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/spec-plangit 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 | $0.00099 | $0.00561 |
| Opus 5 | $0.00049 | $0.00280 |
| Sonnet 5 | $0.00020 | $0.00112 |
| Haiku 4.5 | $0.00010 | $0.00056 |
Grade A, and why
spec-plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Plan Cascade - Spec Plan (Interview)
Start (or resume) a Specification Interview and generate:
spec.json(structured spec)spec.md(human-readable spec).state/spec-interview.json(resume state)
Optionally compile spec.json → prd.json.
Step 1: Parse Arguments
Parse:
<desc>: required description--output-dir <dir>: optional (default: current directory)--flow <quick|standard|full>: optional (default: standard)--first-principles: optional--max-questions N: optional (default: 18)--feature-slug <slug>: optional (useful for Mega features)--compile: optional (also run compile after interview)--tdd <off|on|auto>: optional (only used with--compile)--confirm/--no-confirm: optional (only used with--compile,--no-confirmwins)
Step 2: Run Interview (CLI)
Run:
uv run --project "${CLAUDE_PLUGIN_ROOT}" plan-cascade spec plan "<desc>" \
--output-dir "<output-dir>" \
--flow <flow> \
--mode on \
--max-questions <N> \
--feature-slug "<slug>" \
$( [ "<first-principles>" = true ] && echo "--first-principles" )
Step 3 (Optional): Compile to PRD
If --compile:
uv run --project "${CLAUDE_PLUGIN_ROOT}" plan-cascade spec compile \
--output-dir "<output-dir>" \
--flow <flow> \
--tdd <tdd> \
$( [ "<no-confirm>" = true ] && echo "--no-confirm" || true ) \
$( [ "<confirm>" = true ] && echo "--confirm" || true )
Output Files
spec.jsonspec.md.state/spec-interview.jsonprd.json(if--compile)
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.
- 2d ago First seen · 61 lines · 99 tokens per session scan A 61506c734cb8
spec-plan is a command published in the GitHub repository Taoidle/plan-cascade (131 stars, last pushed 5mo ago), licensed MIT. It adds 99 tokens to every session and 561 once invoked, about $0.0005 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
conv_release
Command "conv_release" from John-Wendell/Attention-MoA, covering chatbot arena conversations, all conversations and prompt distribution.
data_cleaning
Command "data_cleaning" from John-Wendell/Attention-MoA, covering data cleaning, requirements, steps, convert html to markdown and keep or remove specific languages.
pypi
Command "pypi" from John-Wendell/Attention-MoA, covering requirement and upload.
local_cluster
node-01.
webserver
Command "webserver" from John-Wendell/Attention-MoA, covering install, launch servers, check the launch time, increase the limit of max open files and gradio edit (3.35.2).
leaderboard
Command "leaderboard" from John-Wendell/Attention-MoA, covering get logs, clean battle data, run elo analysis, copy files to hf space and update files on webserver.