Borrowing it
Nothing to install: this file belongs to thiagodmont/keynobi. 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/thiagodmont/keynobi/main/AGENTS.mdgit clone --depth 1 https://github.com/thiagodmont/keynobiWrote 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/thiagodmont/keynobi/agents-md)<a href="https://agentmods.dev/instructions/thiagodmont/keynobi/agents-md"><img src="https://agentmods.dev/badge/instructions/thiagodmont/keynobi/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/thiagodmont/keynobi/agents-md"><img src="https://agentmods.dev/badge/instructions/thiagodmont/keynobi/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 | $0.01076 | $0.01076 |
| Opus 5.5 | $0.00430 | $0.00430 |
| Sonnet 5.5 | $0.00215 | $0.00215 |
| Haiku 4.5 | $0.00108 | $0.00108 |
Grade A, and why
keynobi 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 1mo 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Keynobi is a macOS companion app for Android development: Gradle builds, logcat, devices, UI hierarchy, and an MCP server for AI clients. Tauri 2 (Rust, tokio) backend, SolidJS + TypeScript + Vite frontend, ts-rs for IPC types, rmcp for MCP.
Commands
npm ci # install
npm run tauri dev # run the app (first Rust build takes minutes)
npm run dev:web # frontend only, against the mock backend
npm run generate:bindings # after changing Rust models; commit src/bindings/
Where to Look
| Task | Read |
|---|---|
| Any change | references/BEST_PRACTICES.md, references/CODE_PATTERN.md |
| Build, logcat, devices, layout, settings | references/DOMAIN_PATTERNS.md |
| MCP tools, prompts, resources | references/MCP_SERVER.md |
| UI components, styling, accessibility | references/DESIGN_SYSTEM.md |
| User-visible behavior, shortcuts | references/USER_MANUAL.md |
Each reference doc ends with Known Gaps: rules the code does not meet yet. Do not copy a known gap into new code.
Key Rules
- Layering: components → stores/services →
src/lib/tauri-api.ts→ Tauri commands → Rust services. Onlytauri-api.tscallsinvoke; commands validate and delegate. - IPC contract: a command change updates the Rust handler,
generate_handler!inlib.rs, thetauri-api.tswrapper, and the mock backend together. After changing Rust models, runnpm run generate:bindingsandnpm run generate:ipc-fixtures; import IPC types from@/bindingsand never edit generated files. - One implementation per behavior: Tauri commands and MCP tools call the same service function. Never copy logic into
mcp_server.rs. - Process model:
keynobi --mcpattaches to the running app when it can (the app serves the session on its own state) and otherwise runs standalone with its own state, which the GUI does not see. Seereferences/MCP_SERVER.md§ Modes. - Untrusted input: validate identifiers with
utils/validation.rsand paths withutils/path.rs(canonicalized, never rawstarts_with). Arguments toadb shellare re-parsed by the device shell. - Rust: no
unwrap()in production code; new commands returnResult<T, AppError>; never hold a Mutex across.await; every growing collection has a named cap. - Frontend: register shortcuts with
registerKeyAndAction()inApp.tsx; build UI from@/components/uiprimitives and theme tokens. - User data: tests must never read or write
~/.keynobi. Unit tests get a temp data directory automatically (cfg(test)insettings_manager); integration tests must calltests/common::isolate_data_dir()first. CI fails if a test creates~/.keynobi.
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.
- 1mo ago Changed · +32 tokens per session b1aa7b799982
- 1mo ago Changed · -19 lines · -130 tokens per session 071145a4434a
- 2mo ago First seen · 87 lines · 1,174 tokens per session scan A 25c4e395a413
keynobi AGENTS.md is an instructions file published in the GitHub repository thiagodmont/keynobi (202 stars, last pushed 18d ago), licensed MIT. It adds 1,076 tokens to every session, about $0.0043 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.
keynobi AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| keynobi AGENTS.mdthiagodmont/keynobi | Instructions file | 202 | 18d ago | MIT | A | 1,076 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | 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 | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |