What is ace:execute-plan?

A command for carrying out the tasks in the current PLAN.md, using parallel team leads. It reads project state and configuration to decide how the work should proceed.

It helps execute planned tasks, split independent work across team leads, pause for verification or decisions, and continue from the saved project state.

It turns an approved plan into organized implementation work while supporting checkpoints, task-level commits, and different levels of user interaction.

ace:execute-plan — Command by AgriciDaniel

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/execute-plan

Clone the repo

git clone --depth 1 https://github.com/AgriciDaniel/ace-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 3,187 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.

Model	Per session	Once invoked
Fable 5	$0.00013	$0.03187
Opus 5	$0.00006	$0.01594
Sonnet 5	$0.00003	$0.00637
Haiku 4.5	$0.00001	$0.00319

Measured 2d ago against content hash 96e5ffd6dea4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ace:execute-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.

.ace/commands/execute-plan.md · 508 lines

How it starts

The opening of the file, as written. The whole thing — 508 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This is Ace's core execution engine combining:

Planckatron's parallel 3-tier hierarchy
GSD's per-task atomic commits and context management

Required: @.ace/planning/STATE.md @.ace/config.json @.ace/project-types.json

Load plan: If $ARGUMENTS provided: Use that path Else: Read STATE.md for current plan path

Templates: @.ace/templates/planning/summary.md

<execution_strategies>

Workflow Mode (from config.json)

Read config.json for workflow.mode

if workflow.mode == "yolo":
    - Skip plan approval confirmation
    - Auto-proceed at checkpoints
    - Only stop on errors or architectural decisions
    - Faster execution, less interruption

if workflow.mode == "interactive" (default):
    - Show plan before execution
    - Pause at checkpoints for user confirmation
    - Standard behavior with user approvals

Strategy A: Fully Autonomous (No Checkpoints)

Plan has no VERIFY or DECISION checkpoints
Spawn all Team Leads in single message
Each Team Lead commits independently
Main context: orchestration only (~5% usage)

Strategy B: Segmented (Has Verify Checkpoints)

Execute in segments between checkpoints
Spawn Team Leads for each segment
Pause at VERIFY for user confirmation (skip in YOLO mode)
Continue after verification

Strategy C: Decision-Dependent (Has Decision Checkpoints)

Execute in main context (no subagents)
Decision outcomes affect subsequent tasks
Quality maintained through small scope (max 3 tasks)
In YOLO mode: use first/recommended option automatically

</execution_strategies>

1. Pre-Flight Checks

if .ace/planning/ does not exist:
    Error: "Run /ace:new-project first"

if PLAN.md not found:
    Error: "No plan to execute. Run /ace:plan-phase [N]"

if SUMMARY.md already exists for this plan:
    Ask: "Plan already executed. Re-run?"

Read the full file on GitHub · 508 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.

2d ago First seen · 508 lines · 13 tokens per session scan A 96e5ffd6dea4

Subscribe to this mod's changes

ace:execute-plan is a command published in the GitHub repository AgriciDaniel/ace-claude-code (24 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 3,187 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.

Planning ai claude-code claude-code-skill developer-tools open-source

ace:execute-plan

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Workflow Mode (from config.json)

Strategy A: Fully Autonomous (No Checkpoints)

Strategy B: Segmented (Has Verify Checkpoints)

Strategy C: Decision-Dependent (Has Decision Checkpoints)

1. Pre-Flight Checks

What this file has done since we first saw it

Other commands, from other repositories

canvas

document

review

test

fix-issue

migrate