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/cpu)<a href="https://agentmods.dev/commands/kaimingwan/oh-my-kiro/cpu"><img src="https://agentmods.dev/badge/commands/kaimingwan/oh-my-kiro/cpu/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/cpu"><img src="https://agentmods.dev/badge/commands/kaimingwan/oh-my-kiro/cpu.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 | $0.01039 |
| Opus 5.5 | $0.00000 | $0.00416 |
| Sonnet 5.5 | $0.00000 | $0.00208 |
| Haiku 4.5 | $0.00000 | $0.00104 |
Grade A, and why
cpu 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 2mo 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit all changes, push to remote, and complete branch lifecycle. (CPU = Commit Push Update-readme)
Scope
Only operate on the current project (where AGENTS.md lives). NEVER cd into or commit/push other repositories.
Steps
Step 0: Update README (the "U" in CPU)
Before committing, check if README.md needs updating based on what changed.
-
Run
git diff --name-only HEAD(orgit diff --name-only --cached HEADif staged) to get changed files. -
Check each category against README.md:
| Changed path pattern | README section to check |
|---|---|
commands/*.md (new file) |
Command table (@command rows) |
skills/*/SKILL.md (new file) |
Skills table or list |
hooks/**/*.sh (new file) |
Hooks section or directory tree |
| Any new top-level directory | Directory tree in README |
-
For each mismatch found:
- Read the new file to understand what it does (first line or description field)
- Add the missing entry to the appropriate README section
- Match the format of existing entries exactly
-
If no README updates needed, skip silently. If updates were made, stage them with the rest.
Rule: Only ADD entries for new files. Do NOT rewrite, reformat, or "improve" existing README content.
Step 1: Stage & Commit
git add -A && git status --short— show what's staged- Ask user for commit message if not provided, or generate one from the diff
git commit -m "<message>"git push- Report: commit hash + push result
Step 2: Detect Worktree
Check if currently inside a git worktree:
wt_dir=$(git rev-parse --git-common-dir 2>/dev/null)
git_dir=$(git rev-parse --git-dir 2>/dev/null)
if [ "$wt_dir" != "$git_dir" ]; then
echo "IN_WORKTREE=true"
# Get the base branch (the branch of the main working tree)
base_branch=$(git -C "$wt_dir/.." branch --show-current 2>/dev/null || echo "main")
echo "BASE_BRANCH=$base_branch"
else
echo "IN_WORKTREE=false"
fi
- If not in worktree → STOP here. Done (original behavior).
- If in worktree → continue to Step 3.
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.
- 2mo ago First seen · 113 lines · 0 tokens per session scan A 0d0261e5ba53
cpu is a command published in the GitHub repository KaimingWan/oh-my-kiro (107 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,039 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.
cpu compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cpuKaimingWan/oh-my-kiro | Command | 107 | 7mo ago | MIT | A | 0 | Claude Code |
| commit-push-pranthropics/claude-plugins-official | Command | 46k | yesterday | Apache-2.0 | A | 8 | Claude Code |
| changelog-updategonzalezpazmonica/pm-workspace | Command | 51 | 5d ago | MIT | A | 68 | Claude Code |
| changelogricneves-ai/flowgrammers-skills | Command | 117 | 1mo ago | MIT | A | 0 | Claude Code |
| commitfusengine/agents | Command | 34 | 25d ago | MIT | A | 31 | Claude Code |
| flowsynaptiai/synapti-marketplace | Command | 7 | yesterday | Apache-2.0 | A | 68 | Claude Code |
| commitdykyi-roman/awesome-claude-code | Command | 105 | 2mo ago | MIT | A | 36 | Claude Code |