impl-plan

impl-plan is a command for Claude Code from MarioEpkOne/PipelineIQ. It costs 0 tokens per session (3,300 once invoked), scanned A, original, MIT.

A planning command that reads a specification, studies the relevant codebase, creates a separate worktree, and writes an implementation plan. A worktree is an isolated working copy of a repository; this command does not implement the plan.

In plain words
What is it for?
Use it when you need an implementation plan for a named specification. The plan is handed off manually to a later implementation session.
Why use it?
It turns a written requirement into a self-contained set of coding steps while keeping the current code unchanged. It also flags when the live code differs from the specification.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions CLAUDE.md.

Part of the pipelineiq plugin — 10 commands, 6 agents shipped together

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/marioepkone/pipelineiq/impl-plan
Clone the repo
git clone --depth 1 https://github.com/MarioEpkOne/PipelineIQ

Made for: Claude Code.

Or install pipelineiq, the plugin that ships this one along with the rest of its 10 commands, 6 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for impl-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/marioepkone/pipelineiq/impl-plan.svg)](https://agentmods.dev/commands/marioepkone/pipelineiq/impl-plan)
Your own site
<a href="https://agentmods.dev/commands/marioepkone/pipelineiq/impl-plan"><img src="https://agentmods.dev/badge/commands/marioepkone/pipelineiq/impl-plan.svg" alt="Measured on agentmods" height="20"></a>
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 3,300 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 5.1 $0.00000 $0.03300
Opus 5 $0.00000 $0.01650
Sonnet 5 $0.00000 $0.00660
Haiku 4.5 $0.00000 $0.00330

Measured 5d ago against content hash b05991f4cab9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

impl-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 5d 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/impl-plan.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PLAN ONLY — reads a spec, orients in the codebase, creates a worktree, and writes a self-contained implementation plan. Manual handoff: you open a new session and run /impl yourself.

The user's request is: $ARGUMENTS

Constraints

Do not modify any codebase files during this skill. Your only written output is the implementation plan document (and the worktree creation via EnterWorktree).

Process

Phase 1 — Find the Spec

Search the specs/ directory for a file whose name contains the argument (case-insensitive match on the description slug).

  • If multiple matches: list them and ask the user to pick one.
  • If no match: tell the user to run /spec first and exit.
  • If no argument was provided: list all specs in specs/ and ask the user which one to plan.

Read the full spec document.

Phase 2 — Orient in the Codebase

From the spec's Technical Design section, extract every file that will change.

Read every file in that list fully before writing anything.

If the live state diverges from the spec's Current State section (e.g., a method was renamed, a file was deleted, a component is missing), flag the divergence explicitly and ask the user how to proceed before continuing.

Phase 3 — Write the Implementation Plan

Before writing the file, run date '+%Y-%m-%d--%H-%M' in the project root to get the actual current timestamp. Save the plan to Implementation Plans/impl--YYYY-MM-DD--HH-MM--<description>.md in the main project directory (replacing YYYY-MM-DD--HH-MM with the output of that command). This is written before entering the worktree so the plan is visible from the main project and can be found by /impl without switching directories.

The plan must be self-contained — the implementing agent reads only the files listed in the reading list and executes only what is written in the steps. No free exploration.

Worktree path must match reality: The **Worktree**: line in the plan header must point to a worktree that actually exists on disk when the implementing agent runs it. Complete Phase 4 (EnterWorktree) successfully before saving the final plan. If EnterWorktree fails, omit the Worktree line and document the failure — do not write a path that doesn't exist. An implementing agent that reads a declared-but-missing worktree path will waste turns trying to find it.

Read the full file on GitHub · 190 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. 5d ago First seen · 190 lines · 0 tokens per session scan A b05991f4cab9

Subscribe to this mod's changes

impl-plan is a command published in the GitHub repository MarioEpkOne/PipelineIQ (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,300 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 2026-08-31.