smart-plan

A command that creates a detailed plan for implementing a software project or feature. It covers requirements, stakeholders, existing code, design choices, security, performance, and delivery steps.

In plain words
What is it for?
Use it to plan a new feature or project, define acceptance criteria, inspect related code, compare implementation options, and map out the work.
Why use it?
It helps turn a broad request into an ordered set of decisions and tasks before coding begins. It also checks project constraints and existing patterns so the plan fits the codebase.

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/intellegix/intellegix-code-agent-toolkit/smart-plan
Clone the repo
git clone --depth 1 https://github.com/intellegix/intellegix-code-agent-toolkit
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 838 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00000 $0.00838
Opus 5 $0.00000 $0.00419
Sonnet 5 $0.00000 $0.00168
Haiku 4.5 $0.00000 $0.00084

Measured 2d ago against content hash 45b2f89972a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

smart-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.

commands/smart-plan.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Smart Plan - Multi-Phase Project Planning

Create a comprehensive implementation plan for: $ARGUMENTS

Planning Process

Phase 0: Portfolio Context

  1. Check portfolio constraints
    • Read ~/.claude/portfolio/PORTFOLIO.md
    • What tier and phase is this project?
    • Does this plan respect the phase restrictions and anti-patterns?
    • Is the complexity appropriate for the user count?
    • If adding enterprise patterns to a <10 user app, STOP and simplify.

Phase 1: Requirements Analysis

  1. Clarify scope

    • What is the expected outcome?
    • What are the acceptance criteria?
    • Are there constraints (time, technology, budget)?
  2. Identify stakeholders

    • Who will use this feature?
    • Who needs to approve/review?
    • Are there external dependencies?

Phase 2: Research & Context

  1. Explore the codebase

    • Find related existing implementations
    • Identify patterns to follow
    • Note any technical debt or constraints
  2. Research best practices (if needed)

    • Industry standards for this type of feature
    • Security considerations
    • Performance implications

Phase 3: Architecture Design

  1. Design the solution

    • High-level architecture
    • Data flow diagrams
    • API contracts (if applicable)
    • Database schema changes (if applicable)
  2. Create ADR (Architecture Decision Record)

    # ADR-[NUMBER]: [Title]
    
    ## Status
    Proposed
    
    ## Context
    [Why is this decision needed?]
    
    ## Decision
    [What is the decision?]
    
    ## Consequences
    [What are the positive and negative impacts?]
    
    ## Alternatives Considered
    [What other options were evaluated?]
    

Phase 4: Task Breakdown

  1. Create implementation tasks
    • Order by dependency (what must come first)
    • Estimate complexity (S/M/L)
    • Identify parallelizable work

Output Format

# Implementation Plan: [Feature Name]

## Overview
[1-2 paragraph summary of what will be built]

## Requirements
### Functional Requirements
- [ ] FR-1: [Requirement]
- [ ] FR-2: [Requirement]

### Non-Functional Requirements
- [ ] NFR-1: [Performance/Security/Accessibility requirement]

## Architecture

### High-Level Design
[Describe the architecture]

### Data Model Changes
```sql
-- Schema changes if applicable

API Changes

POST /api/v1/resource
Request: { ... }
Response: { ... }

Implementation Tasks

Phase 1: Foundation (Prerequisites)

Task Complexity Dependencies Files
Task 1 S None path/to/file.ts

Phase 2: Core Implementation

Task Complexity Dependencies Files
Task 2 M Task 1 path/to/file.ts

Phase 3: Testing & Polish

Task Complexity Dependencies Files
Add tests M Phase 2 tests/

Risk Assessment

Risk Likelihood Impact Mitigation
Risk 1 Medium High How to mitigate

Testing Strategy

  • Unit tests: [What to test]
  • Integration tests: [What to test]
  • Manual testing: [Scenarios to verify]

Rollout Plan

  1. [Step 1]
  2. [Step 2]

Success Metrics

  • [How will we know this is successful?]

Read the full file on GitHub · 143 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 · 143 lines · 0 tokens per session scan A 45b2f89972a1

Subscribe to this mod's changes

smart-plan is a command published in the GitHub repository intellegix/intellegix-code-agent-toolkit (57 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 838 tokens. 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.