plan

A command that turns a coding task into a phased implementation plan with specific, checkable success criteria.

In plain words
What is it for?
Use it to create plans with file lists and verification checks that other commands can execute and review.
Why use it?
It makes the work and its expected results explicit before coding starts.

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/keez97/phase-gate/plan
Clone the repo
git clone --depth 1 https://github.com/keez97/phase-gate
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,976 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 $0.00018 $0.01976
Opus 5 $0.00009 $0.00988
Sonnet 5 $0.00004 $0.00395
Haiku 4.5 $0.00002 $0.00198

Measured yesterday against content hash 786af836e7b0, 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.

commands/plan.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/plan — Planning Phase

Produces a phased implementation plan with file manifests and a verification.jsonl row per success criterion. The output is consumable by /implement (which executes phases and runs the phase-end verification gate) and /validate (which re-checks the gate post-hoc).

Step 1: Read Context

Read, in order:

  1. The project's own conventions doc(s) at the repo root (README.md, CLAUDE.md, CONTRIBUTING.md, an architecture decision log — whichever exist).
  2. Any existing plan(s) in plans/active/ — open work that may overlap.
  3. The most recent archived plan in plans/archive/ if you need precedent for structure.

Do not re-litigate decisions already settled in conventions or earlier plans. If a prior plan archived in the last 30 days touched the same surface, name it explicitly in the new plan's Dependencies section.

Step 2: Structure the Plan

Save to: plans/active/YYYY-MM-DD-<task-slug>.md.

Required sections:

---
status: draft
date: YYYY-MM-DD
---

# <Plan title>

## Objective

One paragraph. What changes for the project after this plan ships.

## Success Criteria

- [ ] Criterion 1 (one binary, falsifiable bullet — see § Quality Bar)
- [ ] Criterion 2
- [ ] ...

## Phases

### Phase 1 — <name>

<one-paragraph framing>

#### Files
- `path/to/existing.sh` (edit — one-line description of change)
- `path/to/new.sh` (new — one-line description of purpose)

#### Files (conditional) <!-- optional -->
- `path/to/maybe.md` (edit if <trigger condition>)

#### Success Criteria
- [ ] Phase-scoped criterion 1
- [ ] Phase-scoped criterion 2

### Phase 2 — <name>
...

## Dependencies

External or upstream prerequisites. Other plans this builds on.

## Open Questions

- Q1: ...

## Out of Scope

- ...

When saving a new plan, move any plan with status: complete from active/ to archive/YYYY-MM/ first.

Step 2.5: Phase File Manifests (Mandatory)

Every phase that touches files must enumerate them. This is load-bearing: the implementer agent (agents/implementer.md) is spawned with the phase's file manifest as its scoping boundary. A phase without a manifest cannot be delegated safely.

Read the full file on GitHub · 201 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 · 201 lines · 18 tokens per session scan A 786af836e7b0

Subscribe to this mod's changes

plan is a command published in the GitHub repository keez97/phase-gate (1 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 1,976 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.