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 pome-sh/digital-twins --skill pomegit clone --depth 1 https://github.com/pome-sh/digital-twinsWrote 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/pome-sh/digital-twins/pome)<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.
<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>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 | $0.00066 | $0.00752 |
| Opus 5 | $0.00033 | $0.00376 |
| Sonnet 5 | $0.00013 | $0.00150 |
| Haiku 4.5 | $0.00007 | $0.00075 |
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.
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-intakeand 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 |
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.
- 6d ago Changed · -24 lines · -16 tokens per session 408c9390bb3f
- 10d ago First seen · 88 lines · 82 tokens per session scan A 12548bed2768
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.
Other skills, from other repositories
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
mcp-app-verification
Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling, host styling, CSP, and legacy pattern detection.