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/thiagodmont/keynobi/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.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 | $0.01174 | $0.01174 |
| Opus 5 | $0.00587 | $0.00587 |
| Sonnet 5 | $0.00235 | $0.00235 |
| Haiku 4.5 | $0.00117 | $0.00117 |
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 6d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Tech Stack
- Framework: Tauri 2.0 (Rust backend + WKWebView frontend)
- Frontend: SolidJS + TypeScript + Vite
- Backend: Rust (tokio async runtime)
- Parsing: Tree-sitter (
tree-sitter-kotlin-ng) - Search: ripgrep library crates (
grep-regex,grep-searcher,grep-matcher) - Language Intelligence: JetBrains Kotlin/kotlin-lsp (download-on-demand)
- IPC Types:
ts-rs(Rust → TypeScript auto-generation) - State Management: SolidJS Stores (
createStore,produce) - Testing: Vitest (frontend), Rust
#[test]/tokio::test(backend), Criterion (benchmarks)
Before You Write Code
- Read
docs/BEST_PRACTICES.md— architectural principles, security rules, performance targets, and the AI-first design philosophy. - Read
docs/CODE_PATTERN.mdanddocs/DOMAIN_PATTERNS.md— concrete conventions: file naming, store patterns, IPC patterns, testing patterns. - Read
docs/USER_MANUAL.md— understand what the user sees and does, so new features integrate naturally.
Key Rules
- Path security: Every command that accepts a path must validate it against the project root using canonicalization (see
CODE_PATTERN.md§Path Security). Never use rawstarts_with()without canonicalization. - Keybindings = Actions: Use
registerKeyAndAction()inApp.tsx, never bareregisterKeybinding(). Shortcuts that bypass the action registry are invisible in the command palette. - Navigation: All jump-to-location actions must call
openFileAtLocation()fromproject.service.ts, notsetActiveFile()directly. This populates the navigation history stack. - IPC types: Import from
@/bindings, never redefine types that originate in Rust. - Mutex discipline: Lock Rust state, clone what you need, drop the lock, then do I/O. Never hold a Mutex across an
await. - Bounded collections: Every in-memory collection that grows must have an explicit cap (see
BEST_PRACTICES.md). - No
unwrap()in production Rust: Use?or.map_err(...).expect()is allowed only for programmer-error invariants. - Do not commit: The superpower spec and plan files.
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.
- 6d 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 (207 stars, last pushed 2d ago), licensed MIT. It adds 1,174 tokens to every session, about $0.0059 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
Amarok-Hider AGENTS.md
Instructions for deltazefiro/Amarok-Hider, covering amarok, project overview, build, e2e test and agent rules.
sceneview AGENTS.md
AGENTS.md instructions for sceneview/sceneview, covering agents.md — conventions for delegated coding agents, your role, git — you do not own it, secrets and hard technical rules.
maui-labs AGENTS.md
AGENTS.md instructions for dotnet/maui-labs, covering agent instructions, repository overview, products, technology stack and building.
rikkahub AGENTS.md
AGENTS.md instructions for rikkahub/rikkahub, covering repository guidelines, project overview, build, test, and development commands, module structure and concepts.
AppClaw CLAUDE.md
Claude Code instructions for appclawhq/AppClaw, covering claude.md, what is appclaw?, build & run commands, architecture and entry point & cli modes (src/index.ts).
agent-skills-standard CLAUDE.md
Claude Code instructions for HoangNguyen0403/agent-skills-standard, covering agent protocol and self-learning protocol.