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/utensils/claudette/frontendgit clone --depth 1 https://github.com/utensils/claudetteWhat 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 | $0.00394 | $0.00394 |
| Opus 5 | $0.00197 | $0.00197 |
| Sonnet 5 | $0.00079 | $0.00079 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
claudette frontend.instructions.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 2d 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.
What it actually says
Frontend code is React, TypeScript strict mode, Zustand, CSS modules, Vite, Bun, and Vitest. Do not use any; read the actual type definitions before constructing fixtures or Tauri payloads.
State belongs in the existing Zustand slices under src/ui/src/stores/slices/. Add or update a domain slice instead of growing component-local state that must survive navigation, workspace switching, or event replay.
Keep large components from becoming god files. Before adding substantial logic to Sidebar.tsx, ChatPanel.tsx, ChatInputArea.tsx, TerminalPanel.tsx, settings sections, or large CSS modules, prefer a focused child component, hook, pure helper, or testable logic module in the same feature folder.
Preserve established workflows and UI affordances. Treat removed buttons, changed keyboard behavior, lost selection, broken scrolling, altered terminal sizing, dropped context-menu actions, changed tab/session ordering, and missing loading/error states as regressions unless explicitly requested.
Use existing service wrappers in src/ui/src/services/ for Tauri IPC. Keep command names and payload shapes aligned with Rust models and commands. Do not bypass typed wrappers for one-off invoke calls when a service module owns the domain.
All colors outside src/ui/src/styles/theme.css must use CSS custom properties, usually var(--token-name) or rgba(var(--token-rgb), alpha). Do not add raw hex/rgb/rgba literals to components or CSS modules.
Prefer logic tests for behavior-heavy UI. Put pure behavior in helpers when possible and cover it with Vitest. For TypeScript changes, run cd src/ui && bunx tsc -b; test passing alone is not enough.
Do not update bun.lock unless dependency changes are intentional. Use Bun commands, not npm or yarn.
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.
- 2d ago First seen · 20 lines · 394 tokens per session scan A bc66396e1811
claudette frontend.instructions.md is an instructions file published in the GitHub repository utensils/claudette (75 stars, last pushed 2d ago), licensed MIT. It adds 394 tokens to every session, about $0.0020 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
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
sofagent GEMINI.md
Instructions for KongFangXun/sofagent, covering gemini.md · sofagent gemini cli 适配（薄挂载）, 会话开始时按序加载（四层加载链）, 审计强制（平台无关） and 连接 mcp server.
openbridge-webcomponents docgen.instructions.md
Instructions for Ocean-Industries-Concept-Lab/openbridge-webcomponents, covering doc generator cli, it never edits the original and keep the prompt aligned with the rules.
agents CLAUDE.md
Instructions for eloylp/agents, covering claude.md, project overview, directory structure, config model and build & run.
growmos AGENTS.md
Instructions for codician-team/growmos: This repository keeps a knowledge graph in .growmos/ (entities, typed relations, provenance, profiles, a journal). It is the shared world model that survives context windows. Treat it as memory you read at the start of work and write to as you develop. Zero-config commands.
ideate AGENTS.md
Instructions for paultyng/ideate, covering agents.md, build features as mcp tools first, ui second, when to add ui and pattern.