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.
npx agentmods add commands/kaimingwan/oh-my-kiro/executegit clone --depth 1 https://github.com/KaimingWan/oh-my-kiroWrote 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.
[](https://agentmods.dev/commands/kaimingwan/oh-my-kiro/execute)<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>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 | $0.00000 | $0.00532 |
| Opus 5 | $0.00000 | $0.00266 |
| Sonnet 5 | $0.00000 | $0.00106 |
| Haiku 4.5 | $0.00000 | $0.00053 |
Grade A, and why
execute scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute an approved plan with Ralph Loop hard constraint. Agent stops don't matter — bash loop keeps going until all checklist items are done.
Step 1: Load Plan
Resolve which plan to execute:
- Read
docs/plans/.active— if it exists, use that path - If not found, find the most recently modified
docs/plans/*.mdand write it todocs/plans/.active - If multiple plans modified within the last hour, list them and ask the user to pick
Verify the plan has reviewer APPROVE verdict. If not approved, tell the user to run @plan first.
Step 1b: Detect Work Dir
Check if the plan header contains **Work Dir:**:
WORK_DIR=$(grep -oE '^\*\*Work Dir:\*\*\s*.+' "$PLAN_FILE" | sed 's/^\*\*Work Dir:\*\*\s*//' | tr -d '[:space:]')
If Work Dir is set:
- Resolve to absolute path relative to project root
- If path doesn't exist, create worktree (infer submodule and branch from plan slug)
- 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
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.
- 5d ago First seen · 53 lines · 0 tokens per session scan A 5c8c0cfd4291
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.