plan

A planning command that breaks a software task into smaller tasks and records their dependencies. Dependencies show which tasks must finish before others can start.

In plain words
What is it for?
Use it to create a structured plan with task descriptions, task types, dependency relationships, parallel work groups, execution phases, and a dependency graph.
Why use it?
It makes a large task easier to organise and shows which independent tasks can be worked on at the same time. It also places building and testing after the work they depend on.

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/designpipe/exfig/plan
Clone the repo
git clone --depth 1 https://github.com/DesignPipe/exfig

Made for: Claude Code.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,054 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 $0.00012 $0.01054
Opus 5 $0.00006 $0.00527
Sonnet 5 $0.00002 $0.00211
Haiku 4.5 $0.00001 $0.00105

Measured yesterday against content hash 04c89a81a595, 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 · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Planning with Dependencies

Purpose: Analyze a task and break it down into subtasks with explicit dependencies, enabling parallel execution where possible.

Output Format (TOON-like)

Generate plan in this structured format:

command:
  name: plan-<task-slug>
  purpose: <task description>
  version: 1.0

tasks[N]{id,title,description,depends_on,parallel_group,type}:
  <id>,<title>,<description>,[deps],[group],[type]
  ...

execution_order:
  phase_1:
    parallel: [task_ids that can run in parallel]
  phase_2:
    sequential: [task_id] # build/test tasks
  phase_3:
    parallel: [task_ids for fixes if needed]
  ...

dependency_graph:
  <task_id>: [list of task_ids this depends on]
  ...

Task Types

  • analysis - Code analysis, research, reading
  • implementation - Writing new code
  • modification - Changing existing code
  • build - Building project/module
  • test - Running tests
  • fix - Fixing issues found by build/tests
  • review - Code review, validation

Dependency Rules

Critical Rules for Parallel Execution

  1. Independent tasks (no shared files/modules) can run in parallel
  2. Build tasks MUST wait for ALL parallel implementation tasks to complete
  3. Test tasks MUST wait for build to succeed
  4. Fix tasks MUST wait for test results
  5. Tasks modifying same file MUST be sequential

Dependency Detection

  • Same file modification → sequential
  • Same module modification → sequential (unless different files)
  • Different modules → parallel possible
  • Build depends on → all implementation tasks
  • Test depends on → successful build
  • Fix depends on → test results

Instructions

  1. Analyze the task:

    • Read relevant code files mentioned in task
    • Identify affected modules/files
    • Detect potential conflicts
  2. Break down into subtasks:

    • Create atomic, independent subtasks where possible
    • Identify dependencies between subtasks
    • Group parallelizable tasks
  3. Generate execution plan:

Read the full file on GitHub · 145 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. yesterday First seen · 145 lines · 12 tokens per session scan A 04c89a81a595

Subscribe to this mod's changes

plan is a command published in the GitHub repository DesignPipe/exfig (10 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 1,054 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.