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-planninggit 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-planning)<a href="https://agentmods.dev/commands/drobins25/craft/craft-planning"><img src="https://agentmods.dev/badge/commands/drobins25/craft/craft-planning.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 | $0.00021 | $0.05712 |
| Opus 5 | $0.00010 | $0.02856 |
| Sonnet 5 | $0.00004 | $0.01142 |
| Haiku 4.5 | $0.00002 | $0.00571 |
Grade A, and why
planning 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 — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Craft Planning
You are managing the project's feature roadmap - the strategic planning layer that sits above cycles and stories. This is the PM's wiki for tracking what's coming, what's active, and what questions remain open.
Project Root
Set PROJECT to ${CRAFT_PROJECT_ROOT:-.}.
Set PLANNING to $PROJECT/.craft/planning.
Entry Flow
When /craft:planning is invoked, check state and route.
Step 1: Check if planning exists
Use Glob to check if $PLANNING/active.md exists.
If NOT found -> Go to Setup Flow (Step 2). If found -> Go to Active Flow (Step 3).
Step 2: Setup Flow (first time)
No planning folder exists yet. Help the user create one.
"No planning folder found. Let's set up your roadmap."
Use AskUserQuestion:
question: "How would you like to start?"
header: "Setup"
options:
- label: "Generate from input (Recommended)"
description: "Feed me a transcript, doc, or spec and I'll extract concepts for your review"
- label: "Start from scratch"
description: "Describe what you're building and I'll structure it"
- label: "Import from existing backlog"
description: "Turn existing backlog stories into a planning roadmap"
If "Generate from input" -> Go to Add From Input (Step 5). If "Start from scratch" -> Go to Conversational Setup (Step 6). If "Import from existing backlog" -> Go to Import Flow (Step 7).
After setup completes, create the folder structure:
mkdir -p "$PLANNING"
Write README.md and active.md using templates from ${CLAUDE_PLUGIN_ROOT}/templates/planning/. Replace template variables with actual values.
Step 3: Active Flow (planning exists)
Read the current state and suggest the most useful next action.
Use Read to read $PLANNING/active.md. Extract last_updated from frontmatter. Extract the Focus section (content between ## Focus and the next --- divider).
Use Read to read $PLANNING/README.md. Parse the Roadmap table to get concept names, statuses, and files.
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 · 505 lines · 21 tokens per session scan A cf2ef5b6554b
planning is a command published in the GitHub repository drobins25/craft (53 stars, last pushed 6d ago), licensed MIT. It adds 21 tokens to every session and 5,712 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
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.