@chankov/agent-fleet 0.0.10 → 0.0.11
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.pi/extensions/btw/README.md +3 -2
- package/.pi/extensions/pi-voice-stt/README.md +3 -0
- package/.pi/harnesses/agent-hub/README.md +3 -0
- package/.pi/harnesses/agent-hub/package.json +1 -1
- package/.pi/harnesses/coms/package.json +1 -1
- package/.pi/harnesses/damage-control-continue/package.json +1 -1
- package/.versions/0.0.11/.claude/commands/build.md +44 -0
- package/.versions/0.0.11/.claude/commands/code-simplify.md +22 -0
- package/.versions/0.0.11/.claude/commands/design-agent.md +14 -0
- package/.versions/0.0.11/.claude/commands/doctor-agent-fleet.md +22 -0
- package/.versions/0.0.11/.claude/commands/orchestrate.md +112 -0
- package/.versions/0.0.11/.claude/commands/plan.md +16 -0
- package/.versions/0.0.11/.claude/commands/prime.md +22 -0
- package/.versions/0.0.11/.claude/commands/review.md +16 -0
- package/.versions/0.0.11/.claude/commands/set-hermes-telegram.md +15 -0
- package/.versions/0.0.11/.claude/commands/set-hermes-watchdog.md +6 -0
- package/.versions/0.0.11/.claude/commands/setup-agent-fleet.md +17 -0
- package/.versions/0.0.11/.claude/commands/ship.md +72 -0
- package/.versions/0.0.11/.claude/commands/spec.md +15 -0
- package/.versions/0.0.11/.claude/commands/test.md +19 -0
- package/.versions/0.0.11/.claude/commands/webperf.md +32 -0
- package/.versions/0.0.11/.claude/orchestrate-teams.yaml +24 -0
- package/.versions/0.0.11/.opencode/commands/af-build.md +17 -0
- package/.versions/0.0.11/.opencode/commands/af-code-simplify.md +16 -0
- package/.versions/0.0.11/.opencode/commands/af-compound.md +16 -0
- package/.versions/0.0.11/.opencode/commands/af-design-agent.md +15 -0
- package/.versions/0.0.11/.opencode/commands/af-doctor-agent-fleet.md +22 -0
- package/.versions/0.0.11/.opencode/commands/af-orchestrate.md +112 -0
- package/.versions/0.0.11/.opencode/commands/af-plan.md +16 -0
- package/.versions/0.0.11/.opencode/commands/af-prime.md +22 -0
- package/.versions/0.0.11/.opencode/commands/af-review.md +15 -0
- package/.versions/0.0.11/.opencode/commands/af-set-hermes-telegram.md +15 -0
- package/.versions/0.0.11/.opencode/commands/af-set-hermes-watchdog.md +6 -0
- package/.versions/0.0.11/.opencode/commands/af-setup-agent-fleet.md +17 -0
- package/.versions/0.0.11/.opencode/commands/af-ship.md +16 -0
- package/.versions/0.0.11/.opencode/commands/af-spec.md +16 -0
- package/.versions/0.0.11/.opencode/commands/af-test.md +21 -0
- package/.versions/0.0.11/.opencode/commands/af-webperf.md +32 -0
- package/.versions/0.0.11/.opencode/orchestrate-teams.yaml +24 -0
- package/.versions/0.0.11/.pi/agents/dispatch-policy.yaml +32 -0
- package/.versions/0.0.11/.pi/agents/model-profiles.yaml +27 -0
- package/.versions/0.0.11/.pi/agents/peers.yaml +142 -0
- package/.versions/0.0.11/.pi/agents/teams.yaml +41 -0
- package/.versions/0.0.11/.pi/damage-control-rules.yaml +297 -0
- package/.versions/0.0.11/.pi/extensions/agent-fleet-update-check/README.md +57 -0
- package/.versions/0.0.11/.pi/extensions/agent-fleet-update-check/index.ts +161 -0
- package/.versions/0.0.11/.pi/extensions/agent-fleet-update-check/package.json +6 -0
- package/.versions/0.0.11/.pi/extensions/btw/README.md +119 -0
- package/.versions/0.0.11/.pi/extensions/btw/index.ts +917 -0
- package/.versions/0.0.11/.pi/extensions/btw/package.json +6 -0
- package/.versions/0.0.11/.pi/extensions/btw/state.js +179 -0
- package/.versions/0.0.11/.pi/extensions/chrome-devtools-mcp/README.md +55 -0
- package/.versions/0.0.11/.pi/extensions/chrome-devtools-mcp/index.ts +93 -0
- package/.versions/0.0.11/.pi/extensions/chrome-devtools-mcp/package.json +6 -0
- package/.versions/0.0.11/.pi/extensions/compact-and-continue/README.md +42 -0
- package/.versions/0.0.11/.pi/extensions/compact-and-continue/index.ts +120 -0
- package/.versions/0.0.11/.pi/extensions/compact-and-continue/package.json +6 -0
- package/.versions/0.0.11/.pi/extensions/mcp-bridge/README.md +46 -0
- package/.versions/0.0.11/.pi/extensions/mcp-bridge/index.ts +206 -0
- package/.versions/0.0.11/.pi/extensions/mcp-bridge/package.json +6 -0
- package/.versions/0.0.11/.pi/extensions/package-lock.json +1143 -0
- package/.versions/0.0.11/.pi/extensions/package.json +9 -0
- package/.versions/0.0.11/.pi/extensions/pi-voice-stt/README.md +204 -0
- package/.versions/0.0.11/.pi/extensions/pi-voice-stt/config.ts +198 -0
- package/.versions/0.0.11/.pi/extensions/pi-voice-stt/examples/stt.json +35 -0
- package/.versions/0.0.11/.pi/extensions/pi-voice-stt/index.ts +248 -0
- package/.versions/0.0.11/.pi/extensions/pi-voice-stt/package.json +6 -0
- package/.versions/0.0.11/.pi/extensions/pi-voice-stt/providers.ts +214 -0
