pome-sh

pome-sh/digital-twins

Plugin Claude Code

The Pome coach skill set — register an agent, author and verify graded tasks, run them against the digital twins, and read the scored report.

pome-sh/digital-twins

MCP server Claude CodeCodexCursor +2

MCP server "openapi-specs" as configured in pome-sh/digital-twins. Launched with bash scripts/mcp/openapi-specs.sh.

pome-sh/digital-twins

Instructions file CodexOpenCode

Instructions for pome-sh/digital-twins, covering agents.md, intro, layout, commands and rules.

pome-sh/digital-twins

Skill Claude CodeCodex

Author a graded Pome task for a builder's agent and save it to their team catalog. Library-first — adapt an existing task before writing fresh; interview the builder about what would go wrong; draft criteria as code/model markers; validate + dry-run against the twins; then savetask. Use when the user wants to "write a…

pome-sh/digital-twins

Skill Claude CodeCodex

Intakes a Claude managed agent for testing on Pome — collects the full clone scope (agent YAML, environment config, attached memory stores, deployment kickoff events), registers it via the Pome control MCP's intakeclonescope, and reports which of the agent's mcpservers have twin coverage. Use when the user pastes a…

pome-sh/digital-twins

Skill Claude CodeCodex

Runs a verified Pome task against the builder's examinee and scores it from the live twin tape — runtask to mint the session, launch the examinee on its runtime (Managed Agents via ant, or REST), finalizerun the instant it idles while the tape is still live, then narrate getreport; re-runs only the failed tasks after…

pome-sh/digital-twins

Skill Claude CodeCodex

Propose a builder's first Pome task by reading their already-registered agent — reads the pome.json manifest (twins) and the agent's prompt/code, proposes 2–3 candidate tasks grounded in what the agent actually does, runs a short interview to pick one, then hands off to pome-author-task. Use in a repo that already has…

pome-sh/digital-twins

Skill Claude CodeCodex

Verifies a Pome task's seed is a fair exam before any run — verifyseed plus guard-aware triage of already-passing criteria, a state-diff review, an evaluatecriteria dry-run, and opt-in read-only probes on a live twin session. Use when the user has authored or adapted a task and wants to check the seed, asks "is my…

pome-sh/digital-twins

Skill Claude CodeCodex

Entry point for testing an agent with Pome — routes to the right coach skill by context (managed-agent YAML → pome-intake, local repo / self-hosted REST agent → the local-examinee run path, plain task authoring → pome-author-task). Use when the user says "test my agent with pome", "run pome", or "use pome".