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/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 | $0.00092 | $0.05777 |
| Opus 5 | $0.00046 | $0.02889 |
| Sonnet 5 | $0.00018 | $0.01155 |
| Haiku 4.5 | $0.00009 | $0.00578 |
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.
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.
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:
-
Command-line flags to THIS command (highest priority)
- Example:
/mega:plan --flow full --tdd on "Build platform" - Saved to
mega-plan.jsonasflow_config,tdd_config,spec_config, etc.
- Example:
-
Command-line flags to
/mega:approve- Can override values saved in
mega-plan.json - Propagated to all feature PRDs
- Can override values saved in
-
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
-
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 |
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 · 710 lines · 92 tokens per session scan A ea126e3e764b
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.
Other commands, from other repositories
xstatus
Executed by Main Agent directly. Scan the project, collect workflow state, and generate an HTML status report.
org-reorg-trauma-audit
Pre-reorg trauma audit and sequencing plan. Opens with the 70%+ reorg-failure honesty, runs trauma history + threat-activation forecast (SCARF), produces a wave-based sequencing plan, communication architecture grounded in Kotter + Bridges, per-team mitigation, and post-reorg Talent IS monitoring cadence. Refuses…
culture-values-ops
Operationalize declared values into systems. For each value, build the matrix — hire criteria, promote criteria, celebration triggers, fire criteria, measurement metric, pay structure — and run the operational test (can an outsider deduce this value from these systems alone?). Refuses values-as-aspiration; insists on…
lavra-work-teams
Work on multiple beads with persistent worker teammates that self-organize through a ready queue.
lavra-work-ralph
Autonomous retry mode for bead work -- iterates until completion criteria are met or retry budget is exhausted.
lavra-import
Import a markdown plan into beads as an epic with child tasks.