commands.
writing-template-for-ai AGENTS.md
Instructions for hottweelz/writing-template-for-ai, covering agents.md, non-negotiables (read first), source of truth, required startup behavior and two-stage process.