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/sidkandan/clironchef/agents-mdgit clone --depth 1 https://github.com/sidkandan/CLIronChefWrote 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/sidkandan/clironchef/agents-md)<a href="https://agentmods.dev/instructions/sidkandan/clironchef/agents-md"><img src="https://agentmods.dev/badge/instructions/sidkandan/clironchef/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 | $0.02859 | $0.02859 |
| Opus 5 | $0.01430 | $0.01430 |
| Sonnet 5 | $0.00572 | $0.00572 |
| Haiku 4.5 | $0.00286 | $0.00286 |
Grade A, and why
CLIronChef 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 4d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Operating Contract
This file is for Claude Code, Codex CLI, Gemini CLI, and any other agent launched from this repository. Read it before touching a live cook.
About This Project
CLIronChef is a Python CLI + library that controls a Typhur Dome 2 air fryer and Sync ONE wireless probe via the official Typhur cloud API. Its goal: let humans AND AI agents drive adaptive, probe-driven cooks declaratively.
Your role as an agent: configure cooks, monitor probe telemetry, hot-modify mode/temp/time based on probe thresholds, and tell the user when to act. The user always presses physical Start. You never claim to bypass safety interlocks. You stay attentive enough to push-notify when a cook needs attention.
Fresh Session Bootstrap
If you only read one file, read this one. If you are planning or supervising a live cook, also read these before sending commands to the appliance:
- docs/getting-started/GETTING_STARTED_AI_AGENT.md — live-cook operating rules and communication style
- docs/cooking/MODES.md — mode selection by element bias and fan behavior
- docs/cooking/COOK_LIFECYCLE.md — timer semantics, Start/Stop, stuck-state recovery
For docs/navigation work, start at docs/README.md. For release hygiene, use docs/project/PUBLIC_RELEASE_CHECKLIST.md.
Non-Negotiable Rules
- Do not try to bypass the physical Start button. Configure the cook, then ask the user to press Start.
- Do not use API PAUSE. Treat it as terminal.
- Do not let the Dome timer reach
0before the probe target. Timer zero is terminal for normal CLI control. - Do not set
setTime=0to finish a cook. Send STOP at the probe pull target. - Use
setTime=2400for every cooking phase and every hot-modify. - Keep adaptive cooks single-stage:
cookingStageNum=1. - Hot-modify only with the active
cookUuid. - Never overwrite an active cook unless the user explicitly tells you to.
- Do not commit credentials, MQTT certs, run logs, vendor app archives, binary analysis output, or personal device IDs.
- Do not commit raw phone media (
.mov,.heic,.heif). Use cropped, metadata-stripped, muted derivatives underdocs/assets/.
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.
- 4d ago First seen · 258 lines · 2,859 tokens per session scan A 3adb8935b508
CLIronChef AGENTS.md is an instructions file published in the GitHub repository sidkandan/CLIronChef (5 stars, last pushed 3mo ago), licensed MIT. It adds 2,859 tokens to every session, about $0.0143 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 2026-08-31.
Other instructions, from other repositories
core integrations.instructions.md
Instructions for home-assistant/core, covering file locations, general guidelines, entity platforms, integration quality scale and how rules apply.
mdb-esp32-cashless AGENTS.md
Instructions for nodestark/mdb-esp32-cashless, covering vmflow — agent context, 1. mqtt rpc — real-time device control, 2. supabase rest — data & credits, 3. agent playbooks and notes.
iot-dc3 AGENTS.md
AGENTS.md instructions for pnoker/iot-dc3, covering agents.md, scope and precedence, sources of truth, project overview and repository map.
core CLAUDE.md
Claude Code instructions for home-assistant/core, a project described as: :housewithgarden: Open source home automation that puts local control and privacy first.
iot-dc3 CLAUDE.md
Claude Code instructions for pnoker/iot-dc3: This file provides guidance to AI coding assistants when working with code in this repository.
AetherEdge AGENTS.md
Instructions for EvanL1/AetherEdge, covering aetheredge agent instructions, product direction, repository map, architecture boundaries and ai safety.