execute

execute is a command for coding agents from KaimingWan/oh-my-kiro. It costs 0 tokens per session (532 once invoked), scanned A, original, MIT.

A command that runs an already approved coding plan through a checklist until all listed tasks are complete. Ralph Loop is a repeated shell process that continues the work even if the agent stops between steps.

In plain words
What is it for?
Use it to carry out approved plans, find the correct plan file, prepare an isolated work directory when needed, and verify each checklist item.
Why use it?
It removes the need to manually restart plan execution or track unfinished checklist items.

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/kaimingwan/oh-my-kiro/execute
Clone the repo
git clone --depth 1 https://github.com/KaimingWan/oh-my-kiro

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for execute

README.md
[![agentmods](https://agentmods.dev/badge/commands/kaimingwan/oh-my-kiro/execute.svg)](https://agentmods.dev/commands/kaimingwan/oh-my-kiro/execute)
Your own site
<a href="https://agentmods.dev/commands/kaimingwan/oh-my-kiro/execute"><img src="https://agentmods.dev/badge/commands/kaimingwan/oh-my-kiro/execute.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 532 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 $0.00000 $0.00532
Opus 5 $0.00000 $0.00266
Sonnet 5 $0.00000 $0.00106
Haiku 4.5 $0.00000 $0.00053

Measured 5d ago against content hash 5c8c0cfd4291, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

execute 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 5d 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/execute.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execute an approved plan with Ralph Loop hard constraint. Agent stops don't matter — bash loop keeps going until all checklist items are done.

Step 1: Load Plan

Resolve which plan to execute:

  1. Read docs/plans/.active — if it exists, use that path
  2. If not found, find the most recently modified docs/plans/*.md and write it to docs/plans/.active
  3. If multiple plans modified within the last hour, list them and ask the user to pick

Verify the plan has reviewer APPROVE verdict. If not approved, tell the user to run @plan first.

Step 1b: Detect Work Dir

Check if the plan header contains **Work Dir:**:

WORK_DIR=$(grep -oE '^\*\*Work Dir:\*\*\s*.+' "$PLAN_FILE" | sed 's/^\*\*Work Dir:\*\*\s*//' | tr -d '[:space:]')

If Work Dir is set:

  1. Resolve to absolute path relative to project root
  2. If path doesn't exist, create worktree (infer submodule and branch from plan slug)
  3. Launch ralph loop with isolation env vars:
PLAN_POINTER_OVERRIDE=<plan_file_path> RALPH_WORK_DIR=<work_dir_abs> python3 scripts/ralph_loop.py

If Work Dir is absent, proceed normally (backward compatible).

Step 2: Verify Checklist

The plan MUST contain a ## Checklist section with at least one - [ ] item. If missing, STOP and tell the user the plan needs a checklist.

Step 3: Launch Ralph Loop

Run foreground (NEVER use nohup & — you need to see the exit summary):

python3 scripts/ralph_loop.py

This bash script will:

  • Loop until all - [ ] items become - [x]
  • Each iteration spawns a fresh Kiro CLI instance with clean context
  • Circuit breaker: exits if 3 consecutive rounds make no progress
  • Agent stopping is fine — the loop restarts a new instance
  • On exit (success or failure), prints a full summary to stdout

Step 4: Report Results

The script prints a summary block on exit. Use that output to report:

  • How many checklist items completed vs total
  • Any - [SKIP] items with reasons
  • Read skills/omk-finishing/SKILL.md for merge/PR/cleanup options

Read the full file on GitHub · 53 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. 5d ago First seen · 53 lines · 0 tokens per session scan A 5c8c0cfd4291

Subscribe to this mod's changes

execute is a command published in the GitHub repository KaimingWan/oh-my-kiro (103 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 532 tokens. 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.