- package/.versions/0.0.11/.pi/extensions/pi-voice-stt/recorder.ts +158 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/README.md +1004 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/access-approval.ts +135 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/artifacts.js +146 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/assertion-ledger.js +58 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/backend-policy.js +153 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/context-window.js +106 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/delegate.ts +435 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/docs-lane.js +122 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/drift-watchdog.js +211 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/evidence-rules.js +96 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/external-blocker.js +85 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/footer.ts +31 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/helpers.ts +248 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/index.ts +9111 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/monitor-control.ts +9 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/monitor-invoke-journal.ts +131 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/monitor-invoke.ts +92 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/monitor-lifecycle.ts +13 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/monitor-publisher.ts +59 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/monitor-recovery.ts +3 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/monitor-runtime.ts +3 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/monitor-session-bridge.ts +257 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/package.json +7 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/provider-semaphore.js +138 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/research-retention.js +34 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/research-watchdog.ts +40 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/return-contract.js +293 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/return-extract.js +75 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/review-findings.js +102 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/run-budget.js +479 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/run-namespace.js +87 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/safety-routing.ts +22 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/scope-gate.js +103 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/session-health.js +110 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/spawn.ts +354 -0
- package/.versions/0.0.11/.pi/harnesses/agent-hub/version.ts +42 -0
- package/.versions/0.0.11/.pi/harnesses/ask-user-remote/README.md +19 -0
- package/.versions/0.0.11/.pi/harnesses/ask-user-remote/index.ts +321 -0
- package/.versions/0.0.11/.pi/harnesses/ask-user-remote/race-core.js +106 -0
- package/.versions/0.0.11/.pi/harnesses/coms/README.md +100 -0
- package/.versions/0.0.11/.pi/harnesses/coms/index.ts +1767 -0
- package/.versions/0.0.11/.pi/harnesses/coms/package.json +7 -0
- package/.versions/0.0.11/.pi/harnesses/coms/version.ts +42 -0
- package/.versions/0.0.11/.pi/harnesses/damage-control-continue/README.md +124 -0
- package/.versions/0.0.11/.pi/harnesses/damage-control-continue/index.ts +536 -0
- package/.versions/0.0.11/.pi/harnesses/damage-control-continue/package.json +7 -0
- package/.versions/0.0.11/.pi/harnesses/damage-control-continue/version.ts +42 -0
- package/.versions/0.0.11/.pi/harnesses/lib/coms-registry-entry.ts +94 -0
- package/.versions/0.0.11/.pi/harnesses/lib/damage-control-shared.ts +197 -0
- package/.versions/0.0.11/.pi/harnesses/lib/herdr-client.ts +472 -0
- package/.versions/0.0.11/.pi/harnesses/lib/herdr-presence.ts +399 -0
- package/.versions/0.0.11/.pi/harnesses/lib/hermes-monitor-events.ts +136 -0
- package/.versions/0.0.11/.pi/harnesses/lib/hermes-monitor-herdr.ts +28 -0
- package/.versions/0.0.11/.pi/harnesses/lib/hermes-monitor-model.ts +18 -0
- package/.versions/0.0.11/.pi/harnesses/lib/hermes-monitor-registry.ts +6 -0
- package/.versions/0.0.11/.pi/harnesses/lib/hermes-monitor-socket.ts +163 -0
- package/.versions/0.0.11/.pi/harnesses/lib/hermes-monitor-store.ts +31 -0
- package/.versions/0.0.11/.pi/harnesses/lib/spawned-peers.js +190 -0
- package/.versions/0.0.11/.pi/harnesses/package-lock.json +35 -0
- package/.versions/0.0.11/.pi/harnesses/package.json +9 -0
- package/.versions/0.0.11/.pi/prompts/af-build.md +24 -0
- package/.versions/0.0.11/.pi/prompts/af-code-simplify.md +22 -0
- package/.versions/0.0.11/.pi/prompts/af-doctor-agent-fleet.md +22 -0
- package/.versions/0.0.11/.pi/prompts/af-plan.md +16 -0
- package/.versions/0.0.11/.pi/prompts/af-review.md +16 -0
- package/.versions/0.0.11/.pi/prompts/af-set-hermes-telegram.md +15 -0
- package/.versions/0.0.11/.pi/prompts/af-set-hermes-watchdog.md +6 -0
- package/.versions/0.0.11/.pi/prompts/af-setup-agent-fleet.md +19 -0
