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/go4cas/quiver/agents-mdgit clone --depth 1 https://github.com/go4cas/quiverWrote 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/go4cas/quiver/agents-md)<a href="https://agentmods.dev/instructions/go4cas/quiver/agents-md"><img src="https://agentmods.dev/badge/instructions/go4cas/quiver/agents-md.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 | $0.02232 | $0.02232 |
| Opus 5 | $0.01116 | $0.01116 |
| Sonnet 5 | $0.00446 | $0.00446 |
| Haiku 4.5 | $0.00223 | $0.00223 |
Grade A, and why
quiver 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quiver — AI agent context
This file is the single source of truth for AI assistants working in this repo. CLAUDE.md imports it for Claude Code; Codex and other AGENTS.md-aware tools read it directly. Edit conventions here, not in CLAUDE.md.
Quiver is an Arrow.js starter template with file-based routing, layouts, reactive state, composables, and a full testing setup. Stack: Arrow.js · Vite · Tailwind CSS v4 · Vitest · Playwright. The router is built on the Navigation API (modern browsers only).
Folder structure
src/
├── framework/ # Router, DI, store, app bootstrap — edit with care
├── pages/ # File-based routes — add your pages here
├── layouts/ # Page wrapper layouts — add layouts here
├── components/ # Reusable UI components — add components here
├── state/ # Global reactive state modules — add stores here
├── composables/ # Reusable logic functions — add composables here
├── utils/ # Pure helper functions (hmrState)
└── main.js # App entry point — provide() global DI keys here
tests/
├── framework/ # Unit tests for framework utilities (Vitest)
├── composables/ # Unit tests for composables (Vitest)
└── e2e/ # End-to-end tests (Playwright)
Commands
npm run dev # Start Vite dev server
npm test # Run unit tests once
npm run test:watch # Run unit tests in watch mode
npm run test:e2e # Run E2E tests (Playwright)
npm run typecheck # Type-check src/ via JSDoc (tsc --noEmit, checkJs)
npm run build # Production build
npm run docs:dev # Start docs site locally
npm run docs:build # Build docs site
Always run npm run typecheck && npm test && npm run test:e2e before completing a task.
Types
The codebase is plain JavaScript typed via JSDoc, checked by tsc under checkJs + strict (see jsconfig.json). CI enforces a clean npm run typecheck. When adding code:
- Annotate exported functions with
@param/@returns; use@typedeffor shared shapes and@templatefor generics - Reuse existing typedefs via import syntax:
/** @typedef {import('../state/userState.js').User} User */ - Prefer a JSDoc cast
/** @type {X} */ (expr)over restructuring code to satisfy the checker - Do not convert files to TypeScript — the plain-JS + JSDoc setup is deliberate
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 · 184 lines · 2,232 tokens per session scan A ef8e24501c92
quiver AGENTS.md is an instructions file published in the GitHub repository go4cas/quiver (5 stars, last pushed 1mo ago), licensed MIT. It adds 2,232 tokens to every session, about $0.0112 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 instructions, from other repositories
OneJS AGENTS.md
AGENTS.md instructions for Singtaa/OneJS, covering onejs v3: agent guide, requirements, install, project setup and build and live reload.
vuestrata AGENTS.md
Instructions for boussadjra/vuestrata, covering using vite+, the unified toolchain for the web, built-in commands vs scripts, tool versions, review checklist and vuestrata project rules.
vuestrata CLAUDE.md
Instructions for boussadjra/vuestrata, covering claude.md, the one thing that trips people up, slash commands, verifying and testing reka-backed components.
vuestrata copilot-instructions.md
Instructions for boussadjra/vuestrata, covering copilot instructions, copilot-specific notes and before you finish.
OneJS CLAUDE.md
Claude Code instructions for Singtaa/OneJS: Agent guidance for this repository lives in AGENTS.md. Read it first.
vital AGENTS.md
Instructions for jvidalv/vital, covering ai agent development guide, quick reference, component creation workflow, step 1: determine component level and step 2: create component files.