plan

A planning command that turns an idea or Markdown file into a phased implementation plan saved under the project's plans directory. It examines existing files and skills that can be reused.

In plain words
What is it for?
Use it before building a feature to map the work, identify reusable project parts, split delivery into phases, and document research findings.
Why use it?
It gives later implementation work a grounded scope and records research needed for facts that may change, such as provider or API details.

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/littlebearapps/untether/plan
Clone the repo
git clone --depth 1 https://github.com/littlebearapps/untether

Made for: Claude Code.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,541 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 $0.00010 $0.01541
Opus 5 $0.00005 $0.00771
Sonnet 5 $0.00002 $0.00308
Haiku 4.5 $0.00001 $0.00154

Measured yesterday against content hash aba338c3a237, 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 · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are handling /plan. /plan turns an idea into a grounded, phased plan pack under docs/plans/<slug>/. It is the scope half of delivery — read-only on code, it produces the artefact that /implement later executes one phase at a time.

User input: $ARGUMENTS

Untether adaptations (read first)

Load .claude/rules/workflow-commands.md (routing + cross-cutting rules). For /plan:

  • Authority: writes plan docs only, never code. Runs in plan mode by nature.
  • Reuse, don't duplicate. The blueprint MUST include a reuse map citing existing Untether files/skills to reuse before proposing new code. A plan with no reuse map is incomplete.
  • Research gate. Never plan provider/API-sensitive or current-truth work from memory — route it to the global /research and capture findings under docs/findings/<YYYY-MM-DD>-<slug>.md, then cite them.
  • Date every current-state claim. State-of-the-world facts drift; stamp them.
  • Note on location: docs/plans/ is gitignored — plan packs are local by design (this very plan lives there untracked). /implement reads them locally; only committed code lands in git.

Sub-commands

Form Action
/plan incoming/<file>.md Plan from a captured idea file
/plan #NN Plan from a GitHub issue
/plan <inline idea text> Plan from a one-line idea
/plan <slug> --status Read-only: print an existing pack's phase table + progress
/plan --help Usage, then stop

Flow

P-1. Redirect check (don't plan the wrong thing)

Classify the idea first:

  • A defect / regression → STOP, route to /fix (or /debug to understand). A plan pack is for net-new capability, not bug work.
  • An existing pack (a docs/plans/<slug>/ already covers this) → STOP, don't re-plan; offer --status or route to /implement for the next phase.

P-2. Brainstorm intent (superpowers)

Invoke superpowers:brainstorming via the Skill tool to explore intent, requirements, and design before mapping code. Capture the sharpened problem statement and success criteria.

Read the full file on GitHub · 128 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 · 128 lines · 10 tokens per session scan A aba338c3a237

Subscribe to this mod's changes

plan is a command published in the GitHub repository littlebearapps/untether (66 stars, last pushed 2d ago), licensed MIT. It adds 10 tokens to every session and 1,541 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 2026-08-30.