Borrowing it
Nothing to install: this file belongs to vvedantb/eva. 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/vvedantb/eva/main/AGENTS.mdgit clone --depth 1 https://github.com/vvedantb/evaWrote 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/vvedantb/eva/agents-md)<a href="https://agentmods.dev/instructions/vvedantb/eva/agents-md"><img src="https://agentmods.dev/badge/instructions/vvedantb/eva/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 5.1 | $0.00541 | $0.00541 |
| Opus 5 | $0.00270 | $0.00270 |
| Sonnet 5 | $0.00108 | $0.00108 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
eva 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- eva CLAUDE.md — 86% identical, 11 lines differ
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FOLLOW ALL OF THESE RULES
Same rules as CLAUDE.md. Domain details live in the two docs below — read them when relevant.
Git / ship
- NEVER create a new branch, push, or open a PR unless the user asks.
- If already on main and the user asks to ship: commit and push directly to main.
- Prefer
/preflightoccasionally over husky commit/push gates (hooks under.husky/are commented out). - Plans: final step is
/shipunless the user says not to.
Always
- Greenfield OK — breaking changes fine.
- Implementing from an agreed plan: just implement.
- Think first; simplest solution wins. Ask when unsure / ambiguous — as many questions as needed.
- Prefer a detailed plan over a quick one. Plan mode: concise plans; list unresolved questions; use
grill-me/ AskUserQuestion to interview until shared understanding. - Explain changes when done. Check web/docs when needed.
- Only edit
CLAUDE.md/ this file when the user explicitly asks. Entries: 1 sentence (~20 words max), not changelog paragraphs. - No
any,unknown,as, or non-null!. NoisRecord(object: unknown)— parse at the boundary (Zod). Hard types → rethink design. - Prefer simplicity, small diffs, co-location, explicit behavior, long-term maintainability. No premature abstractions. No new deps unless necessary.
- Do not default to
useState/useRef— pick the right state ownership first. - Do not run dev / lint / build unless the user asks.
- After medium+ changes: no banned types;
tscwhere relevant; updateinternal/changelog.md(createinternal/if missing). Changelog entry: Title, Date (YYYY-MM-DD), WHY summary, architectural reason if any.
Domain docs (read when relevant)
- Frontend / UI work →
docs/eva-ui.md(tone-based surfaces, no decorative hairlines; components, router, vite, nuqs) - Convex / schema / migrations →
docs/eva-convex.md - agent-browser on eva app → navigate to
/?agentto auto sign in as the agent user
Product facts
- This repo is a platform for managing other codebases and running them remotely (sandbox app ≠ this codebase).
- Sandbox provider is Vercel; Daytona is legacy. Sandboxes: IPv4 only (no IPv6).
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 · 38 lines · 541 tokens per session scan A c496b6150b1f
eva AGENTS.md is an instructions file published in the GitHub repository vvedantb/eva (101 stars, last pushed yesterday), licensed MIT. It adds 541 tokens to every session, about $0.0027 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 2026-09-03.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.