plan

A command that creates a large project plan by splitting it into features that can be developed in parallel, while recording dependencies between them.

In plain words
What is it for?
Use it to plan projects with multiple features, optionally setting a shared workflow, test-driven development (TDD), or specification process for those features.
Why use it?
It makes complex projects easier to coordinate by showing which features can proceed independently and which must wait.

Command

Install

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.

agentmods
npx agentmods add commands/taoidle/plan-cascade/plan
Clone the repo
git clone --depth 1 https://github.com/Taoidle/plan-cascade
Per session 92 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,777 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00092 $0.05777
Opus 5 $0.00046 $0.02889
Sonnet 5 $0.00018 $0.01155
Haiku 4.5 $0.00009 $0.00578

Measured 2d ago against content hash ea126e3e764b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

Origin

This is a copy

86% identical to mega-plan — 223 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/mega-plan/commands/plan.md · 710 lines

How it starts

The opening of the file, as written. The whole thing — 710 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mega Plan - Project-Level Feature Orchestration

You are creating a Mega Plan - a project-level plan that orchestrates multiple features in parallel.

Execution Flow Parameters

This command accepts flow control parameters that propagate to all feature executions:

Parameter Priority

Parameters flow through three stages in mega-plan execution:

  1. Command-line flags to THIS command (highest priority)

    • Example: /mega:plan --flow full --tdd on "Build platform"
    • Saved to mega-plan.json as flow_config, tdd_config, spec_config, etc.
  2. Command-line flags to /mega:approve

    • Can override values saved in mega-plan.json
    • Propagated to all feature PRDs
  3. PRD-level overrides (per feature, if needed)

    • Individual features can have custom parameters in their PRDs
    • Rarely used; usually all features use mega-plan settings
  4. Default values (lowest priority)

Parameter Propagation Chain:

# Step 1: Create mega-plan with parameters
/mega:plan --flow full --tdd on --spec auto "Build e-commerce"
# → Saves to mega-plan.json:
#   flow_config: {level: "full", propagate_to_features: true}
#   tdd_config: {mode: "on", propagate_to_features: true}
#   spec_config: {mode: "auto", ...}

# Step 2: Execute with saved parameters
/mega:approve
# → Reads from mega-plan.json
# → For each feature: creates PRD with inherited flow/tdd settings
# → Sub-agents execute stories with these settings

# Step 3: Execute with override
/mega:approve --flow standard
# → Uses flow="standard" (overrides mega-plan.json)
# → All features get flow="standard", tdd="on" (from mega-plan.json)

Note: Spec interview parameters (--spec, --first-principles, --max-questions) are used by the orchestrator in mega-approve Step 6.0, NOT propagated to feature agents.

--flow <quick|standard|full>

Override the execution flow depth for all feature approve phases.

Flow Gate Mode AI Verification Code Review Test Enforcement
quick soft disabled no no
standard soft enabled no no
full hard enabled required required

Read the full file on GitHub · 710 lines

Changes

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.

  1. 2d ago First seen · 710 lines · 92 tokens per session scan A ea126e3e764b

Subscribe to this mod's changes

plan is a command published in the GitHub repository Taoidle/plan-cascade (131 stars, last pushed 5mo ago), licensed MIT. It adds 92 tokens to every session and 5,777 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to mega-plan, differing in 223 lines, and is treated as a copy.