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/u14app/deep-research/agents-mdgit clone --depth 1 https://github.com/u14app/deep-researchWhat 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 | $0.01460 | $0.01460 |
| Opus 5 | $0.00730 | $0.00730 |
| Sonnet 5 | $0.00292 | $0.00292 |
| Haiku 4.5 | $0.00146 | $0.00146 |
Grade C, and why
deep-research AGENTS.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Destructive Actions**: Avoid `rm -rf` or history rewriting in git unless explicitly requested. How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This document provides essential guidelines and technical references for AI agents (and human developers) working on the Deep Research repository. Adhere to these patterns to ensure consistency, security, and maintainability.
🚀 Development Workflow & Commands
The project uses pnpm as the primary package manager.
Core Commands
- Install Dependencies:
pnpm install - Development Server:
pnpm dev(Runs athttp://localhost:3000) - Build Project:
pnpm build - Static Export:
pnpm build:export(Generatesout/directory) - Standalone Build:
pnpm build:standalone - Linting:
pnpm lint
Testing
- Status: Currently, there are no automated tests in the codebase.
- Guideline: If adding tests, use Vitest or Jest following standard Next.js patterns. Place test files next to the code they test (e.g.,
ComponentName.test.tsx) or in a__tests__directory. - Single Test: To run a single test (if added), use
pnpm vitest run path/to/file.test.ts.
📂 Project Structure
src/app: Next.js App Router (Pages, API routes, Layouts).src/components: UI components.ui/: Shadcn primitives.Internal/: Custom shared components.Research/,Knowledge/, etc.: Feature-specific components.
src/hooks: Custom React hooks for business logic and state interaction.src/libs: External service integrations (e.g., MCP server logic).src/store: Zustand stores for global state and persistence.src/utils: Helper functions and core deep research logic.src/locales: I18n translation files (JSON).
🎨 Code Style & Conventions
1. TypeScript & Types
- Strict Mode:
strict: trueis enabled intsconfig.json. Always provide explicit types for function parameters and return values. - Global Types: Core business logic types (e.g.,
SearchTask,Knowledge,Source) are defined insrc/types.d.ts. Check this file before creating new interfaces. - Explicit Any: While
@typescript-eslint/no-explicit-anyis currentlyoff, avoidanyunless absolutely necessary for external library compatibility. Preferunknownor specific interfaces. - Zod: Use Zod for schema validation, especially for AI response parsing and API request bodies. See
src/app/api/mcp/server.tsfor examples.
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 · 123 lines · 1,460 tokens per session scan C 1740f40dca71
deep-research AGENTS.md is an instructions file published in the GitHub repository u14app/deep-research (4,682 stars, last pushed 2mo ago), licensed MIT. It adds 1,460 tokens to every session, about $0.0073 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
bob-plugin-ollama-translator AGENTS.md
Instructions for CaicoLeung/bob-plugin-ollama-translator, covering repository guidelines, project overview, architecture & data flow, key directories and development commands.
bob-plugin-ollama-translator CLAUDE.md
Instructions for CaicoLeung/bob-plugin-ollama-translator, covering claude.md, agent skills, issue tracker, triage labels and domain docs.
ClawRouter CLAUDE.md
Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
SearChat CLAUDE.md
Claude Code instructions for yokingma/SearChat, covering claude.md, project overview, architecture, monorepo structure and key technologies.
ima2-gen AGENTS.md
Instructions for lidge-jun/ima2-gen, covering ima2-gen — ai context, what this project does, tech stack, project structure and agent skills (packaged).
AI-MarkDone copilot-instructions.md
Instructions for zhaoliangbin42/AI-MarkDone, covering ai copy enhance - ai coding agent instructions, project overview, architecture patterns, adapter pattern for multi-platform support and shadow dom isolation.