- package/.versions/0.0.11/.pi/prompts/af-ship.md +17 -0
- package/.versions/0.0.11/.pi/prompts/af-spec.md +15 -0
- package/.versions/0.0.11/.pi/prompts/af-test.md +19 -0
- package/.versions/0.0.11/.pi/skills/bowser/SKILL.md +145 -0
- package/.versions/0.0.11/.version +1 -0
- package/.versions/0.0.11/agents/architect.md +24 -0
- package/.versions/0.0.11/agents/bowser.md +27 -0
- package/.versions/0.0.11/agents/builder.md +54 -0
- package/.versions/0.0.11/agents/code-reviewer.md +208 -0
- package/.versions/0.0.11/agents/deep-researcher.md +32 -0
- package/.versions/0.0.11/agents/documenter.md +18 -0
- package/.versions/0.0.11/agents/orchestrator.md +72 -0
- package/.versions/0.0.11/agents/plan-reviewer.md +83 -0
- package/.versions/0.0.11/agents/planner.md +70 -0
- package/.versions/0.0.11/agents/releaser.md +24 -0
- package/.versions/0.0.11/agents/researcher.md +28 -0
- package/.versions/0.0.11/agents/security-auditor.md +167 -0
- package/.versions/0.0.11/agents/test-engineer.md +153 -0
- package/.versions/0.0.11/agents/web-debugger.md +43 -0
- package/.versions/0.0.11/agents/web-performance-auditor.md +193 -0
- package/.versions/0.0.11/codex/CONDUCTOR.md +148 -0
- package/.versions/0.0.11/docs/ARCHITECTURE.md +303 -0
- package/.versions/0.0.11/docs/agent-fleet-setup.md +377 -0
- package/.versions/0.0.11/docs/claude-code-coms-bridge.md +109 -0
- package/.versions/0.0.11/docs/codex-remote-conductor.md +170 -0
- package/.versions/0.0.11/docs/coms-hermes-bridge.md +189 -0
- package/.versions/0.0.11/docs/getting-started.md +254 -0
- package/.versions/0.0.11/docs/npm-install.md +514 -0
- package/.versions/0.0.11/docs/opencode-setup.md +281 -0
- package/.versions/0.0.11/docs/pi-extensions.md +368 -0
- package/.versions/0.0.11/docs/pi-setup.md +571 -0
- package/.versions/0.0.11/docs/skill-anatomy.md +150 -0
- package/.versions/0.0.11/hermes/README.md +347 -0
- package/.versions/0.0.11/hermes/desktop-plugins/agent-fleet-herdr/plugin.js +1291 -0
- package/.versions/0.0.11/hermes/desktop-plugins/agent-fleet-herdr/presentation.js +672 -0
- package/.versions/0.0.11/hermes/desktop-plugins/agent-fleet-monitor/plugin.js +19 -0
- package/.versions/0.0.11/hermes/desktop-plugins/agent-fleet-monitor/state.js +10 -0
- package/.versions/0.0.11/hermes/gates/gate-o-capability.md +8 -0
- package/.versions/0.0.11/hermes/gates/gate-o-validator-fixtures.json +1 -0
- package/.versions/0.0.11/hermes/plugins/agent-fleet-herdr/dashboard/activity.py +770 -0
- package/.versions/0.0.11/hermes/plugins/agent-fleet-herdr/dashboard/coms_registry.py +134 -0
- package/.versions/0.0.11/hermes/plugins/agent-fleet-herdr/dashboard/coms_send.py +350 -0
- package/.versions/0.0.11/hermes/plugins/agent-fleet-herdr/dashboard/herdr_source.py +193 -0
- package/.versions/0.0.11/hermes/plugins/agent-fleet-herdr/dashboard/manifest.json +4 -0
- package/.versions/0.0.11/hermes/plugins/agent-fleet-herdr/dashboard/plugin_api.py +444 -0
- package/.versions/0.0.11/hermes/plugins/agent-fleet-herdr/dashboard/sessions.py +205 -0
- package/.versions/0.0.11/hermes/plugins/agent-fleet-herdr/dashboard/tasks.py +300 -0
- package/.versions/0.0.11/hermes/plugins/agent-fleet-herdr/dashboard/watch.py +819 -0
- package/.versions/0.0.11/hermes/plugins/agent-fleet-herdr/plugin.yaml +8 -0
- package/.versions/0.0.11/hermes/plugins/agent-fleet-monitor/dashboard/adapter.py +139 -0
- package/.versions/0.0.11/hermes/plugins/agent-fleet-monitor/dashboard/manifest.json +11 -0
- package/.versions/0.0.11/hermes/plugins/agent-fleet-monitor/dashboard/plugin_api.py +50 -0
- package/.versions/0.0.11/hermes/skills/hub-conductor/SKILL.md +84 -0
- package/.versions/0.0.11/hermes/skills/hub-liaison/SKILL.md +84 -0
- package/.versions/0.0.11/hermes/skills/hub-watchdog/SKILL.md +76 -0
- package/.versions/0.0.11/hermes/skills/hub-watchdog/manifest.json +1 -0
- package/.versions/0.0.11/hermes/skills/hub-watchdog/scripts/watchdog.py +249 -0
- package/.versions/0.0.11/hermes/skills/hub-watchdog/scripts/watchdog_actions.py +124 -0
- package/.versions/0.0.11/hermes/skills/hub-watchdog/scripts/watchdog_contract.py +76 -0
- package/.versions/0.0.11/hermes/skills/hub-watchdog/scripts/watchdog_delivery.py +10 -0
- package/.versions/0.0.11/hermes/skills/hub-watchdog/scripts/watchdog_engine.py +128 -0
- package/.versions/0.0.11/hermes/skills/hub-watchdog/scripts/watchdog_judgment.py +41 -0
- package/.versions/0.0.11/hermes/skills/hub-watchdog/scripts/watchdog_recovery.py +103 -0
- package/.versions/0.0.11/hermes/skills/hub-watchdog/scripts/watchdog_state.py +163 -0
- package/.versions/0.0.11/hermes/skills/hub-watchdog/scripts/watchdog_transport.py +138 -0
- package/.versions/0.0.11/hermes/watchdog-tests/__init__.py +0 -0
- package/.versions/0.0.11/hooks/SIMPLIFY-IGNORE.md +90 -0
- package/.versions/0.0.11/hooks/coms-stop-hook.mjs +84 -0
- package/.versions/0.0.11/hooks/hooks.json +14 -0
- package/.versions/0.0.11/hooks/session-start.sh +74 -0
