plan

A command that writes an implementation plan for a data task and then stops before changing code.

In plain words
What is it for?
Use it to inspect a repository, assign parts of a data task to suitable specialists, document non-goals and verification steps, and create a plan under docs/PLAN-<slug>.md.
Why use it?
It helps clarify scope, responsibilities, dependencies, risks, and checks for success before implementation begins. The plan is saved as a Markdown file for review.

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/luccapinto/agentic-data-kit/plan
Clone the repo
git clone --depth 1 https://github.com/luccapinto/agentic-data-kit

Made for: Claude Code.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 256 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 $0.00019 $0.00256
Opus 5 $0.00010 $0.00128
Sonnet 5 $0.00004 $0.00051
Haiku 4.5 $0.00002 $0.00026

Measured yesterday against content hash ced9c0900801, 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 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.

.claude/commands/plan.md · 26 lines

What it actually says

Workflow: /plan

Usage: /plan <what you want to build>

Produce a written plan before any implementation. This command writes a plan file and stops — it does not write code.

Steps

  1. Understand. Read the relevant parts of the repo. If a key requirement is genuinely ambiguous, ask; otherwise state your assumptions.
  2. Route. Identify which agent(s) own each part of the work (e.g. data-engineer for the pipeline, analytics-engineer for the model, powerbi-developer for the dashboard).
  3. Write the plan to docs/PLAN-<slug>.md, where <slug> is 2–3 hyphenated keywords from the request. Include:
    • Goal & scope (and explicit non-goals).
    • Task breakdown with the responsible agent per task.
    • Dependencies & risks.
    • Verification checklist (how we'll know it works).
  4. Report the exact file path created and suggest reviewing it before implementing.
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. yesterday First seen · 26 lines · 19 tokens per session scan A ced9c0900801

Subscribe to this mod's changes

plan is a command published in the GitHub repository luccapinto/agentic-data-kit (7 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 256 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 2026-08-31.