Borrowing it
Nothing to install: this file belongs to epicsagas/Velith. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/epicsagas/Velith/main/AGENTS.mdgit 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/instructions/epicsagas/velith/agents-md)<a href="https://agentmods.dev/instructions/epicsagas/velith/agents-md"><img src="https://agentmods.dev/badge/instructions/epicsagas/velith/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/epicsagas/velith/agents-md"><img src="https://agentmods.dev/badge/instructions/epicsagas/velith/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01986 | $0.01986 |
| Opus 5.5 | $0.00794 | $0.00794 |
| Sonnet 5.5 | $0.00397 | $0.00397 |
| Haiku 4.5 | $0.00199 | $0.00199 |
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 1mo 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 — 100 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 that produces books to the human-quality bar: a cold reader should not be able to tell the manuscript was machine-drafted. 6-phase pipeline (Onboarding → Ideation → Outlining → Drafting → Editing → Publishing), 18 skills, 12 agents, 7 genre systems + custom, a model-agnostic visual pipeline, and an optional Svelte dashboard. Ships as a plugin with zero npm dependencies at the root.
Architecture
Plugin structure
skills/{skill-name}/SKILL.md — Skills (slash commands): frontmatter (name, description, argument-hint) + prompt
skills/loom/quality-bar.md — Shared standard: 5-axis rubric, 2026 AI-tell taxonomy (en/ko/ja), cold-read protocol, visual rules
agents/{agent-name}.md — Agents: frontmatter (name, description, tools[], effort) + prompt
velith.mjs — Unified CLI + HTTP server (scan/agents/stats/words/list/migrate/metrics/snapshot/images/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. Agents are subagents invoked by skills. loom is the router. quality-bar.md is read by every writing, editing, and reviewing agent; changes there change the whole product.
${CLAUDE_PLUGIN_ROOT} is used in skills and agents (Claude Code substitutes it). Codex TOMLs use {PLUGIN_ROOT} and are generated from agents/*.md; do not hand-edit them.
Operating principles (v0.5, supersede the 2025 design)
- Full-manuscript context. Agents read the whole manuscript, not summaries.
bible.mdis an index and ledger. (Replaces ADR-005 summary-based context.) - Sequential drafting for narrative genres; parallel (≤3) only for technical/reference/academic chapters proven independent by the outline DAG. (Amends ADR-003.)
- Voice lock on a sample chapter before drafting volume; recorded in
STYLE.md## Voice Lock. - Draft → critique → revise inside
chapter-writer; critiques saved in.velith/critiques/. - Editing rewrites in place with snapshots (
velith.mjs snapshot) and stage reports; 7 stages (0 fact-check … 6 readiness). - Readiness gate:
beta-readerwritesedits/readiness-report.mdwith YAMLverdict: PASS|REVISE,score,axes. Publishing requires PASS or an explicit override. - One look per book:
art-bible.md+.velith/art-bible.json; prompts compiled byvelith.mjs images compile; diagrams/charts/drawings are code-rendered byfigure-engineer; every image passes vision QA; look lock precedes volume. - Author checkpoints (required stops): concept, outline approval, voice lock, look lock, developmental restructures, readiness verdict.
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.
- 1mo ago Changed · -36 lines · -730 tokens per session d00c3b792b0c
- 1mo ago Changed · -9 lines · +512 tokens per session ef0df1adb1bf
- 1mo ago Changed · +10 lines · +281 tokens per session da6f1b28cf8d
- 1mo 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 (39 stars, last pushed 28d ago), licensed Apache-2.0. It adds 1,986 tokens to every session, about $0.0079 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.