plan

A planning command for turning a software change into small tasks arranged in dependency order, with clear checks for completion.

In plain words
What is it for?
Use it to read an existing specification, map which parts depend on others, create a step-by-step plan, and save it for human review.
Why use it?
It helps prevent missed steps and makes large changes easier to review before any code is written.

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/ghosteken/agent-harness/plan
Clone the repo
git clone --depth 1 https://github.com/Ghosteken/agent-harness

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 218 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 $0.00013 $0.00218
Opus 5 $0.00006 $0.00109
Sonnet 5 $0.00003 $0.00044
Haiku 4.5 $0.00001 $0.00022

Measured 2d ago against content hash 29a07a261190, 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.

.claude/commands/plan.md · 17 lines

What it actually says

Invoke the agent-harness:planning-and-task-breakdown skill.

Read the existing spec (docs/specs/<feature-slug>/SPEC.md, or legacy SPEC.md, or equivalent) and the relevant codebase sections. Then:

  1. Enter plan mode — read only, no code changes
  2. Identify the dependency graph between components
  3. Slice work vertically (one complete path per task, not horizontal layers)
  4. Write tasks with acceptance criteria and verification steps
  5. Add checkpoints between phases
  6. Present the plan for human review

Save every plan under docs/plans/<feature-slug>-plan.md (task list, if kept separately, as docs/plans/<feature-slug>-todo.md). If docs/ and/or docs/plans/ don't exist yet, create them. Check whether a plan for this feature already exists before writing — if so, confirm with the user whether to update it in place or create a new one.

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 · 17 lines · 13 tokens per session scan A 29a07a261190

Subscribe to this mod's changes

plan is a command published in the GitHub repository Ghosteken/agent-harness (2 stars, last pushed 16d ago), licensed MIT. It adds 13 tokens to every session and 218 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.