ace:plan-phase

A command that creates a PLAN.md file for a selected project phase. It reads the project's roadmap, requirements, current state, configuration, and optional codebase notes before defining the work.

In plain words
What is it for?
Use it to plan a numbered roadmap phase, assign up to three tasks to ALPHA, BETA, or GAMMA zones, and account for dependencies and deferred issues.
Why use it?
It turns a phase goal into a small, ordered plan while respecting the project's execution zones and existing issues.

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/agricidaniel/ace-claude-code/plan-phase
Clone the repo
git clone --depth 1 https://github.com/AgriciDaniel/ace-claude-code
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,012 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 $0.00011 $0.01012
Opus 5 $0.00005 $0.00506
Sonnet 5 $0.00002 $0.00202
Haiku 4.5 $0.00001 $0.00101

Measured 2d ago against content hash 290fdacb418d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ace:plan-phase 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.

.ace/commands/plan-phase.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Each task is assigned to a zone (ALPHA/BETA/GAMMA) for parallel execution.

Required: @.ace/planning/STATE.md @.ace/planning/PROJECT.md @.ace/planning/ROADMAP.md

Load: @.ace/config.json (for project type) @.ace/project-types.json (for zone definitions)

Optional: @.ace/planning/codebase/ (if exists) @.ace/planning/ISSUES.md (for deferred items to address)

Template: @.ace/templates/planning/plan.md

1. Validate Phase Number

if $ARGUMENTS is empty:
    Error: "Specify phase number: /ace:plan-phase 1"

if phase $ARGUMENTS not in ROADMAP.md:
    Error: "Phase $ARGUMENTS not found in ROADMAP.md"

2. Load Context

Read and understand:

  • Current phase goal from ROADMAP.md
  • Project requirements from PROJECT.md
  • Current state from STATE.md
  • Project type and zone definitions
  • Any open issues to potentially address

3. Determine Plan Number

count existing plans in .ace/planning/phases/{phase}/
next_plan = count + 1
plan_id = "{phase:02d}-{next_plan:02d}"

4. Design Tasks

Create maximum 3 tasks based on:

  • Phase goal
  • Zone ownership (project-types.json)
  • Dependencies between tasks

Each task must:

  • Be assigned to exactly one zone
  • Have clear file scope
  • Be independently committable
  • Have verification criteria

5. Display Visual Plan

+==============================================================+
|                    ACE PLAN                             |
+==============================================================+
|  Phase: [X] - [Phase Name]                                   |
|  Plan: [Y] of [estimated]                                    |
+==============================================================+

              "[Phase Goal]"
                    |
    +---------------+---------------+
    |               |               |
    v               v               v
+--------+     +--------+     +--------+
| ALPHA  |     |  BETA  |     | GAMMA  |
+--------+     +--------+     +--------+
| Task 1 |     | Task 2 |     | Task 3 |
| [desc] |     | [desc] |     | [desc] |
+--------+     +--------+     +--------+
| Files: |     | Files: |     | Files: |
| - x.ts |     | - y.ts |     | - z.ts |
+--------+     +--------+     +--------+

+==============================================================+
|  Execution: PARALLEL (3 Team Leads)                          |
|  Estimated commits: 4 (3 tasks + 1 docs)                     |
+==============================================================+

Read the full file on GitHub · 168 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. 2d ago First seen · 168 lines · 11 tokens per session scan A 290fdacb418d

Subscribe to this mod's changes

ace:plan-phase is a command published in the GitHub repository AgriciDaniel/ace-claude-code (24 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 1,012 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.