plan

A planning command for larger code changes, using the project's own plan template and completion checklist.

In plain words
What is it for?
Use it before changes over 20 lines or changes to planned parts of the codebase.
Why use it?
It turns a broad request into agreed steps, affected files, and checks, reducing missed edge cases and unfinished work.

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/whieet/harness-kit/plan
Clone the repo
git clone --depth 1 https://github.com/whieet/harness-kit
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 387 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 $0.00060 $0.00387
Opus 5 $0.00030 $0.00193
Sonnet 5 $0.00012 $0.00077
Haiku 4.5 $0.00006 $0.00039

Measured 2d ago against content hash 50b486e3748c, 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.

commands/plan.md · 24 lines

What it actually says

/harness-kit:plan

Drive a disciplined plan for the requested change.

Steps

  1. Read .harness/config.json first and follow its language preference for AI interaction and generated plan content. Do not translate file/directory names, command names, or config keys.

  2. Read the project plan template (<plan.dir>/_template.md, where plan.dir comes from .harness/config.json) so your plan matches the project's expected structure and Definition-of-Done format.

  3. Investigate enough to plan well: search for existing utilities/patterns to reuse, identify the files to change, and consider edge cases (empty/error states, performance, regressions).

  4. Enter plan mode and present a plan with: Context (why), the approach, the affected files, step-by-step actions with their verification method, and a Definition of Done whose items are checkable.

  5. On approval, the on-plan-approved hook automatically writes the plan into <plan.dir>/active/. As you implement, check off the DoD items — the Stop-hook gate verifies them before you can finish, and harness-check-plan-dod reminds you to archive the plan to completed/ when done.

Notes

  • For changes ≤ ~20 lines with no interface change, a full plan is optional — but still run /harness-kit:verify before declaring done.
  • If you edit planned code (plan.codeGlob) with no covering plan, the plan-gate hook auto-scaffolds one for you to fill in.
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 · 24 lines · 60 tokens per session scan A 50b486e3748c

Subscribe to this mod's changes

plan is a command published in the GitHub repository whieet/harness-kit (5 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 387 once invoked, about $0.0003 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.