Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add drobins25/craft/plugin install 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-cycle-design)<a href="https://agentmods.dev/commands/drobins25/craft/craft-cycle-design"><img src="https://agentmods.dev/badge/commands/drobins25/craft/craft-cycle-design.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 | $0.00045 | $0.03270 |
| Opus 5 | $0.00023 | $0.01635 |
| Sonnet 5 | $0.00009 | $0.00654 |
| Haiku 4.5 | $0.00005 | $0.00327 |
Grade A, and why
cycle-design 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 6d 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cycle Design
Create a new cycle or detail an existing one — this IS the planning phase. Stories come out fully fleshed with implementation details.
Phase Dispatch (runs before Step 1)
If args specify an existing planning cycle directory (e.g., /craft:cycle-design 5-auth-flow AND .craft/cycles/5-auth-flow/cycle.yaml exists with status: planning):
→ Read ${CLAUDE_PLUGIN_ROOT}/commands/references/cycle-design/detailing-mode.md for the flesh-out flow.
If args are provided AND .craft/cycles/[arg]/cycle.yaml exists but status is NOT planning (i.e., cycle is ready, active, or complete):
→ Show error: "Cycle [arg] is not in planning status. Use /craft:cycle-start [arg] to activate it, or run /craft:cycle-design without args to create a new cycle." Stop. Do NOT continue to Philosophy or Step 1.
Otherwise (no args, or args don't match an existing cycle directory): Continue to Philosophy and the standard flow below.
Philosophy
Plan first. Files last. Align before you chunk.
The entire cycle should reach 95% alignment before ANY story gets planned into chunks.
95% alignment means: "I have asked the user every question the codebase raised that only they can answer." It's about capturing the user's intent - not about whether the solution approach is right. A spawned Explore agent investigates the codebase and surfaces conflicts, adjacencies, and assumptions; the orchestrator turns those findings into product questions and confirms the user's decisions through dialogue. The orchestrator does not do the investigation itself - it spawns the agent. See commands/references/alignment-check.md for the full pattern.
- Discuss everything in conversation
- Lock decisions as you go
- Run the alignment check per-story (codebase investigation + product questions)
- Confirm the whole plan
- THEN plan chunks (with full alignment)
No half-baked stories. No "I'll figure it out during implementation." Align thoroughly, execute confidently.
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.
- 6d ago First seen · 304 lines · 45 tokens per session scan A 5d62a65bac54
cycle-design is a command published in the GitHub repository drobins25/craft (53 stars, last pushed 7d ago), licensed MIT. It adds 45 tokens to every session and 3,270 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.