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 skills add amirkiarafiei/subagent-cli-skills --skill oh-my-pigit clone --depth 1 https://github.com/amirkiarafiei/subagent-cli-skillsWrote 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/skills/amirkiarafiei/subagent-cli-skills/oh-my-pi)<a href="https://agentmods.dev/skills/amirkiarafiei/subagent-cli-skills/oh-my-pi"><img src="https://agentmods.dev/badge/skills/amirkiarafiei/subagent-cli-skills/oh-my-pi/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/skills/amirkiarafiei/subagent-cli-skills/oh-my-pi"><img src="https://agentmods.dev/badge/skills/amirkiarafiei/subagent-cli-skills/oh-my-pi.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 | $0.00088 | $0.02392 |
| Opus 5 | $0.00044 | $0.01196 |
| Sonnet 5 | $0.00018 | $0.00478 |
| Haiku 4.5 | $0.00009 | $0.00239 |
Grade C, and why
oh-my-pi scanned grade C with 1 finding 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 3d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
> "critical destructive patterns such as `rm -rf /`, fork bombs, remote-fetch-then-execute, writes to How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oh My Pi CLI (subagent/task delegation)
Documented, not verified. Written from Oh My Pi's own docs source on 2026-09-06 and not checked against an installed binary. Before trusting any flag here, run
omp --help; on a mismatch use what the binary actually offers and tell the user which line in this file is wrong.
Use Oh My Pi (omp) to run a separate long-horizon pass over the repo: multi-step
implementation, broad refactors, batch file writes, or deep exploration—similar to handing a task to a
subagent. You stay orchestrator: smaller prompts, less context burn.
When to use Oh My Pi
- Large or multi-step work: several files, phases, or checkpoints (feature slice, migration, test suite, docs sweep).
- Time-bounded delegation:
--max-time <duration>is a real wall-clock limit (600,10m,1h) — the only one among the CLIs in this repo, and the reasonompis a good fit for unattended runs. - Machine-readable progress:
--mode jsonemits a structured event stream for headless consumption. - Fine-grained approval control: a documented three-level approval model (
always-ask/write/yolo) rather than one all-or-nothing switch. - Session portability:
--from-claude/--from-codeximport an existing Claude Code or Codex session. - User explicitly asks for Oh My Pi or "use omp for this."
When not to use
- Small / single-step tasks answerable with one or two edits or a short explanation.
- Tight feedback loops where the user wants rapid back-and-forth refinement in one thread.
- Secrets or policy-sensitive flows—avoid piping credentials; redact before delegating.
- Already-loaded context where duplicating the whole plan adds no value—handle locally.
- Low ROI (Return on Investment): if the task requires high precision over a single line, or composing the Handoff Table costs more than editing the file yourself.
Delegation and context (critical)
Isolated subagent context saves tokens but splits the story: omp does not see the main session's
full thread. Poor handoffs cause misread subtasks, conflicting assumptions (stack, style, APIs), and
wasted edits.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 160 lines · 88 tokens per session scan C 1cdfa48a372f
oh-my-pi is a skill published in the GitHub repository amirkiarafiei/subagent-cli-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 88 tokens to every session and 2,392 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.
Other skills, from other repositories
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
brainstorm
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
wish
Convert an idea into a structured wish plan with scope, acceptance criteria, and execution groups for work.
project-context
Use PowerContext project memory and handoff tools through MCP when continuing prior work, recalling decisions, maintaining durable memory, or transferring work across tasks, sessions, or agents.
report
Investigate bugs comprehensively — cascade through trace, capture browser evidence, extract observability data, and prepare or explicitly create a GitHub issue with grounded findings.