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-reviewgit clone --depth 1 https://github.com/Taoidle/plan-cascadeWrote 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/taoidle/plan-cascade/design-review)<a href="https://agentmods.dev/commands/taoidle/plan-cascade/design-review"><img src="https://agentmods.dev/badge/commands/taoidle/plan-cascade/design-review.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 | $0.00033 | $0.02326 |
| Opus 5 | $0.00016 | $0.01163 |
| Sonnet 5 | $0.00007 | $0.00465 |
| Haiku 4.5 | $0.00003 | $0.00233 |
Grade A, and why
design-review 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 — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Cascade - Review Design Document
Review the current design_doc.json and make interactive edits to components, patterns, architectural decisions, and story mappings.
Path Storage Modes
Design documents are user-visible files and remain in the working directory in both modes:
design_doc.json: Located in current working directory (project root or worktree)- PRD references may be in different locations based on storage mode
This command primarily works with design_doc.json in the current directory.
Tool Usage Policy (CRITICAL)
To avoid command confirmation prompts:
-
Use Read tool for file reading - NEVER use
catvia Bash- ✅
Read("design_doc.json"),Read("prd.json") - ❌
Bash("cat design_doc.json")
- ✅
-
Use Write tool for file updates
- ✅
Write("design_doc.json", content) - ❌
Bash("echo '...' > design_doc.json")
- ✅
Step 1: Load Design Document
Read design_doc.json:
If design_doc.json does not exist:
ERROR: No design document found.
Generate one with:
/plan-cascade:design-generate (from PRD)
/plan-cascade:design-import <file> (from external doc)
EXIT
Step 2: Validate Document
Check for structural issues:
- Missing required sections
- Empty overview title
- Invalid ADR references
- Orphaned story mappings
Report any validation errors before proceeding.
Step 3: Display Design Document
Format and display the design document:
════════════════════════════════════════════════════════════════
DESIGN DOCUMENT REVIEW
════════════════════════════════════════════════════════════════
📋 OVERVIEW
────────────────────────────────────────────────────────────────
Title: <overview.title>
Summary: <overview.summary>
Goals:
• <goal 1>
• <goal 2>
...
Non-Goals:
• <non-goal 1>
...
🏗️ ARCHITECTURE
────────────────────────────────────────────────────────────────
Components (N total):
[1] ComponentName
Description: <description>
Responsibilities:
• <responsibility 1>
• <responsibility 2>
Dependencies: <dep1>, <dep2>
Files: <file1>, <file2>
[2] AnotherComponent
...
Data Flow:
<data_flow description>
Patterns (M total):
[1] PatternName
Description: <description>
Rationale: <rationale>
[2] AnotherPattern
...
📝 ARCHITECTURAL DECISIONS
────────────────────────────────────────────────────────────────
[ADR-001] <title>
Status: <status>
Context: <context>
Decision: <decision>
Rationale: <rationale>
Alternatives: <alt1>, <alt2>
[ADR-002] <title>
...
🔌 INTERFACES
────────────────────────────────────────────────────────────────
APIs (P endpoints):
[API-001] <METHOD> <path>
Description: <description>
Request: <request_body summary>
Response: <response summary>
[API-002] ...
Data Models (Q models):
[1] ModelName
Description: <description>
Fields:
• field_name: <type>
• field_name: <type>
[2] AnotherModel
...
🔗 STORY MAPPINGS
────────────────────────────────────────────────────────────────
story-001: Components=[A, B], Decisions=[ADR-001], Interfaces=[API-001]
story-002: Components=[C], Decisions=[], Interfaces=[Model1]
...
════════════════════════════════════════════════════════════════
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 · 403 lines · 33 tokens per session scan A 1507a846ddbf
design-review is a command published in the GitHub repository Taoidle/plan-cascade (140 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 2,326 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
setup-video-vision
Interactive setup wizard for claude-video-vision — configure backend, whisper, frames, and verify dependencies.
doctor
Health check for greatcto. Shows pipeline state, missing artefacts, hook status, last run per agent, and permission-denied tail.
review
12-angle code review + skeptical triage (3-round + arbiter) for security/reliability P0/P1 findings, OR traceability tree. Default: review current branch vs main. --deep: triage ALL P0/P1 angles (not just security). With trace : render REQ → IMPL → TEST tree for impact analysis. Creates or closes gate:code for…
discover
Run a full product discovery cycle — from outcome definition through opportunity mapping, prioritisation, and experiment design. Use when the team isn't sure what to build next, or before writing a PRD for a complex feature space.
ccr
CCR (Compressed Context with Retrieval) — recall the full original of context that greatcto compressed/filtered out, by its short id. The retrieval half of the compression layer.
coding-audit
Medical-coding / revenue-cycle compliance audit. Invokes rcm-reviewer to assess autonomous ICD-10-CM / CPT / HCPCS coding for False Claims Act exposure (upcoding/unbundling), NCCI edits + MUEs, medical necessity (LCD/NCD), modifier discipline, HIPAA minimum-necessary — and force a certified-coder (CPC/CCS) sign-off.