pome

pome is a skill for Claude Code from pome-sh/digital-twins. It costs 66 tokens per session (752 once invoked), scanned A, original, Apache-2.0.

A routing guide for testing an AI agent with Pome, a service that runs agents against simulated versions of connected tools and grades their results. It chooses the right coaching guide based on the agent and task you provide.

In plain words
What is it for?
Use it when you want to test an agent, run Pome, or decide whether to register an agent, suggest a task, inspect a local agent, or write a task.
Why use it?
It removes the need to decide which Pome testing procedure to follow. It also makes clear when Pome's control connection is missing and must be authenticated.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pome-coach plugin — 6 skills shipped together

Good fit Use it when you want to test an agent, run Pome, or decide whether to register an agent, suggest a task, inspect a local agent, or write a task.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pome-sh/digital-twins/pome
Install

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.

Any agent
npx skills add pome-sh/digital-twins --skill pome
Clone the repo
git clone --depth 1 https://github.com/pome-sh/digital-twins

Made for: Claude Code.

Or install pome-coach, the plugin that ships this one along with the rest of its 6 skills.

Wrote 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.

agentmods badge for pome

README.md
[![agentmods](https://agentmods.dev/badge/skills/pome-sh/digital-twins/pome/github.svg)](https://agentmods.dev/skills/pome-sh/digital-twins/pome)
Your own site
<a href="https://agentmods.dev/skills/pome-sh/digital-twins/pome"><img src="https://agentmods.dev/badge/skills/pome-sh/digital-twins/pome/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.

agentmods 80×15 button for pome

Your own site · 80×15
<a href="https://agentmods.dev/skills/pome-sh/digital-twins/pome"><img src="https://agentmods.dev/badge/skills/pome-sh/digital-twins/pome.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 752 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00066 $0.00752
Opus 5 $0.00033 $0.00376
Sonnet 5 $0.00013 $0.00150
Haiku 4.5 $0.00007 $0.00075

Measured 6d ago against content hash 408c9390bb3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pome 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 6d 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.

skills/pome/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pome (entry router)

You are the coach: you talk to the builder and to the Pome control MCP (mcp.pome.sh). The examinee is their agent running against Pome's digital twins. Pome grades the run from the twin tape. Read the builder's context and route to the applicable coach skill.

If the mcp__pome__* tools are missing, ask the user to connect the MCP and complete OAuth in a browser: claude mcp add --transport http pome https://mcp.pome.sh/mcp.

Route by context

The builder arrives with… Route
A Claude managed-agent YAML Use pome-intake.
A registered local agent with no task Use pome-suggest-tasks.
A local repository agent that uses REST Register with the CLI, then use pome-run-task. See Choose CLI or MCP registration.
A test idea Use pome-author-task.
A drafted task Use pome-verify-seed.
A verified task Use pome-run-task.

Use pome-suggest-tasks when the manifest's task directory has no Markdown files and list_tasks is empty. If local task files exist, ask whether the builder wants to run one or create a new task.

When the route is unclear, ask whether the agent is managed or runs from a local repository.

Choose CLI or MCP registration

Choose the registration surface from the agent location:

  • For a local repository, run pome register agent <name> [--twins ...]. Only the CLI updates the Pome manifest and .pome/link.json.
  • For a managed agent with no local repository, use pome-intake and the MCP registration tools.

Run an explicit CLI registration command verbatim. Do not replace it with MCP register_agent. MCP registration does not write the local files.

For an existing registration, register_agent(name, twins:[...]) can add twins to the allowlist.

This is not the CLI

The pome CLI records traces locally. Pome evaluates and scores hosted runs.

CLI-era habit Hosted (coach) equivalent
pome register agent See Choose CLI or MCP registration.
pome run <task> Call run_task, launch the agent, call finalize_run when it is idle, then call get_report.
pome run -n 3 Call run_trials, finalize each run, then call list_runs(group_id).
Local task files on disk Call save_task, then browse with list_tasks.
"Where are my results?" get_report(run_id) / list_runs, and the dashboard on app.pome.sh

Read the full file on GitHub · 64 lines

Files

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.

Changes

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.

  1. 6d ago Changed · -24 lines · -16 tokens per session 408c9390bb3f
  2. 10d ago First seen · 88 lines · 82 tokens per session scan A 12548bed2768

Subscribe to this mod's changes

pome is a skill published in the GitHub repository pome-sh/digital-twins (14 stars, last pushed 4d ago), licensed Apache-2.0. It adds 66 tokens to every session and 752 once invoked, about $0.0003 per session on Opus 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 2026-08-30.