plan-to-file

plan-to-file is a command for Claude Code from alexander-akhmetov/programmator. It costs 22 tokens per session (524 once invoked), scanned A, original, MIT.

A command that converts the current Claude Code plan into a plan file for Programmator, a separate planning tool. It turns plan sections into actionable checklist tasks and includes relevant test, lint, and build commands when found.

In plain words
What is it for?
Use it after creating a Claude Code plan when you need a Programmator-compatible task list with a title, implementation steps, and validation commands.
Why use it?
It saves time when the same implementation plan must be used in both tools. It also helps carry validation steps from the project instructions into the new plan.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

Part of the programmator plugin — 1 skill, 2 commands shipped together

Good fit Use it after creating a Claude Code plan when you need a Programmator-compatible task list with a title, implementation steps, and validation commands.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/alexander-akhmetov/programmator/plan-to-file
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.

Clone the repo
git clone --depth 1 https://github.com/alexander-akhmetov/programmator

Made for: Claude Code.

Or install programmator, the plugin that ships this one along with the rest of its 1 skill, 2 commands.

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 plan-to-file

README.md
[![agentmods](https://agentmods.dev/badge/commands/alexander-akhmetov/programmator/plan-to-file.svg)](https://agentmods.dev/commands/alexander-akhmetov/programmator/plan-to-file)
Your own site
<a href="https://agentmods.dev/commands/alexander-akhmetov/programmator/plan-to-file"><img src="https://agentmods.dev/badge/commands/alexander-akhmetov/programmator/plan-to-file.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 524 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00022 $0.00524
Opus 5 $0.00011 $0.00262
Sonnet 5 $0.00004 $0.00105
Haiku 4.5 $0.00002 $0.00052

Measured 7d ago against content hash adadaa5bf1e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

plan-to-file 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 7d 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-to-file.md · 52 lines

What it actually says

Plan to File

Converts a Claude Code plan file into a programmator-compatible plan file.

Instructions

  1. Find the most recent plan file:

    ls -lt ~/.claude/plans/*.md | head -1
    
  2. Read the plan content

  3. Extract title: Get the title from the plan's first # heading. Strip any "Plan:" prefix if already present.

  4. Extract tasks from the plan: Analyze the plan structure and identify the logical steps. Rules:

    • Each major implementation step/section becomes a task
    • Task format: - [ ] Task N: Name - brief actionable description
    • Keep task count proportional to plan complexity
    • Task names must be actionable (what to do, not just a label)
    • If the plan already has checkbox tasks, reuse them as-is
  5. Detect validation commands: Read CLAUDE.md in the current project root (and any CLAUDE.md files it references) to find test, lint, and build commands. Look for sections like "Build and Test Commands", "Testing", "Linting", etc. Extract the relevant commands (e.g., go test ./..., make lint). If CLAUDE.md doesn't exist or has no such commands, fall back to scanning the plan text for mentions of test/lint/build commands. If nothing is found, omit the validation section.

  6. Build the plan file with this structure:

    # Plan: <title>
    
    ## Validation Commands
    - `<command 1>`
    - `<command 2>`
    
    ## Tasks
    - [ ] Task 1: Name - description
    - [ ] Task 2: Name - description
    ...
    
  7. Check output path: If ./plan.md already exists in the current directory, ask the user what filename to use. Otherwise default to ./plan.md.

  8. Write the file to the chosen path.

  9. Report: Show the written filename, the extracted title, task count, and any validation commands found. Mention that the user can now run programmator start ./plan.md to execute it.

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. 7d ago First seen · 52 lines · 22 tokens per session scan A adadaa5bf1e0

Subscribe to this mod's changes

plan-to-file is a command published in the GitHub repository alexander-akhmetov/programmator (2 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 524 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.