- package/.versions/0.0.11/hooks/simplify-ignore.sh +302 -0
- package/.versions/0.0.11/install-manifest.json +3615 -0
- package/.versions/0.0.11/justfile +254 -0
- package/.versions/0.0.11/manifest-meta.json +472 -0
- package/.versions/0.0.11/references/accessibility-checklist.md +160 -0
- package/.versions/0.0.11/references/definition-of-done.md +67 -0
- package/.versions/0.0.11/references/fleet-coordination-patterns.md +151 -0
- package/.versions/0.0.11/references/observability-checklist.md +91 -0
- package/.versions/0.0.11/references/orchestration-patterns.md +370 -0
- package/.versions/0.0.11/references/performance-checklist.md +153 -0
- package/.versions/0.0.11/references/prompting-patterns.md +380 -0
- package/.versions/0.0.11/references/security-checklist.md +179 -0
- package/.versions/0.0.11/references/testing-patterns.md +236 -0
- package/.versions/0.0.11/scripts/codex-conductor.ts +41 -0
- package/.versions/0.0.11/scripts/codex-remote-control.ts +167 -0
- package/.versions/0.0.11/scripts/coms-claude-bridge.ts +401 -0
- package/.versions/0.0.11/scripts/coms-cli.ts +484 -0
- package/.versions/0.0.11/scripts/coms-hermes-bridge.ts +413 -0
- package/.versions/0.0.11/scripts/fleet.ts +168 -0
- package/.versions/0.0.11/scripts/hermes-monitor-capability-runner.ts +25 -0
- package/.versions/0.0.11/scripts/hermes-monitor-scenario.ts +474 -0
- package/.versions/0.0.11/scripts/hermes-watchdog-capability-probe.ts +45 -0
- package/.versions/0.0.11/scripts/install-hermes-plugin.sh +180 -0
- package/.versions/0.0.11/scripts/lib/claude-bridge-core.ts +165 -0
- package/.versions/0.0.11/scripts/lib/codex-conductor.ts +88 -0
- package/.versions/0.0.11/scripts/lib/codex-remote-control.ts +480 -0
- package/.versions/0.0.11/scripts/lib/coms-envelope.ts +582 -0
- package/.versions/0.0.11/scripts/lib/fake-herdr-server.ts +88 -0
- package/.versions/0.0.11/scripts/lib/fleet-command.ts +111 -0
- package/.versions/0.0.11/scripts/lib/herdr-layout.ts +281 -0
- package/.versions/0.0.11/scripts/lib/hermes-bridge-core.ts +241 -0
- package/.versions/0.0.11/scripts/lib/hermes-monitor-events.ts +1 -0
- package/.versions/0.0.11/scripts/lib/hermes-monitor-herdr.ts +2 -0
- package/.versions/0.0.11/scripts/lib/hermes-monitor-model.ts +3 -0
- package/.versions/0.0.11/scripts/lib/hermes-monitor-registry.ts +2 -0
- package/.versions/0.0.11/scripts/lib/hermes-monitor-socket.ts +2 -0
- package/.versions/0.0.11/scripts/lib/hermes-monitor-store.ts +2 -0
- package/.versions/0.0.11/scripts/lib/monitor-env.ts +134 -0
- package/.versions/0.0.11/scripts/lib/peer-launch.ts +314 -0
- package/.versions/0.0.11/scripts/lib/persona-banner.ts +62 -0
- package/.versions/0.0.11/scripts/lib/spawn-stagger.ts +101 -0
- package/.versions/0.0.11/scripts/lib/team-project.ts +193 -0
- package/.versions/0.0.11/scripts/lib/team-snapshot.ts +147 -0
- package/.versions/0.0.11/scripts/peer-banner.ts +40 -0
- package/.versions/0.0.11/scripts/peer-launch.ts +259 -0
- package/.versions/0.0.11/scripts/team-snapshot.ts +237 -0
- package/.versions/0.0.11/scripts/team-up.ts +360 -0
- package/.versions/0.0.11/skills/_internal/grilling.md +11 -0
- package/.versions/0.0.11/skills/browser-testing-with-devtools/SKILL.md +351 -0
- package/.versions/0.0.11/skills/code-review-and-quality/SKILL.md +381 -0
- package/.versions/0.0.11/skills/compound-learning/SKILL.md +137 -0
- package/.versions/0.0.11/skills/context-engineering/SKILL.md +291 -0
- package/.versions/0.0.11/skills/deprecation-and-migration/SKILL.md +206 -0
- package/.versions/0.0.11/skills/designing-agents/SKILL.md +394 -0
- package/.versions/0.0.11/skills/designing-agents/pi-harness-authoring.md +222 -0
- package/.versions/0.0.11/skills/frontend-ui-engineering/SKILL.md +328 -0
- package/.versions/0.0.11/skills/git-workflow-and-versioning/SKILL.md +316 -0
- package/.versions/0.0.11/skills/guided-workspace-setup/SKILL.md +226 -0
- package/.versions/0.0.11/skills/guided-workspace-setup/companion-manifest.json +38 -0
- package/.versions/0.0.11/skills/idea-refine/SKILL.md +182 -0
- package/.versions/0.0.11/skills/idea-refine/examples.md +238 -0
- package/.versions/0.0.11/skills/idea-refine/frameworks.md +99 -0
- package/.versions/0.0.11/skills/idea-refine/refinement-criteria.md +113 -0
- package/.versions/0.0.11/skills/idea-refine/scripts/idea-refine.sh +15 -0
- package/.versions/0.0.11/skills/incremental-implementation/SKILL.md +287 -0
- package/.versions/0.0.11/skills/interview-me/SKILL.md +226 -0
- package/.versions/0.0.11/skills/orchestration-verification/SKILL.md +181 -0
- package/.versions/0.0.11/skills/peer-coms/SKILL.md +90 -0
- package/.versions/0.0.11/skills/performance-optimization/SKILL.md +350 -0
- package/.versions/0.0.11/skills/planning-and-task-breakdown/SKILL.md +254 -0
- package/.versions/0.0.11/skills/security-and-hardening/SKILL.md +461 -0
- package/.versions/0.0.11/skills/spec-driven-development/SKILL.md +257 -0
