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-dashboardgit 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-dashboard)<a href="https://agentmods.dev/commands/drobins25/craft/craft-dashboard"><img src="https://agentmods.dev/badge/commands/drobins25/craft/craft-dashboard.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 5.1 | $0.00043 | $0.01497 |
| Opus 5 | $0.00022 | $0.00749 |
| Sonnet 5 | $0.00009 | $0.00299 |
| Haiku 4.5 | $0.00004 | $0.00150 |
Grade A, and why
dashboard 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dashboard
Opens .craft/dashboard.html - a single page rendering your project's whole graph (cycles, stories, records, and how they connect). The page is a copied artifact with its own version, independent of the plugin version; this command is what keeps it current.
Project Root
Use $CRAFT_PROJECT_ROOT (set at session start) as the base path for all .craft/ references. If not set, resolve it by walking up from PWD to find the nearest .craft/.global-state.
Set PROJECT to ${CRAFT_PROJECT_ROOT:-.}.
Flow
Step 1: Check the page
Run:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/dashboard/dashboard-page.sh --check --root "$PROJECT"
Read STATE and COPY from its output. Branch:
STATE=no-project - print one plain line: "No craft project found here - run /craft:init first." Stop. Do not rebuild, do not open.
STATE=missing - this is a first run, nothing to ask. Pull silently:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/dashboard/dashboard-page.sh --pull --root "$PROJECT"
No question, no extra line about it. Remember that this was the first run - Step 2 prints the reveal instead of the routine receipt. Continue to Step 2.
STATE=behind - the shipped template moved ahead of the user's copy. Ask via AskUserQuestion, wording chosen by COPY:
COPY=edited: "Your copy has local edits. Pulling replaces it - your edited version will be kept at .craft/dashboard-backup.html."COPY=unknown: "Your dashboard page looks different from what craft last delivered (or was never tracked). Pulling replaces it - your current version will be kept at .craft/dashboard-backup.html."COPY=pristine: "A better version of your second brain is ready. Pull it?"
Options are "Pull the update" and "Keep my current page" (declining is always allowed). If the user accepts, run:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/dashboard/dashboard-page.sh --pull --root "$PROJECT"
Either way, continue to Step 2.
STATE=current - nothing to ask, nothing to print about it. Continue to Step 2.
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 · 119 lines · 43 tokens per session scan A e7c5e1278308
dashboard is a command published in the GitHub repository drobins25/craft (53 stars, last pushed 6d ago), licensed MIT. It adds 43 tokens to every session and 1,497 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
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.
project
Generate project documentation (product.md, structure.md, tech.md, codemaps/).
repo-architect
Repository structure optimization and multi-repo management with ruv-swarm coordination for scalable project architecture and development workflows.
analyst
Use when performing local analyst review before pushing PR changes. Assesses code quality, impact analysis, and maintainability.
performance-bottlenecks
Identify and resolve performance bottlenecks in your development workflow.