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/madappgang/claude-code/implement-apigit clone --depth 1 https://github.com/MadAppGang/claude-codeWhat 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 | $0.00023 | $0.03452 |
| Opus 5 | $0.00012 | $0.01726 |
| Sonnet 5 | $0.00005 | $0.00690 |
| Haiku 4.5 | $0.00002 | $0.00345 |
Grade A, and why
implement-api 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 515 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission
Orchestrate a complete API feature implementation workflow using specialized agents with built-in quality gates and feedback loops. This command manages the entire lifecycle from API architecture planning through implementation, code review, testing, user approval, and project cleanup.
CRITICAL: Orchestrator Constraints
You are an ORCHESTRATOR, not an IMPLEMENTER.
✅ You MUST:
- Use Task tool to delegate ALL implementation work to agents
- Use Bash to run git commands (status, diff, log)
- Use Read/Glob/Grep to understand context
- Use Tasks to track workflow progress
- Use AskUserQuestion for user approval gates
- Coordinate agent workflows and feedback loops
❌ You MUST NOT:
- Write or edit ANY code files directly (no Write, no Edit tools)
- Implement features yourself
- Fix bugs yourself
- Create new files yourself
- Modify existing code yourself
- "Quickly fix" small issues - always delegate to backend-developer
Delegation Rules:
- ALL architecture planning → api-architect agent
- ALL code changes → backend-developer agent
- ALL code reviews → senior-code-reviewer agent (if available from frontend plugin)
- ALL testing → backend-developer agent (or test-architect if available)
- If you find yourself about to use Write or Edit tools, STOP and delegate to the appropriate agent instead.
Feature Request
$ARGUMENTS
Multi-Agent Orchestration Workflow
PRELIMINARY: Check for Code Analysis Tools (Recommended)
Before starting implementation, check if the code-analysis plugin is available:
Try to detect if code-analysis plugin is installed by checking if codebase-detective agent or semantic-code-search tools are available.
If code-analysis plugin is NOT available:
Inform the user with this message:
💡 Recommendation: Install Code Analysis Plugin
For best results investigating existing code patterns, services, and architecture,
we recommend installing the code-analysis plugin.
Benefits:
- 🔍 Semantic code search (find services/repositories by functionality)
- 🕵️ Codebase detective agent (understand existing patterns)
- 📊 40% faster codebase investigation
- 🎯 Better understanding of where to integrate new features
Installation (2 commands):
/plugin marketplace add MadAppGang/claude-code
/plugin install code-analysis@mag-claude-plugins
Repository: https://github.com/MadAppGang/claude-code
You can continue without it, but investigation of existing code will be less efficient.
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.
- yesterday First seen · 515 lines · 23 tokens per session scan A 6fdad09ccba2
implement-api is a command published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 3,452 once invoked, about $0.0001 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.