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.
git 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/edit)<a href="https://agentmods.dev/commands/taoidle/plan-cascade/edit"><img src="https://agentmods.dev/badge/commands/taoidle/plan-cascade/edit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/taoidle/plan-cascade/edit"><img src="https://agentmods.dev/badge/commands/taoidle/plan-cascade/edit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00038 | $0.00825 |
| Opus 5.5 | $0.00015 | $0.00330 |
| Sonnet 5.5 | $0.00008 | $0.00165 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
edit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hybrid Ralph - Edit PRD
You are opening the PRD file for manual editing.
Path Storage Modes
PRD file location depends on the storage mode:
- New Mode:
~/.plan-cascade/<project-id>/prd.jsonor in worktree directory - Legacy Mode:
prd.jsonin project root or worktree
The command uses PathResolver to find the correct file location.
Step 1: Verify PRD Exists
# Get PRD path from PathResolver
PRD_PATH=$(uv run python -c "from plan_cascade.state.path_resolver import PathResolver; from pathlib import Path; print(PathResolver(Path.cwd()).get_prd_path())" 2>/dev/null || echo "prd.json")
# Also check local prd.json (in worktree)
if [ -f "prd.json" ]; then
PRD_PATH="prd.json"
elif [ ! -f "$PRD_PATH" ]; then
echo "ERROR: No PRD found at: $PRD_PATH"
echo "Please generate one first with:"
echo " /plan-cascade:hybrid-auto <description>"
echo " /plan-cascade:hybrid-manual <path>"
exit 1
fi
Step 2: Open in Editor
Open the PRD file with the system's default editor:
# Detect platform and open editor
if [[ "$OSTYPE" == "msys" || "$OSTYPE" == "win32" || "$OS" == "Windows_NT" ]]; then
# Windows
start "$PRD_PATH"
elif [[ "$OSTYPE" == "darwin"* ]]; then
# macOS
open "$PRD_PATH"
else
# Linux - use $EDITOR or fallback
${EDITOR:-nano} "$PRD_PATH"
fi
Tell the user:
Opening PRD at: {PRD_PATH} in your default editor...
Make your changes, then save and close the editor to continue.
Step 3: Wait for Editor to Close
Wait for the user to finish editing. (The editor command will block until closed.)
Step 4: Validate Updated PRD
After the editor closes, validate the modified PRD:
# Check JSON syntax
if ! uv run python -m json.tool "$PRD_PATH" > /dev/null 2>&1; then
echo "ERROR: Invalid JSON in PRD at: $PRD_PATH"
echo "Please fix the syntax errors and run /plan-cascade:edit again"
exit 1
fi
Validate structure:
- Has
metadata,goal,objectives,stories - Each story has required fields
- Story IDs are unique
- Dependency references exist
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.
- 1mo ago First seen · 110 lines · 38 tokens per session scan A b4a79d0b454a
edit is a command published in the GitHub repository Taoidle/plan-cascade (132 stars, last pushed 7mo ago), licensed MIT. It adds 38 tokens to every session and 825 once invoked, about $0.0002 per session on Opus 5.5. 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.
create-epo-patent
Create a complete EPO-compliant patent application from invention disclosure through filing-ready package.
search-flights
Search award flight availability across airlines.
scan
Populate the world model — the project's directories and files, stored as tables in the trajectory DB — by walking the project root for git repos and pulling each dir's README.md into a summary. Single phase — no background fill required for the primary navigation surface.
guide
Interactive guide to fellowship. Walks you through a real task using the structured research-plan-implement flow, then shows you what's next.
ui-audit
Run comprehensive UI/UX design validation against design principles, accessibility standards, and usability laws.