- package/.versions/0.0.11/skills/using-agent-skills/SKILL.md +199 -0
- package/.versions/0.0.11/systemd/user/agent-fleet-codex-remote-control.service.in +23 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/LICENSE +21 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/README.md +11 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/api-and-interface-design/SKILL.md +294 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/browser-testing-with-devtools/SKILL.md +317 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/ci-cd-and-automation/SKILL.md +390 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/code-review-and-quality/SKILL.md +396 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/code-simplification/SKILL.md +331 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/context-engineering/SKILL.md +289 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/debugging-and-error-recovery/SKILL.md +300 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/deprecation-and-migration/SKILL.md +247 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/documentation-and-adrs/SKILL.md +278 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/doubt-driven-development/SKILL.md +243 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/frontend-ui-engineering/SKILL.md +328 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/git-workflow-and-versioning/SKILL.md +355 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/idea-refine/SKILL.md +178 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/idea-refine/examples.md +238 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/idea-refine/frameworks.md +99 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/idea-refine/refinement-criteria.md +113 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/idea-refine/scripts/idea-refine.sh +15 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/incremental-implementation/SKILL.md +249 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/interview-me/SKILL.md +225 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/observability-and-instrumentation/SKILL.md +203 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/performance-optimization/SKILL.md +350 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/planning-and-task-breakdown/SKILL.md +234 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/security-and-hardening/SKILL.md +467 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/shipping-and-launch/SKILL.md +310 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/source-driven-development/SKILL.md +194 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/spec-driven-development/SKILL.md +206 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/test-driven-development/SKILL.md +383 -0
- package/.versions/0.0.11/vendor/agent-skills-upstream/skills/using-agent-skills/SKILL.md +191 -0
- package/CHANGELOG.md +7 -0
- package/docs/pi-extensions.md +5 -0
- package/install-manifest.json +1 -1
- package/package.json +1 -1
- package/scripts/lib/monitor-env.ts +15 -1
|
@@ -31,8 +31,9 @@ opens a modal over it:
|
|
|
31
31
|
- **`/af-btw <task>`** — start a side task and open its modal.
|
|
32
32
|
- **`/af-btw`** (no args) — reopen the modal on the last-viewed (or most recent) thread.
|
|
33
33
|
- **`Alt+'`** — reopen the modal. (Chosen because it doesn't collide with a pi
|
|
34
|
-
composer motion the way `Alt+B` does — that's the editor's cursor-word-left.
|
|
35
|
-
|
|
34
|
+
composer motion the way `Alt+B` does — that's the editor's cursor-word-left.) On
|
|
35
|
+
macOS, configure the terminal to send Option as Meta; in Zed set
|
|
36
|
+
`terminal.option_as_meta` to `true`.
|
|
36
37
|
|
|
37
38
|
Once any `/af-btw` command or `Alt+'` has run in a session, the **agent-hub** harness
|
|
38
39
|
footer surfaces an `Alt+' btw` hint next to its `Alt+A view:` hint (via a
|
|
@@ -178,6 +178,9 @@ can be raised.
|
|
|
178
178
|
|
|
179
179
|
## Troubleshooting
|
|
180
180
|
|
|
181
|
+
- **macOS: Option shortcuts type symbols instead of activating** — configure the terminal to send
|
|
182
|
+
Option as Meta. In Zed set `terminal.option_as_meta` to `true`; this is terminal-specific, not an
|
|
183
|
+
OS-wide shortcut change.
|
|
181
184
|
- **`/af-stt doctor` says ffmpeg not found** — install ffmpeg or set `capture.ffmpegPath`.
|
|
182
185
|
- **Linux: no audio** — ensure PulseAudio/PipeWire is running; try `capture.input` of a
|
|
183
186
|
specific source name from `pactl list sources short`.
|
|
@@ -326,6 +326,9 @@ are inert in dashboard mode (use `/af-zoom <name>` there).
|
|
|
326
326
|
> Terminal note: `Alt+[` emits `ESC [` (a CSI prefix) and may be swallowed by some terminals'
|
|
327
327
|
> escape parsers; `Alt+]` and `Alt+\` are the reliable pair. `Alt+↑/↓/←/→` are reserved by the pi
|
|
328
328
|
> editor, which is why the switcher uses the bracket/backslash keys.
