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/manta-ide/manta/agents-mdgit clone --depth 1 https://github.com/manta-ide/mantaWrote 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/manta-ide/manta/agents-md)<a href="https://agentmods.dev/instructions/manta-ide/manta/agents-md"><img src="https://agentmods.dev/badge/instructions/manta-ide/manta/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 | $0.00585 | $0.00585 |
| Opus 5 | $0.00293 | $0.00293 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
manta 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 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.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
- Root app: Next.js (TypeScript) in
srcwith App Router.- UI in
src/components, hooks insrc/hooks, utilities insrc/lib. - Routes: pages under
src/app(e.g.,page.tsx), API undersrc/app/api/*.
- UI in
- Public assets in
public/. - Helper scripts in
scripts/(e.g.,scripts/setup-db.ts). - Vite template in
vite-base-template/(standalone dev environment).
Build, Test, and Development Commands
- Root app:
npm run dev— start Next.js with Turbopack onhttp://localhost:3000.npm run build— production build.npm run start— run built app.npm run lint— ESLint checks.
- Vite template:
cd vite-base-template && npm run dev— start Vite (default:5173).npm --prefix vite-base-template run build— build Vite app.
Coding Style & Naming Conventions
- Language: TypeScript (
strictenabled,noEmit: true). Path alias@/*→src/*. - Linting: Next.js + TypeScript config (
eslint.config.mjs);@typescript-eslint/no-explicit-anyis disabled. - Indentation: 2 spaces. Components in PascalCase, variables/functions in camelCase, files in kebab-case (Next.js conventions like
page.tsx,route.ts). - Styling: Tailwind CSS v4 is configured.
Testing Guidelines
- No test runner is currently configured. Prefer:
- Unit/UI: Vitest or Jest + React Testing Library.
- E2E: Playwright.
- Place tests next to source:
Component.test.tsxor under__tests__/. - Aim for critical-path coverage (core components, API handlers).
Commit & Pull Request Guidelines
- Commit messages: imperative, concise, scoped if helpful.
- Examples:
feat(editor): add split panes,fix(api): handle 500 on export.
- Examples:
- PRs must include:
- Summary of changes and rationale.
- Steps to test locally; attach screenshots for UI changes.
- Linked issue(s) and checklist: builds, lints, and runs locally.
Security & Configuration Tips
- Environment: use
.env.localfor developer machines; do not commit secrets. - Key vars:
NEXT_PUBLIC_*are client-exposed. - Rotate any leaked credentials promptly; prefer per-env keys.
- Proxy/iframe: app rewrites
/iframe/*to a dynamic API (src/app/api/iframe).
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 · 47 lines · 585 tokens per session scan A 774ede7381c3
manta AGENTS.md is an instructions file published in the GitHub repository manta-ide/manta (74 stars, last pushed 8d ago), licensed MIT. It adds 585 tokens to every session, about $0.0029 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
OpenHands AGENTS.md
AGENTS.md instructions for OpenHands/OpenHands, covering repository notes, general, repository map — what belongs where, cross-repository boundaries and pr description human check.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
OwnPilot AGENTS.md
Instructions for ownpilot/OwnPilot, covering ownpilot, architecture, key patterns, commands and tech stack.
SeekMoney-ai CLAUDE.md
Instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.
kernel-lore-mcp CLAUDE.md
Claude Code instructions for mjbommar/kernel-lore-mcp, covering kernel-lore-mcp — project state, pointers, standards, original goal and non-negotiable product constraints.
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.