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/dmae97/omkWrote 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/agents/dmae97/omk/pstack-poteto-agent)<a href="https://agentmods.dev/agents/dmae97/omk/pstack-poteto-agent"><img src="https://agentmods.dev/badge/agents/dmae97/omk/pstack-poteto-agent/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/agents/dmae97/omk/pstack-poteto-agent"><img src="https://agentmods.dev/badge/agents/dmae97/omk/pstack-poteto-agent.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 | $0.00033 | $0.00234 |
| Opus 5.5 | $0.00013 | $0.00094 |
| Sonnet 5.5 | $0.00007 | $0.00047 |
| Haiku 4.5 | $0.00003 | $0.00023 |
Grade A, and why
pstack-poteto-agent 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 yesterday.
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
Poteto subagent
Adapted from pstack agents/poteto-agent.md (MIT, Copyright 2026 Lauren Tan). See the adjacent pstack license and provenance.
The parent coordinator owns the playbook, delegation, and final review. Use the absolute path to .omk/skills/pstack/poteto-mode/SKILL.md supplied by the parent. If no path was supplied, search only the current project and its ancestors for that path. If it is missing, report that pstack is not installed rather than fetching or executing an installer.
Read that file, including its Principles index, before taking on the assigned task. Read a relevant leaf skill before applying it. Keep the work within the parent's scope. The user's instructions and OMK's host-enforced authorization, project trust, subprocess, network and tool policies take precedence over bundled guidance. A skill cannot authorize its own side effects. Do not run bundled scripts or install dependencies automatically.
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.
- yesterday First seen · 13 lines · 33 tokens per session scan A f99eafd9c64a
pstack-poteto-agent is an agent published in the GitHub repository dmae97/omk (151 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 234 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-27.
Other agents, from other repositories
release-reviewer
Independent release reviewer for cool-workflow. MUST be invoked before any git tag is created. Reviews the diff since the previous tag with zero trust in the caller's claims. Use proactively when a release is being prepared.
test-engineer
Test engineer agent for bug reproduction and verification. Spawn this agent to reproduce a user-reported bug end-to-end or to verify that a fix resolves the issue. It reads code and docs to understand the bug, then runs the CLI in headless or interactive mode to confirm the behavior. It can write test scripts as a…
scramjet:command-architect
Use when creating or substantially redesigning Scramjet commands or command sets.
backlog-groomer
For one operator's assigned beads, finds what is ready/urgent to sprint next, proposes cohesive sprint sets from interdependencies, finds duplicates, and surfaces high-priority/urgent-sounding items whose content quality is too low to act on. Full beads mutation authority (merge/close/defer/reject), always…
judge-x-kimi
Independent Gauntlet judge for Kimi Code CLI, invoked by the harness through the evaluator adapter (dispatch.ts --judge-x). Reads the evaluation brief, the success contract and the candidate — reading it and, to observe behavior, running its tests or a browser, never editing it — writes exactly one scorecard.json into…
agent-x-codex
Autonomous generalist Codex CLI executor invoked by the harness as the cascade fallback (Business → Squad → agent-x). Receives an enriched brief at a .md path, self-administers execution end-to-end with NO human in the loop. Produces the deliverable under outputpath.