|
|
329
|
+
>
|
|
330
|
+
> On macOS, configure the outer terminal to send Option as Meta. For Zed, set
|
|
331
|
+
> `terminal.option_as_meta` to `true`; otherwise Option combinations produce composed characters.
|
|
329
332
|
|
|
330
333
|
## Configuration
|
|
331
334
|
|
|
@@ -0,0 +1,44 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
Invoke the agent-fleet:incremental-implementation skill alongside agent-fleet:test-driven-development.
|
|
6
|
+
|
|
7
|
+
## Modes
|
|
8
|
+
|
|
9
|
+
- **`/build`** — implement the *next* pending task, then stop (careful, one slice at a time).
|
|
10
|
+
- **`/build auto`** — generate the plan if needed, get a single approval, then implement *every* task without stopping between them.
|
|
11
|
+
|
|
12
|
+
`$ARGUMENTS` selects the mode. Treat `auto` (canonical) or `all` as autonomous mode; anything else (or empty) is the default single-task mode. Note: autonomous mode is not faster *per task* — it runs the same test-driven loop — it only removes the human stepping *between* tasks.
|
|
13
|
+
|
|
14
|
+
## Default: one task
|
|
15
|
+
|
|
16
|
+
Pick the next pending task from the plan. Then:
|
|
17
|
+
|
|
18
|
+
1. Read the task's acceptance criteria
|
|
19
|
+
2. Load relevant context (existing code, patterns, types)
|
|
20
|
+
3. Write a failing test for the expected behavior (RED)
|
|
21
|
+
4. Implement the minimum code to pass the test (GREEN)
|
|
22
|
+
5. Run the full test suite to check for regressions
|
|
23
|
+
6. Run the build to verify compilation
|
|
24
|
+
7. Commit with a descriptive message
|
|
25
|
+
8. Mark the task complete and stop
|
|
26
|
+
|
|
27
|
+
## Autonomous: the whole plan (`/build auto`)
|
|
28
|
+
|
|
29
|
+
Use this once a spec exists and you want to collapse plan + build into one run. It removes the manual stepping between tasks — **not** the verification. Every task still earns a passing test and its own commit.
|
|
30
|
+
|
|
31
|
+
1. **Require a spec.** Look only for a spec at a known path: `SPEC.md` at the repo root, `docs/SPEC.md`, or a file under `spec/`. A README or arbitrary doc does **not** count. If none exists, stop and tell the user to run `/spec` first — do not invent requirements.
|
|
32
|
+
2. **Establish a clean baseline.** Run `git status --porcelain`. If there are uncommitted changes outside the expected planning artifacts (`SPEC.md`, `docs/SPEC.md`, `spec/*`, `tasks/plan.md`, `tasks/todo.md`), stop and ask the user to commit, stash, or confirm how to handle them. Autonomous per-task commits must not absorb unrelated local work, or the clean-rollback guarantee breaks.
|
|
33
|
+
3. **Plan if needed.** If there is no `tasks/plan.md`, invoke agent-fleet:planning-and-task-breakdown to generate one.
|
|
34
|
+
4. **Single checkpoint.** Present the full plan and wait for an unambiguous affirmative (e.g. "approve", "go", "yes"). Treat hedged responses ("looks reasonable", "I guess") as **not** approved. This is the only human gate — after approval, run autonomously. If you generated `tasks/plan.md`, commit it as a single preparatory commit now so it doesn't bleed into the first task's commit.
|
|
35
|
+
5. **Execute every task in dependency order.** Use each task's declared dependencies; if they aren't explicit, execute in the order the plan lists them. For each task, run the full default loop above (RED → GREEN → regression → build → commit → mark complete). Stage only the files that task touched plus its task-status update — never `git add -A` blindly — and make one commit per task so any point is a clean rollback.
|
|
36
|
+
6. **Stop and ask the user** (do not push through) when:
|
|
37
|
+
- a test can't be made to pass or the build breaks without an obvious fix → follow agent-fleet:debugging-and-error-recovery
|
|
38
|
+
- the spec is ambiguous, or a task needs a decision the spec doesn't cover
|
|
39
|
+
- a task is high-risk or irreversible — auth/permission changes, destructive data migrations, payments, deletions, deploys, anything touching secrets, **or anything you can't undo with `git revert`** → follow agent-fleet:doubt-driven-development and get explicit sign-off before continuing
|
|
40
|
+
|
|
41
|
+
After the user resolves a blocker, they re-invoke `/build auto` — it resumes from the next pending task.
|
|
42
|
+
7. **Summarize at the end:** tasks completed, tests added, commits made, and anything skipped, flagged, or left for the user.
|
|
43
|
+
|
|
44
|
+
If any step fails, follow the agent-fleet:debugging-and-error-recovery skill.
|
|
@@ -0,0 +1,22 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Simplify code for clarity and maintainability — reduce complexity without changing behavior
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
Invoke the agent-fleet:code-simplification skill.
