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 skills add ai-driven-dev/framework --skill 12-cookgit clone --depth 1 https://github.com/ai-driven-dev/frameworkWrote 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/skills/ai-driven-dev/framework/12-cook)<a href="https://agentmods.dev/skills/ai-driven-dev/framework/12-cook"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/12-cook/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/skills/ai-driven-dev/framework/12-cook"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/12-cook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.00462 |
| Opus 5.5 | $0.00017 | $0.00185 |
| Sonnet 5.5 | $0.00008 | $0.00092 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
12-cook 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.
What it actually says
Cook
flowchart LR
unnamed([unnamed recipe]) --> list
named-new([new recipe]) --> research
named-update([update recipe]) --> research
named-research([research topic]) --> research
named-apply([apply recipe]) --> apply
named-validate([validate recipe or all]) --> validate
list -->|list only| listed([listed])
list -->|create, update, or reselect for research| research
list -->|select or reselect to apply| apply
list -->|resume dedup| upsert
list -->|reselect to validate| validate
research -->|unnamed or stale number| list
research -->|standalone research| researched([researched])
research -->|create, update, or selected insights| upsert
upsert -->|new or substantial, missing verified results| research
upsert -->|new, before dedup| list
upsert -->|written| validate
validate -->|stale number| list
validate -->|CLI absent or unsupported| unavailable([validation unavailable])
validate -->|standalone, pass| validated([validated])
validate -->|standalone, findings| findings([findings])
validate -->|upsert, pass| saved([saved])
validate -->|upsert, findings: repair at Scaffold| upsert
apply -->|unnamed or stale number| list
apply -->|report only or chosen steps complete| reported([reported])
Actions
Run the flow above. Read only the next action file.
| Action | Does |
|---|---|
| list | list project and bundled recipes |
| research | research one recipe or topic |
| upsert | create or update one recipe |
| apply | apply one existing recipe |
| validate | validate one or all recipes |
Transversal rules
- Never maintain a separate recipe index.
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- actions/01-list.md 1.2 KB
- actions/02-upsert.md 2.2 KB
- actions/03-research.md 2.2 KB
- actions/04-apply.md 1.6 KB
- actions/05-validate.md 2.1 KB
- assets/recipe-template.md 1.2 KB
- assets/recipes/install-aiddy-in-codex.md 2.1 KB
- assets/recipes/mcp-installation.md 11 KB
- assets/recipes/token-optimization.md 19 KB
- assets/research-checklist.md 496 B
- assets/research-goal-checklist.md 830 B
- assets/validation-report-template.md 742 B
- references/recipe-contract.md 932 B
- references/recipe-locations.md 1.4 KB
- references/research-playbook.md 2.8 KB
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 Changed · +21 lines · -1 tokens per session 07747e1ec7b2
- 1mo ago First seen · 32 lines · 43 tokens per session scan A f8063bd51cc5
12-cook is a skill published in the GitHub repository ai-driven-dev/framework (523 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 462 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
tech-stack-detective
Reverse-engineer a company's tech stack from public signals — job listings, StackShare, GitHub, engineering blog, and their live website. Use this skill when a user asks "what tech does Stripe use", "what's Linear's stack", "what does Notion run on", "reverse engineer [company]'s tech stack", "what framework does…
agent
Default browser automation agent — click, fill forms, navigate, log in, and extract structured data from any website using a natural-language goal, or run the same task across multiple sites in parallel. New users get 600 free automation credits to start; beyond that it draws on your plan's automation credits (unlike…
apple-tools
Reach Apple PIM data (Calendar, Contacts, Reminders, Messages, Location, Maps, Weather) from a pi session via iMCP + pi's built-in MCP on macOS. Use when the user asks to read/search their Apple Calendar, Contacts, Reminders, iMessages, current Location, Maps, or Weather. Does NOT cover Apple Mail — iMCP exposes no…
pi-dashboard-bootstrap
Make sure the local pi-dashboard server is running before any pi-dashboard action. Use FIRST whenever the user mentions the pi dashboard, pi sessions or pi agents, or asks to start/open the dashboard; also when a dashboard call fails with "connection refused".
automation
Instructions for managing scheduled tasks through the host's structured automation tool, including reminders, delayed work, recurring checks, and result delivery.
kb-search
Search the local markdown knowledge base for facts, prior decisions, definitions, people, error codes, config flags, and how-we-fixed-it notes. ALWAYS search here BEFORE answering a project-specific question from memory, guessing, or asking the user. Use whenever you hit an unknown term, an unfamiliar entity, an error…