plan

A command that asks Claude Code to explore a repository and write a read-only implementation plan. The plan describes the work without changing code.

In plain words
What is it for?
Use it to produce plans for coding tasks, optionally saving the plan to a file or running the request in the background.
Why use it?
It helps map an unfamiliar codebase and decide what should change before implementation begins. This is useful when a task spans several parts of a project.

Command

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/tornikegomareli/claude-plugin-codex/plan
Clone the repo
git clone --depth 1 https://github.com/tornikegomareli/claude-plugin-codex
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 413 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 $0.00031 $0.00413
Opus 5 $0.00015 $0.00206
Sonnet 5 $0.00006 $0.00083
Haiku 4.5 $0.00003 $0.00041

Measured 2d ago against content hash 90bbe6970205, 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 2d 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.

plugins/claude/commands/plan.md · 32 lines

What it actually says

Ask Claude Code to produce an implementation plan for the user's task. Claude explores the repository read-only and returns a structured plan; it makes no code changes.

Raw slash-command arguments: $ARGUMENTS

Locating the companion script:

  • The companion script is scripts/claude-companion.mjs inside this plugin's root directory (the installed claude plugin directory that contains .codex-plugin/plugin.json).
  • Always invoke it with an absolute path.

Execution mode rules:

  • If the raw arguments include --wait, run in the foreground without asking.
  • If the raw arguments include --background, run with --background without asking.
  • Otherwise: for a short, single-subsystem task, run in the foreground. If the task names multiple subsystems or sounds open-ended, ask the user exactly once, in plain conversation, with "Run in background (Recommended)" first and "Wait for results" second.

Flow:

  • Run:
node "<plugin-root>/scripts/claude-companion.mjs" plan "$ARGUMENTS"
  • Return the plan output verbatim, exactly as-is, including the closing hint about @claude implement.
  • Do not start implementing the plan yourself.
  • For background runs, tell the user: "Claude is drafting the plan in the background. Check @claude status for progress and @claude result for the plan."

Sandbox requirements:

  • The companion spawns the claude CLI, which needs network access to reach the Anthropic API.
  • If the sandbox blocks the command or Claude reports a connection error, rerun the same shell command with escalated permissions and explain why in the justification.
  • Do not work around a sandbox denial by improvising your own review or edits; the command's value is Claude's independent output.
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. 2d ago First seen · 32 lines · 31 tokens per session scan A 90bbe6970205

Subscribe to this mod's changes

plan is a command published in the GitHub repository tornikegomareli/claude-plugin-codex (9 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 413 once invoked, about $0.0002 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.