|
|
6
|
+
|
|
7
|
+
Simplify recently changed code (or the specified scope) while preserving exact behavior:
|
|
8
|
+
|
|
9
|
+
1. Read CLAUDE.md and study project conventions
|
|
10
|
+
2. Identify the target code — recent changes unless a broader scope is specified
|
|
11
|
+
3. Understand the code's purpose, callers, edge cases, and test coverage before touching it
|
|
12
|
+
4. Scan for simplification opportunities:
|
|
13
|
+
- Deep nesting → guard clauses or extracted helpers
|
|
14
|
+
- Long functions → split by responsibility
|
|
15
|
+
- Nested ternaries → if/else or switch
|
|
16
|
+
- Generic names → descriptive names
|
|
17
|
+
- Duplicated logic → shared functions
|
|
18
|
+
- Dead code → remove after confirming
|
|
19
|
+
5. Apply each simplification incrementally — run tests after each change
|
|
20
|
+
6. Verify all tests pass, the build succeeds, and the diff is clean
|
|
21
|
+
|
|
22
|
+
If tests fail after a simplification, revert that change and reconsider. Use `code-review-and-quality` to review the result.
|
|
@@ -0,0 +1,14 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Design and write a new agent persona (agents/), workflow skill (skills/), or pi harness (.pi/harnesses/)
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
Invoke the agent-fleet:designing-agents skill.
|
|
6
|
+
|
|
7
|
+
Begin by understanding what the user wants to author:
|
|
8
|
+
1. Is this a **persona** (a role/lens the agent adopts, e.g. a reviewer or auditor), a **skill** (a repeatable workflow with gated steps and verification), or a **pi harness** (a TypeScript pi extension that reshapes the session — footer, tool-call gate, new command, or orchestrator)?
|
|
9
|
+
2. The one-sentence purpose and when it should be invoked
|
|
10
|
+
3. The framework or steps — dimensions evaluated (persona), ordered workflow (skill), or session surface and events hooked (harness)
|
|
11
|
+
4. Explicit non-goals and scope limits
|
|
12
|
+
5. Output shape — what a typical invocation should produce
|
|
13
|
+
|
|
14
|
+
Then scan the target location (`agents/`, `skills/`, or `.pi/harnesses/`) for overlap, draft the artifact using the matching template — four-block persona structure, the section order from `docs/skill-anatomy.md`, or the harness pattern in `skills/designing-agents/pi-harness-authoring.md` — verify the draft against `references/prompting-patterns.md`, and confirm with the user before writing the file(s).
|
|
@@ -0,0 +1,22 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Scan agent-fleet install targets for broken symlinks, stale persona references, and overrides-file problems, then offer repairs
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
Run the repair pass on its own. `/setup-agent-fleet` offers the same thing as soon as it finds prior install state; this command is when the user wants only that.
|
|
6
|
+
|
|
7
|
+
Run the CLI — do not walk directories or repair files yourself:
|
|
8
|
+
|
|
9
|
+
```
|
|
10
|
+
node <source-root>/bin/cli.js doctor --workspace <workspace> [--agent <agent>] --json
|
|
11
|
+
```
|
|
12
|
+
|
|
13
|
+
Resolve `<source-root>` from `<workspace>/.ai/.agent-fleet-bootstrap.json`, or this command's realpath if it is a symlink, or by asking. Never scan the filesystem for agent-fleet clones.
|
|
14
|
+
|
|
15
|
+
The report has two halves, and they are repaired differently on purpose:
|
|
16
|
+
|
|
17
|
+
- `repairs` — recorded items that are missing, dangling, or linked outside the source root. These are rebuilt through the same `apply()` path `install` writes with, so a repaired file is byte-identical to a freshly installed one.
|
|
18
|
+
- `findings` — what the install record cannot own: broken symlinks in a pre-engine workspace, stale persona names in `.pi/agents/*.yaml` (`reviewer` → `code-reviewer`, `red-team` → `security-auditor`), plus advisory ones. `overrides` and `yaml-shape` findings are **advisory**: report them with "edit by hand" and never fix them, because the fix is always a hand edit of the flagged file.
|
|
19
|
+
|
|
20
|
+
Print the two lists as text, then ask one `AskUserQuestion` — *"Apply the suggested fixes?"* — and on yes re-run with `--fix`. An empty answer or a cancel applies nothing.
|
|
21
|
+
|
|
22
|
+
Exit codes: `0` nothing to repair, `2` repairable issues found (or advisories present, or a repair failed), `1` could not run. Report the counts the CLI returns; do not invent your own.
|
|
@@ -0,0 +1,112 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Orchestrate a config-defined team of subagents — route planner/builder (and more) as a runtime roster, handling NEEDS_RESEARCH and PLAN_FILE handoffs
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
You are the **orchestrator**. The primary agent drives a team of installed Claude Code
|
|
6
|
+
subagents to deliver the task in `$ARGUMENTS`. Subagents cannot nest — **all dispatching is
|
|
7
|
+
yours**.
|
|
8
|
+
|
|
9
|
+
## Roles
|
|
10
|
+
|
|
11
|
+
| Role | What it does |
|
|
12
|
+
|---|---|
|
|
13
|
+
| `researcher` | Always-available read-only recon. Cites `file:line`. Never edits. |
|
|
14
|
+
| `planner` | Writes a plan doc only; ends with `PLAN_FILE: <path>` or pauses on `NEEDS_RESEARCH:`. |
|
|
15
|
+
| `builder` | Implements in small increments; may pause on `NEEDS_RESEARCH:`. |
|
|
16
|
+
| `plan-reviewer` / `code-reviewer` | Read-only; their whole result is findings (no handoff marker). |
|
|
17
|
+
|
|
18
|
+
## Step 0 — Resolve the team
|
|
19
|
+
|
|
20
|
+
1. Read `.claude/orchestrate-teams.yaml` (a map of team-name → ordered persona list).
|
|
21
|
+
2. Resolve team + task from `$ARGUMENTS`:
|
|
22
|
+
- Treat the **first token** as a team name **only** when it is a bare single word that
|
|
23
|
+
exactly matches a config key **and** is followed by the rest of the task. To force a
|
|
24
|
+
team explicitly, the user writes `/orchestrate team=<name> <task>`. Otherwise the
|
|
25
|
+
team is the first key (`default`) and all of `$ARGUMENTS` is the task.
