Navigator is an open-source AI workspace for individuals and teams that combines conversations with AI models, MCP tools, image generation, custom agents, visual workflows, and collaboration. People use it to interact with AI providers and automate work through a shared interface; the catalogue instruction relates to using Navigator.
Borrowing it
Nothing to install: this file belongs to keinsaasforever/better-chatbot. 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/keinsaasforever/better-chatbot/main/AGENTS.mdgit clone --depth 1 https://github.com/keinsaasforever/better-chatbotWrote 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/keinsaasforever/better-chatbot/agents-md)<a href="https://agentmods.dev/instructions/keinsaasforever/better-chatbot/agents-md"><img src="https://agentmods.dev/badge/instructions/keinsaasforever/better-chatbot/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/keinsaasforever/better-chatbot/agents-md"><img src="https://agentmods.dev/badge/instructions/keinsaasforever/better-chatbot/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 | $0.00617 | $0.00617 |
| Opus 5.5 | $0.00247 | $0.00247 |
| Sonnet 5.5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
better-chatbot 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 7d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Layout
pnpm + Turborepo workspace.
apps/web— the Next.js app; almost all changes happen heresrc/app(routes, API, middleware),src/components(UI),src/lib(auth, db, ai, storage),src/hooks
apps/desktop— Electron shell (local MCP servers, filesystem, keychain)packages/*— shared MCP schemas and contracts; never import fromapps/webservers/mcp-stdio— local-exec MCP server used by the desktop apptests/(end-to-end),scripts/(maintenance),docker/
Root commands pass through to apps/web, so pnpm dev and friends work from
the repository root.
Commands
| Command | What it does |
|---|---|
pnpm dev |
Run locally |
pnpm build / pnpm start |
Production build and run |
pnpm check |
Lint, typecheck, unit tests — the gate before every commit |
pnpm test / pnpm test:e2e |
Vitest / Playwright |
pnpm db:migrate / pnpm db:studio |
Apply migrations / browse the database |
pnpm db:check-parity |
Verify a journal replay matches the schema |
pnpm docker-compose:up |
Full local stack |
Conventions
- Verification gate:
pnpm checkbefore every commit. Addpnpm buildfor changes to streaming, the schema, or the client/server boundary. - Commits: Conventional Commits (
feat:,fix:,docs:, …). Filenames are kebab-case. Biome formats and lints on commit. - Migrations are hand-written SQL in
apps/web/src/lib/db/migrations/pg/plus a matchingmeta/_journal.jsonentry. Do not rundrizzle-kit generate— it produces drifted snapshots against this schema. A journal entry's timestamp must be newer than every entry before it, or the migration is silently skipped on databases that are already past it. - Auth: API routes go through
withAuthfromlib/auth/route-guard. Repository reads and writes are scoped by user and workspace — do not widen them. Never return a raw error message from a 500 handler. - Chat history reads stay bounded by
CHAT_MESSAGE_WINDOW(lib/const.ts). - Streamed markdown is split into block-stable units and memoized; keep per-update work proportional to the tail block, not the whole message.
- Tests cover the happy path plus one failure mode, and run without a
database — mock
pgDb.
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.
- 7d ago Changed · +6 lines · -18 tokens per session 4baddab79f4e
- 2mo ago First seen · 43 lines · 635 tokens per session scan A a0e059f6fa51
better-chatbot AGENTS.md is an instructions file published in the GitHub repository keinsaasforever/better-chatbot (1,196 stars, last pushed yesterday), licensed MIT. It adds 617 tokens to every session, about $0.0025 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.
better-chatbot AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| better-chatbot AGENTS.mdkeinsaasforever/better-chatbot | Instructions file | 1.2k | yesterday | MIT | A | 617 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |