bottega: Command for Claude Code

.claude/commands/planification.md

planification is a command for Claude Code from vdaubry/bottega. It costs 20 tokens per session (1,272 once invoked), scanned B, original, MIT.

A planning command that turns a request into a structured Markdown implementation plan saved at a predictable path. It may research or ask questions, but it is restricted to writing that one plan file and does not implement code.

In plain words
What is it for?
Capturing the original request, researching its requirements and writing a plan for the current Git branch or worktree.
Why use it?
It gives later coding work a fixed, reviewable set of steps while preventing the planning stage from changing source code or configuration.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents; names the TodoWrite tool.

This is vdaubry/bottega's own configuration. It tells Claude Code how to work on bottega itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bottega configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vdaubry/bottega. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vdaubry/bottega/main/.claude/commands/planification.md
Clone the repo
git clone --depth 1 https://github.com/vdaubry/bottega

Made for: Claude Code.

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 planification

README.md
[![agentmods](https://agentmods.dev/badge/commands/vdaubry/bottega/planification/github.svg)](https://agentmods.dev/commands/vdaubry/bottega/planification)
Your own site
<a href="https://agentmods.dev/commands/vdaubry/bottega/planification"><img src="https://agentmods.dev/badge/commands/vdaubry/bottega/planification/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for planification

Your own site · 80×15
<a href="https://agentmods.dev/commands/vdaubry/bottega/planification"><img src="https://agentmods.dev/badge/commands/vdaubry/bottega/planification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,272 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00020 $0.01272
Opus 5.5 $0.00008 $0.00509
Sonnet 5.5 $0.00004 $0.00254
Haiku 4.5 $0.00002 $0.00127

Measured 24d ago against content hash d36f7d97b242, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

planification scanned grade B with 1 finding 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 24d 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- Explicit instruction: "Do NOT write any files, run any scripts, or ask user questions. Only explore
.claude/commands/planification.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a planning agent. You MUST NOT implement code, modify configuration, or touch any file other than the single plan file described below. Do not use Edit, Write, or TodoWrite for anything else. Your ONLY outputs are: spawning research sub-agents (Task), asking clarifying questions (AskUserQuestion), and writing the plan file (Write — to the plan file only).

Primary Goal

Produce a planning document (markdown only — no code, no config, no other files) that follows the project's plan template exactly, and write it to the deterministic plan path for this worktree.

Step 0: Resolve the plan path and capture the original request

  1. Compute the plan path (one plan per worktree/task — deterministic):

    leaf="$(git branch --show-current 2>/dev/null | sed 's#.*/##')"
    [ -z "$leaf" ] && leaf="plan"
    mkdir -p tmp/plans
    echo "tmp/plans/${leaf}.md"
    

    The printed path is your plan file. Use it everywhere <plan-path> appears below.

  2. Capture the Original Request — verbatim. The original request is whatever the user passed as arguments to this command ($ARGUMENTS) and/or what they asked for in this conversation. Preserve their exact wording — do not paraphrase, summarize, or omit any part of it.

    • If a plan file already exists at <plan-path> (you are re-planning the same task), read it first and reuse its existing ## Original Request section verbatim instead of re-deriving it.
  3. Read the plan template in full before doing anything else: reference/server/constants/templates/plan-template.md Your output must follow this template's structure section-for-section, in the same order, with no sections removed.

Planning Workflow

You spawn a research sub-agent to explore the codebase; then YOU (the master agent) handle clarification and write the plan. Only you write the plan file. Sub-agents are for research only.

Step 1: Explore (sub-agent)

Spawn a planning sub-agent (Task tool, subagent_type=Plan) to explore the codebase. Its ONLY job is research — it must NOT write files, run scripts, or ask user questions.

Read the full file on GitHub · 114 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. 24d ago First seen · 114 lines · 20 tokens per session scan B d36f7d97b242

Subscribe to this mod's changes

planification is a command published in the GitHub repository vdaubry/bottega (88 stars, last pushed 24d ago), licensed MIT. It adds 20 tokens to every session and 1,272 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-06.