メニュー
Guidance for creating, running, fixing, and promoting behavioral evaluations. Use when verifying agent decision logic, debugging failures, debugging prompt steering, or adding workspace regression tests.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Rewrite any text as a solemn, slightly absurd 19th-century Civil War field dispatch (Ken Burns documentary voice), then optionally turn it into a multimodal video — period narration via ElevenLabs, the letter in fancy script on aged parchment, a mournful music bed, and a slow Ken Burns pan/zoom of the letter being read. Use when the user types /civilwar, asks to "civil-war-ify" or "Ken Burns" some text, or asks for a documentary-style letter video.
Router / skill-set hub for the 33GOD / DeLoNET project platform. Routes user intent to the right member skill: project bootstrap (33god-projects), pjangler implementation (pjangler-dev), agent hook/skill fan-out (agent-config-fanout), Hermes fleet operations (hermes-fleet-operations), Plane ticket operations (managing-tickets-and-tasks-in-plane), Bloodbank events (bloodbank-integration), host conventions (delonet-conventions), versioning (mise-versioning), task authoring (mise-tasks), and memory (hindsight). Use when the request spans multiple 33GOD components or when you are unsure which member skill owns a 33GOD task. Triggers: 33god, 33GOD, DeLoNET, project platform, pjangler, CommonProject, Hermes, Plane, Bloodbank, agent hooks, skill fan-out, fleet, project bootstrap. Does NOT implement procedures; it loads the member skill that does.
Create, wire, and maintain 33god/DeLoNET projects. Covers pjangler/CommonProject bootstrap, repo-local `.project.json`, Hermes PM and scrum-master/Ticket Sentinel provisioning requests, mise/.env.op, BMAD, Hindsight/Bloodbank hook wiring, and project-scoped hook + skill fan-out adoption. Use when running `pjangler init`, `pjangler hermes-agent`, or `mise run init-project`; adding PM/sentinel agents; wiring mise/op inject; installing BMAD; configuring hooks; or adopting `.agents/local.json`, `defer_to_global`, and `hooks.master.json`. Do NOT use for developing pjangler (pjangler-dev), generic fan-out mechanics (agent-config-fanout), fleet updates/backfills (hermes-fleet-operations), live Plane issues, Bloodbank schemas, or host conventions.
Keep one hand-edited master config and generate per-agent CLI configs from it. Covers SSOT fan-out for agent hooks and skills: master-to-dialect propagation, ambiguity lock files, drift checks, and the Bloodbank services/agent-hooks reference implementation. Use for hooks.master.json, hooks.mappings.lock.json, generated-config drift, fan-out, SSOT, agent hooks, defer_to_global, .agents/local.json, sync.py, project-scoped hooks, skill fan-out, and new agent CLI dialects. Do NOT use for using pjangler to create projects or adoption checklists (33god-projects), event schemas or Bloodbank topology (bloodbank-integration), versioning (mise-versioning), or single-target config.
Integrate services or agent harnesses with the 33GOD Bloodbank event bus. Covers schemas in Bloodbank schemas/ and docs/event-naming.md, producing events (NATS preferred; Dapr, HTTP /publish, hookd_bridge alternatives), consuming events (NATS, Dapr, FastStream, event-toaster), and agent hook wiring. Use for event publish/consume, authoring schemas, integrating harnesses (Claude Code, Copilot CLI, OpenCode, Cursor, Aider, Codex CLI), or debugging missing envelopes. Triggers: bloodbank, event bus, publish, subscribe, NATS subject, holyfields legacy, CloudEvents, hookd, event-toaster, ntfy.delo.sh/bloodbank, agent.session.started, agent.tool.invoked, command.{agent}.{action}. Skip for generic brokers, n8n, hindsight memory, or non-event-bus 33GOD.
Operate and maintain the Hermes agent fleet: shared install, ~/.hermes/fleet.env, ~/.hermes/config.yaml, ~/.hermes/agents-registry.yaml, hermes-agent-template, role profiles and inherited config, runtime repo provisioning, systemd user units, fleet self-checks, template defaults, and PM/template backfills. Use when updating Hermes core, changing fleet defaults, provisioning agents, debugging fleet-wide MCP failures, running a Hermes fleet self-check, or propagating template changes to existing PM agents. Triggers: Hermes fleet, hermes-agent-template, ~/.hermes/fleet.env, ~/.hermes/config.yaml, ~/.hermes/agents-registry.yaml, inherited profile, fleet self-check, systemd hermes-*, template backfill, runtime repo provisioning. Do NOT use for: project bootstrap decisions or repo-local agent requests (→ 33god-projects); Plane ticket operations (→ managing-tickets-and-tasks-in-plane); Bloodbank event contracts (→ bloodbank-integration); generic SSOT config fan-out mechanics (→ agent-config-fanout).
| name | behavioral-evals |
| description | Guidance for creating, running, fixing, and promoting behavioral evaluations. Use when verifying agent decision logic, debugging failures, debugging prompt steering, or adding workspace regression tests. |
| pipeline-status | ["new"] |
Behavioral evaluations (evals) are tests that validate the agent's decision-making (e.g., tool choice) rather than pure functionality. They are critical for verifying prompt changes, debugging steerability, and preventing regressions.
[!NOTE] Single Source of Truth: For core concepts, policies, running tests, and general best practices, always refer to evals/README.md.
appEvalTest (AppRig). See creating.md.evalTest (TestRig). See creating.md.USUALLY_PASSES.ALWAYS_PASSES (locks in regression).Seed the workspace with necessary files using the files object to simulate a realistic scenario (e.g., NodeJS project with package.json).
Audit agent decisions using rig.setBreakpoint() (AppRig only) or index verification on rig.readToolLogs().
Run single tests locally with Vitest. Confirm stability locally before relying on CI workflows.
Detailed procedural guides: