plan

An architecture-planning command for designing a feature or system change without implementing it.

In plain words
What is it for?
Use it at project kickoff or before a major feature when you need an implementation sequence and architecture assessment.
Why use it?
It creates a technical plan that accounts for the existing codebase, affected components, interfaces, data changes, decisions, risks, and complexity.

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/zevtos/agentpipe/plan
Clone the repo
git clone --depth 1 https://github.com/zevtos/agentpipe
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 491 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 $0.00026 $0.00491
Opus 5 $0.00013 $0.00246
Sonnet 5 $0.00005 $0.00098
Haiku 4.5 $0.00003 $0.00049

Measured 2d ago against content hash dd11d9a73372, 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.

commands/plan.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are creating an architecture plan. This is the PLANNING ONLY command — it does NOT implement anything. Use /feature if you want end-to-end development including implementation.

Context

@CLAUDE.md

What to Plan

$ARGUMENTS

Pipeline

Step 1: Design (Architect Agent) — MANDATORY

You MUST use the Agent tool with subagent_type: "architect" to run the architect agent. Do NOT skip this step. Do NOT substitute it with an Explore agent or your own analysis. The architect agent has specialized capabilities for system design.

Prompt for the architect agent: "Plan the implementation of: $ARGUMENTS

Analyze the current codebase thoroughly, then produce:

  1. Current architecture assessment — what exists, what patterns are used
  2. Component diagram showing affected modules
  3. API contract changes (if any endpoints change)
  4. Data model changes (if schema changes needed)
  5. Implementation steps in dependency order
  6. ADR for any significant technical decisions
  7. Risk assessment with mitigations
  8. Estimated complexity: SMALL (1-2 files) / MEDIUM (3-5 files) / LARGE (5+ files)"

IMPORTANT: Wait for the architect agent to complete before proceeding. Use its output as the foundation for the plan.

Step 2: Breakout

Break the plan into atomic, committable units:

  • Each unit should be independently deployable if possible
  • Each unit maps to one conventional commit
  • Dependencies between units are explicit

Step 3: Present

## Implementation Plan: $ARGUMENTS

### Architecture Changes
[Diagram and description]

### Implementation Steps
1. [step] — `commit type: description`
2. [step] — `commit type: description`
...

### ADRs
[Any architecture decisions]

### Risks
[What could go wrong]

### Recommendation
- Complexity: [SMALL | MEDIUM | LARGE]
- Suggested approach: [implement directly | use /feature for full pipeline | break into sub-tasks]

Ask: "Plan ready. Want me to implement it? I can use /feature for the full pipeline or start implementing directly."

Read the full file on GitHub · 65 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 · 65 lines · 26 tokens per session scan A dd11d9a73372

Subscribe to this mod's changes

plan is a command published in the GitHub repository zevtos/agentpipe (11 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 491 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.