implement

A guided workflow for building a requested software feature, from clarifying its behavior and defining data structures to implementing and testing it.

In plain words
What is it for?
Use it to plan and implement features across frontend, backend, database, types, tests, and related project files.
Why use it?
It turns a feature request into an organized development process and helps account for affected files, databases, edge cases, and users.

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/implement
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 995 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 $0.00995
Opus 5 $0.00000 $0.00498
Sonnet 5 $0.00000 $0.00199
Haiku 4.5 $0.00000 $0.00100

Measured 2d ago against content hash 000b1544c239, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement 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/implement.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement Feature

Implement the feature described: $ARGUMENTS

Implementation Process

Phase 0: Portfolio Gate

  1. Check project constraints
    • Read ~/.claude/portfolio/PORTFOLIO.md
    • If Maintenance phase: ONLY bug fixes. Reject feature requests.
    • If Prototype phase: Skip tests, skip types, skip CI.
    • Match complexity to tier. T3/T4 = simplest possible implementation.

Phase 1: Planning (Types First)

  1. Clarify Requirements

    • What is the expected behavior?
    • What are the acceptance criteria?
    • Are there edge cases to consider?
    • Who are the users of this feature?
  2. Identify Scope

    • Which files need to be created/modified?
    • What new types/interfaces are needed?
    • What's the data flow?
    • Are there database changes needed?
  3. Create Type Definitions

    // TypeScript: src/types/[feature].ts
    export interface FeatureName {
      id: string;
      // ... properties
    }
    
    # Python: src/models/[feature].py
    from pydantic import BaseModel
    
    class FeatureName(BaseModel):
        id: str
        # ... fields
    

Phase 2: Implementation (Backend First)

  1. Database Layer (if applicable)

    • Create migrations
    • Add models/schemas
    • Update seed data if needed
  2. Service Layer

    • Implement business logic
    • Use Result pattern for error handling
    • Add logging at key points
  3. API Layer (if applicable)

    • Create endpoints following API patterns
    • Add input validation (Zod/Pydantic)
    • Implement proper error responses

Phase 3: Implementation (Frontend)

  1. Components (if applicable)

    • Create React components
    • Add custom hooks for data fetching
    • Implement state management
  2. Integration

    • Connect frontend to backend
    • Add loading/error states
    • Implement optimistic updates if needed

Phase 4: Testing

  1. Write Tests
    # Unit tests for services
    # Integration tests for API
    # Component tests for UI
    

Read the full file on GitHub · 166 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 · 166 lines · 0 tokens per session scan A 000b1544c239

Subscribe to this mod's changes

implement 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 995 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.