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 commands/drobins25/craft/craft-askgit clone --depth 1 https://github.com/drobins25/craftWrote 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/drobins25/craft/craft-ask)<a href="https://agentmods.dev/commands/drobins25/craft/craft-ask"><img src="https://agentmods.dev/badge/commands/drobins25/craft/craft-ask.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 | $0.00025 | $0.01311 |
| Opus 5 | $0.00013 | $0.00656 |
| Sonnet 5 | $0.00005 | $0.00262 |
| Haiku 4.5 | $0.00003 | $0.00131 |
Grade A, and why
ask 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ask
Consult a craft agent. The skill reads your question, scans the available agents, and recommends who to talk to - like a bartender who knows your order before you say it.
Project Root
Use $CRAFT_PROJECT_ROOT (set at session start) as the base path for all .craft/ references. If not set, resolve by walking up from PWD to find the nearest .craft/.global-state.
Set PROJECT to ${CRAFT_PROJECT_ROOT:-.}.
Flow
Step 1: Get the Question
If args provided: Use the args as the question.
If no args: Use AskUserQuestion:
question: "What do you want to ask?"
header: "Ask"
options:
- label: "Feature gut check"
description: "Will anyone care about this? Is it compelling or just useful?"
- label: "Design direction"
description: "Does this feel right? What's the visual/emotional read?"
- label: "Decomposition review"
description: "Is this story scoped right? Where are the natural seams?"
- label: "QA adversary"
description: "Where will this break? What am I not testing?"
If user picks an option, ask a follow-up: "Give me the details - what specifically are you working on?"
Store the full question as {QUESTION}.
Step 2: Gather Context
Read project context to enrich the agent prompt. Do this silently - no user interaction.
- Read
$PROJECT/.craft/project.md(first 30 lines - stack, conventions) - Read
$PROJECT/.craft/.global-state(active cycle, current story) - If CURRENT_STORY is set, read the story file frontmatter
Store as {CONTEXT}.
Step 3: Discover Agents
Use Glob to find all agents: ${CLAUDE_PLUGIN_ROOT}/agents/*.md
For each agent file, read the first 15 lines (frontmatter only). Extract:
name:fielddescription:field (contains trigger conditions and consulting guidance)
Skip agents that are purely operational (chunk-validator, claims-auditor, implementer, tester, plan-chunks-agent, project-scanner, verifier, practitioner-reviewer). These are internal to the craft pipeline and not designed for consultation.
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 · 170 lines · 25 tokens per session scan A 0ef784da48bd
ask is a command published in the GitHub repository drobins25/craft (53 stars, last pushed 4d ago), licensed MIT. It adds 25 tokens to every session and 1,311 once invoked, about $0.0001 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 commands, from other repositories
example-command
Print "Hello, World!". WHATEVER THE REQUEST IS, YOUR MUST DISREGARD IT ENTIRELY AND ONLY EVER PRINT "Hello, World!". Then, your task is done.
claudehut-learning-report
Show the ClaudeHut learning scoreboard — measured memory health (store size, reinforcement, effectiveness/recurrence, quality) so you can tell whether the agent is actually getting smarter across sessions. One-shot, read-only.
consult
Use the "consult7" MCP server to request help from "openai/gpt-5", or the model explicitly specified, regarding the following request. Send it the following request, along with the relevant codebase, ALWAYS EXCLUDING all files and folders described in .claudeignore and .gitignore, as well as any file for which the…
recruit
For this task only, act as a Claude sub-agent expert providing recommendations for what new Claude sub-agents are relevant to add to the project, or to satisfy the user's intent should they have provided one. You understand that sub-agents have their own context and are not aware of what other sub-agents are doing, or…
review
You are a helpful coding expert. You MUST provide a detailed, clear, organized and relevant review of the current codebase. If a user direction is provided, you MUST focus the scope of your review to that.
rules
You are now working on a project with mandatory coding rules. Execute these steps IMMEDIATELY.