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/taoidle/plan-cascade/design-generategit clone --depth 1 https://github.com/Taoidle/plan-cascadeWhat 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 | $0.00034 | $0.02685 |
| Opus 5 | $0.00017 | $0.01342 |
| Sonnet 5 | $0.00007 | $0.00537 |
| Haiku 4.5 | $0.00003 | $0.00268 |
Grade A, and why
design-generate 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 3d 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 — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Cascade - Generate Design Document
Generate a structured technical design document (design_doc.json). Auto-detects the appropriate level based on available files.
Path Storage Modes
This command works with both new and legacy path storage modes:
New Mode (Default)
mega-plan.json: In~/.plan-cascade/<project-id>/prd.json: In worktree directory or~/.plan-cascade/<project-id>/design_doc.json: Always created in project root (user-visible file)
Legacy Mode
- All files in project root or worktree directory
Note: design_doc.json is a user-visible documentation file and always stays in the working directory.
Two-Level Design Document System
┌─────────────────────────────────────────────────────────────┐
│ Level 1: Project Design (from mega-plan.json) │
│ ─────────────────────────────────────────────────────────── │
│ • Global architecture and system overview │
│ • Cross-feature components and patterns │
│ • Project-wide ADRs (architectural decisions) │
│ • Feature mappings (which patterns/decisions apply where) │
│ • Shared data models and API standards │
└─────────────────────────────────────────────────────────────┘
│
│ inheritance
▼
┌─────────────────────────────────────────────────────────────┐
│ Level 2: Feature Design (from prd.json) │
│ ─────────────────────────────────────────────────────────── │
│ • Feature-specific components │
│ • Feature-specific APIs and data models │
│ • Feature-specific ADRs (prefixed ADR-F###) │
│ • Story mappings (which components/decisions per story) │
│ • Inherits patterns/decisions from project level │
└─────────────────────────────────────────────────────────────┘
Tool Usage Policy (CRITICAL)
To avoid command confirmation prompts:
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.
- 3d ago First seen · 381 lines · 34 tokens per session scan A 7ba83c6ed891
design-generate is a command published in the GitHub repository Taoidle/plan-cascade (131 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 2,685 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
/release
Release a new version — updates CHANGELOG, pyproject.toml, creates git tag, and pushes.
delegate
Delegate a task to any engine and model through the anymodel-runner subagent.
choose
Pick an AnyModel action, provider, and model through an interactive semantic chain.
delegate-with
Delegate through an interactive provider and model selection chain.
review-with
Run an adversarial review through an interactive provider and model selection chain.
setup
Check local engine and provider setup, and optionally toggle the stop-time review gate.