plan-phase

A planning command for one phase of a technical specification. It designs the architecture first, then maps files, code interfaces, dependencies, and parallel work areas.

In plain words
What is it for?
Use it to plan a named specification phase, including affected files, classes, types, functions, signatures, dependencies, and agent swim lanes.
Why use it?
It gives agents clear code boundaries and prevents the implementation plan from driving the architecture in the wrong direction.

Command for Claude Code

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/consiliency/code-index-mcp/plan-phase
Clone the repo
git clone --depth 1 https://github.com/Consiliency/Code-Index-MCP

Made for: Claude Code.

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 658 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 $0.00028 $0.00658
Opus 5 $0.00014 $0.00329
Sonnet 5 $0.00006 $0.00132
Haiku 4.5 $0.00003 $0.00066

Measured 2d ago against content hash e63884e72ab8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-phase 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.

.claude/commands/plan-phase.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Implementation For a Spec Phase (Architecture-First, Code-Boundary Swim Lanes)

Inputs:

  • $1 = spec file path relative to spec/ (e.g., MASTER_ROADMAP.md, api/ocr-pipeline.md)
  • $2 = phase name or identifier within that spec (e.g., Phase 2 – Ingestion Service)

The goal is to design the best architecture first, then define swim lanes that fit that architecture. Do not alter the design to accommodate swim lanes.


0. Load & Scope

  1. Read the spec file:
    • @spec/$1
  2. Find the phase whose heading/label best matches "$2".
    • Treat this phase as the primary scope.
    • Consider other phases only when explicitly referenced as dependencies.

A. Architectural Baseline & Component Catalog (For Phase $2)

From the requirements of phase $2, define the post-implementation component catalog:

  1. Files

    • Paths to be added, modified, or removed.
    • Reuse existing files when it makes architectural sense.
  2. Classes / Types

    • Names, paths, visibility.
    • Mark each as new or modified.
  3. Functions / Methods

    • Names, paths, signatures:
      • Parameters (names, types, optionality).
      • Return type.
      • Error behavior.
  4. Data Structures

    • DTOs, event payloads, schemas, enums, config.
    • Fields + types, required vs optional, invariants, versioning.

At this stage, do not assign swim lanes. Focus entirely on optimal phase-level architecture.


B. Code-Level Interface Contracts (Freeze Before Lane Work)

Define interfaces that span module or service boundaries for phase $2:

  • Types of interfaces:
    • HTTP/GraphQL/RPC endpoints (routes + handler symbols).
    • Public library APIs (exported functions/methods).
    • Events/queues/topics with payload schemas.
    • DB queries/contracts and schema changes.

For each interface:

  • Specify:
    • Defining file(s) and symbol names.
    • Input/output shapes (types, fields).
    • Error behavior, including failure modes and retry semantics.
    • Invariants and idempotency guarantees where relevant.

Read the full file on GitHub · 87 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 · 87 lines · 0 tokens per session scan A e63884e72ab8

Subscribe to this mod's changes

plan-phase is a command published in the GitHub repository Consiliency/Code-Index-MCP (57 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 658 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.