pome-run-task

pome-run-task is a skill for Claude Code from pome-sh/digital-twins. It costs 123 tokens per session (2,563 once invoked), scanned A, original, Apache-2.0.

A test runner for Pome, a system that evaluates coding agents on tasks using recorded activity from a live test environment. It launches an agent, runs one verified task, and produces a score and report.

In plain words
What is it for?
Use it to evaluate a registered coding agent on a prepared Pome task, score its behavior, and report the result.
Why use it?
It removes the manual work of starting an evaluation, ending it at the right time, and reviewing the resulting activity record. It can repeat only tasks that failed.

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 to evaluate a registered coding agent on a prepared Pome task, score its behavior, and report the result.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/pome-sh/digital-twins/pome-run-task"><img src="https://agentmods.dev/badge/skills/pome-sh/digital-twins/pome-run-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,563 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 $0.00123 $0.02563
Opus 5 $0.00062 $0.01282
Sonnet 5 $0.00025 $0.00513
Haiku 4.5 $0.00012 $0.00256

Measured 6d ago against content hash 0b3c47c7617b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pome-run-task 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-run-task/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pome run task (Skill 4)

You are the coach: you talk to the builder and to the Pome control MCP (mcp.pome.sh). The examinee is the sandbox clone Skill 0 (pome-intake) registered, launched here for real against live twins. This skill runs one already-verified task and scores it from the twin tape. Verify the seed first (pome-verify-seed) — this skill does not re-check fairness.

Only one step here is examinee-runtime-specific: launching the examinee. Minting, finalizing, scoring, reporting, and the fix loop are runtime-agnostic (ADR-018). The launch policyalways_allow, closed-book web tools, memory snapshot-clone, the network clamp — is owned by the examinee_launch spec, not by this prose: you execute the spec, you do not restate it.

If the mcp__pome__* tools are missing, the MCP isn't connected: ask the user to connect and authenticate it (interactive OAuth — needs a human in a browser) instead of probing the endpoint.

SENSITIVE — the bearer. run_task returns agent_token, a session-scoped JWT that is the bearer for every twin URL — a live credential. It exists for one purpose: handing the examinee its twin authentication at launch (§2). Pass it straight into the launcher's env or vault and then let go of it — never write it to disk, into a task, or a log, never repeat it back to the builder, and never keep it around "for later". Nothing downstream needs it: finalize_run derives the bearer from session_id server-side. It dies at expires_at regardless.

1. Mint the run

Mint a grp_-prefixed group_id now and reuse it for every trial of this attempt — the baseline and any pre-fix flaky retries — so they aggregate as one exam (aggregation keys on (group_id, task); never reuse a group_id across different tasks). A post-fix rerun is the exception: it opens a new group_id and links back to the baseline via baseline_group_id (see §5). Then call run_task(task_id, agent_id, agent_version, group_id) (the agent_id from intake). It seeds live twin sandboxes and returns session_id, expires_at, agent_token, examinee_task (the prompt + twins the examinee sees — no criteria), and examinee_launch (the full launch spec).

Read the full file on GitHub · 161 lines

Files

What ships with it

3 files 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 · +3 lines 0b3c47c7617b
  2. 10d ago First seen · 158 lines · 123 tokens per session scan A b70fba85ff24

Subscribe to this mod's changes

pome-run-task is a skill published in the GitHub repository pome-sh/digital-twins (14 stars, last pushed 4d ago), licensed Apache-2.0. It adds 123 tokens to every session and 2,563 once invoked, about $0.0006 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.