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.
git clone --depth 1 https://github.com/hainamchung/agent-assistantWrote 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/commands/hainamchung/agent-assistant/cook)<a href="https://agentmods.dev/commands/hainamchung/agent-assistant/cook"><img src="https://agentmods.dev/badge/commands/hainamchung/agent-assistant/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/commands/hainamchung/agent-assistant/cook"><img src="https://agentmods.dev/badge/commands/hainamchung/agent-assistant/cook.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 | $0.00010 | $0.00444 |
| Opus 5.5 | $0.00004 | $0.00178 |
| Sonnet 5.5 | $0.00002 | $0.00089 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
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 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.
What it actually says
/cook — Feature Implementation Router
ROUTER DIRECTIVE: Analyze feature complexity and route to appropriate implementation workflow.
$ARGUMENTS
🛑 PRE-FLIGHT (DO FIRST — BLOCKS EXECUTION)
LOAD now (in order; path ./rules/ or ~/.{TOOL}/skills/agent-assistant/rules/):
- CORE.md — Identity, Laws, Routing
- PHASES.md — Phase Execution
- AGENTS.md — Tiered Execution
⛔ Do not run any workflow phase until all are loaded. Follow all rules in those files. Then run this file's ROUTING LOGIC, LOAD the chosen variant workflow, and execute it.
ROUTING LOGIC
IF feature is simple (clear spec, low complexity):
→ Route to /cook:fast
IF feature is complex (multi-component, research needed):
→ Route to /cook:hard
IF feature is complex AND maximum quality with team collaboration needed:
→ Route to /cook:team
IF unsure:
→ Default to /cook:fast
AVAILABLE ROUTES
| Route | When to Use |
|---|---|
/cook:fast |
Quick features, clear specifications |
/cook:hard |
Complex features, full workflow |
/cook:team |
Maximum quality with parallel agent team collaboration |
PRESENT OPTIONS
## 🍳 Feature Mode Selection
**Feature**: [parsed feature]
**Choose workflow:**
1. ⚡ **Fast** → `/cook:fast` — Quick implementation
2. ⚡⚡⚡ **Hard** → `/cook:hard` — Full feature development
3. 👥 **Team** → `/cook:team` — Full team collaboration (parallel agents, maximum quality)
⏳ Awaiting selection...
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 First seen · 71 lines · 10 tokens per session scan A b6642da137ee
cook is a command published in the GitHub repository hainamchung/agent-assistant (54 stars, last pushed 5mo ago), licensed MIT. It adds 10 tokens to every session and 444 once invoked, about $0.0000 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 commands, from other repositories
taskstoissues
Deprecated: Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
speckit.github.taskstoissues
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
nxs.intake
Record a design change that already landed, whose reasoning lives in its merged pull request. One reference in; a drafted close record read from the pull request's body, review threads and commit messages; one approval gate; a drainable intake entry out. Writes nothing to GitHub before approval, cuts no branch, opens…
nxs.close
Relay to nexus close, the plain command that closes an epic over its merged pull requests. Runs only when its arguments name the epic — --epic , a bare , or --pr , which close resolves to its epic; otherwise it refuses at once and names nexus close --epic . Given one, it runs nexus close with the same arguments, shows…
template
Manage issue templates for streamlined issue creation.
speckit.assess.intake
Capture and normalize a raw idea (text, URL, ticket, or codebase pointer) into an intake note.