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.
git 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/do)<a href="https://agentmods.dev/commands/kaimingwan/oh-my-kiro/do"><img src="https://agentmods.dev/badge/commands/kaimingwan/oh-my-kiro/do/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/kaimingwan/oh-my-kiro/do"><img src="https://agentmods.dev/badge/commands/kaimingwan/oh-my-kiro/do.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00443 |
| Opus 5 | $0.00000 | $0.00221 |
| Sonnet 5 | $0.00000 | $0.00089 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
do 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 9d 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.
What it actually says
Lightweight command for small tasks (< 1 hour). No plan file, no review dispatch. Prevents context drift across multi-turn interactions.
Stage 1: Scratchpad (MANDATORY, even if task seems trivial)
Before ANY code change, write a scratchpad to /tmp/task-scratch.md:
## Task: <one-line description>
- Files: <list files to read/modify, discovered via LSP>
- Constraint: <key constraints or gotchas>
- Verify: <how to verify success>
Discovery steps (silent, no user output):
search_symbols/find_references/get_diagnosticsto identify all affected files- Read each affected file's relevant sections (NOT entire files — use line offsets)
- Update scratchpad with actual file list and key findings
Stage 2: Execute
Make changes following skills/omk-coding/SKILL.md Phase 1-4.
Context anchor rule: After EVERY code modification, append a one-line status to the scratchpad:
- [done] modified hooks/feedback/context-enrichment.sh L37-41: expanded CN keywords
- [done] created symlink commands/auto.md → oh-my-kiro
- [blocked] test fails: grep pattern doesn't match "超时"
Stage 3: Verify
- Run the verify method from scratchpad
- Re-read scratchpad to confirm all items addressed
- Report result to user
Multi-turn recovery
If the conversation has gone ≥ 3 turns on this task:
- STOP and re-read
/tmp/task-scratch.md - Compare current state vs scratchpad — identify drift
- If drifted, state what drifted and correct course
User's task: (The user's next message is the task. If this is the first message after @do was invoked and no task appears above, wait for the user's next message — it will contain the task. Do NOT ask "what do you want to do?" — the user already knows they need to provide input after @do.)
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.
- 9d ago First seen · 46 lines · 0 tokens per session scan A 22d8fbe5e27d
do 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 443 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.