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-dialgit 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-dial)<a href="https://agentmods.dev/commands/drobins25/craft/craft-dial"><img src="https://agentmods.dev/badge/commands/drobins25/craft/craft-dial.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 | $0.00031 | $0.00588 |
| Opus 5 | $0.00015 | $0.00294 |
| Sonnet 5 | $0.00006 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
dial 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 5d 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
Dial
Settle a visual question on a surface that already renders, by putting the candidates on the real page instead of describing them. Craft measures the live surface, injects 2-4 lettered positions plus a small control panel, and you click through A/B/C in your own browser - against real data, real neighbors, real viewport. Nothing is ever written to source; a refresh discards everything. Every session files a record, including the ones where the current value wins.
This shell owns only routing. The flow lives in one reference file.
Flow
Step 1: Parse the subject
If args provided: the args are the subject - what to dial, on which surface.
If no args: take the subject from the session context (the conversation that led here names it). If nothing in context names a visual question with a bounded candidate set, ask conversationally - "What are we dialing, and on which surface?" - no AskUserQuestion, never; the flow asks nothing through widgets end to end.
Step 2: Degradation preflight
Establish which rung this session runs on before opening anything. The ladder is defined in the flow reference (Step 0 there); the short form: no reachable dev server and no discoverable way to start one means dial cannot run - say so plainly and stop. Runnable-but-not-running folds the server start into the flow's opening move, never a separate question.
Step 3: Run the flow
Read ${CLAUDE_PLUGIN_ROOT}/commands/references/dial-inline.md and execute it inline, from Step 0, with the subject and session context in hand.
Never invoke the flow via the Skill tool - a Skill-tool call ends the turn and control never comes back for the react loop and the four exits; inline execution is the contract (see .claude/rules/skill-invocation-chain-breaks.md).
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.
- 5d ago First seen · 39 lines · 31 tokens per session scan A d855ad809342
dial is a command published in the GitHub repository drobins25/craft (53 stars, last pushed 6d ago), licensed MIT. It adds 31 tokens to every session and 588 once invoked, about $0.0002 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
run-action
Execute a learned Maestro flow ("action") by name with optional -e KEY=VALUE parameters. Looks the flow up via packages/rn-dev-agent-core/dist/learned-actions.js (same inventory as /rn-dev-agent:list-learned-actions), then replays it via cdprunaction — auto-repair-aware orchestration with structured RunRecords (GH.
interactive-dev
Start a persistent interactive development session with natural language browser control, auto-error monitoring, and full dev tool access.
record-workflow
Record browser interactions and generate a Playwright test with assertions and best-practice selectors.
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.
orchestrate
This tool coordinates Claude Code's actions. It does NOT write code or create content.
repo-architect
Repository structure optimization and multi-repo management with ruv-swarm coordination for scalable project architecture and development workflows.