|
|
26
|
+
- **Fallbacks:** if the config is **absent / empty / fails to parse**, fall back to the
|
|
27
|
+
built-in `planner` + `builder` default and **say which fallback fired** (don't proceed
|
|
28
|
+
silently). If a named team is requested but not found, list the available team keys and
|
|
29
|
+
ask rather than guessing.
|
|
30
|
+
3. **Validate personas:** each persona in the resolved team must exist in `.claude/agents/`.
|
|
31
|
+
Skip-with-warning any that don't. If every persona is missing, fall back to the built-in
|
|
32
|
+
default.
|
|
33
|
+
4. List the resolved team back to the user before dispatching.
|
|
34
|
+
|
|
35
|
+
`researcher` / `deep-researcher` are **always available** even when not listed in the team.
|
|
36
|
+
|
|
37
|
+
## Step 1 — The team is a roster, not a fixed pipeline
|
|
38
|
+
|
|
39
|
+
The persona list is the set of specialists you may route to; **you decide the order at
|
|
40
|
+
runtime from the task state** (the listed order is only a sensible starting default). So:
|
|
41
|
+
|
|
42
|
+
- **Skip `planner`** when a usable plan already exists (the user passed a `PLAN_FILE` or
|
|
43
|
+
pointed at one) — go straight to `builder`.
|
|
44
|
+
- **Re-dispatch `researcher` at any point** — after `planner`, mid-build — whenever a
|
|
45
|
+
specialist needs a fact checked, not only as a first step.
|
|
46
|
+
- **Loop back to `planner`** if `builder` surfaces that the plan is wrong.
|
|
47
|
+
|
|
48
|
+
Do **not** enforce a hard `researcher → planner → builder` sequence.
|
|
49
|
+
|
|
50
|
+
## The Verification Contract (applies across every step)
|
|
51
|
+
|
|
52
|
+
Read `skills/orchestration-verification/SKILL.md` before non-trivial work and hold its
|
|
53
|
+
contract for the whole run. Subagents here cannot persist a shared ledger, so **you** keep
|
|
54
|
+
the acceptance assertions in your own working notes and refuse "done" until each is proven.
|
|
55
|
+
|
|
56
|
+
- **Build the assertions first.** Before dispatching `builder` for any non-trivial task,
|
|
57
|
+
convert the request into numbered, tagged assertions (`test` | `runtime-ui` | `code-grep`
|
|
58
|
+
| `manual`, one checkable pass condition each). Pass the relevant assertions **verbatim**
|
|
59
|
+
into each dispatch and advance only on assertions that come back *proven with named
|
|
60
|
+
evidence* — propagation in prose is not verification.
|
|
61
|
+
- **Inventory parity for "behave like X" requests.** When the request is "make X behave like
|
|
62
|
+
existing Y", dispatch `researcher` / `deep-researcher` **first** to enumerate every site
|
|
63
|
+
where the exemplar is special-cased (flags, branches, display, validation, translations,
|
|
64
|
+
fixtures, tests), and turn each site into an assertion covering the *whole* set — otherwise
|
|
65
|
+
the exemplar ships and its siblings are missed.
|
|
66
|
+
- **Require runtime proof for UI assertions.** A `runtime-ui` assertion (visibility,
|
|
67
|
+
placement, "appears in the table") is closed only by an actual runtime observation via
|
|
68
|
+
`browser-testing-with-devtools`, never a static review.
|
|
69
|
+
- **Accept assertion status, not verdicts.** Treat specialist returns as `assertions_proven`
|
|
70
|
+
/ `assertions_unproven` / `assertions_failed`; demote any "approved" claim with no named
|
|
71
|
+
evidence to unproven and re-dispatch it.
|
|
72
|
+
- **Reset on "wrong again".** When the user reports a delivered requirement is wrong again,
|
|
73
|
+
treat prior summaries as suspect, rebuild the affected assertions from the **latest**
|
|
74
|
+
correction (re-running the parity inventory for "behave like" cases), then re-dispatch.
|
|
75
|
+
|
|
76
|
+
## Step 2 — Route to specialists, honouring handoff markers
|
|
77
|
+
|
|
78
|
+
State the chosen next step (and why) before each dispatch, so routing is visible.
|
|
79
|
+
|
|
80
|
+
- `planner` → read its `PLAN_FILE: <path>` and load the plan.
|
|
81
|
+
- `builder` → loop over the plan's `## Task List`, **one task per dispatch**, checking each
|
|
82
|
+
task's acceptance criteria **and the relevant acceptance assertions** before moving on.
|
|
83
|
+
- **Marker-less personas** (`plan-reviewer` / `code-reviewer`) emit no handoff marker —
|
|
84
|
+
their returned report **is** the result; "done" = the report came back, nothing to wait
|
|
85
|
+
for. Fold findings forward; if a `code-reviewer` raised must-fix issues, loop back to
|
|
86
|
+
`builder`.
|
|
87
|
+
|
|
88
|
+
## Step 3 — NEEDS_RESEARCH dispatch (core)
|
|
89
|
+
|
|
90
|
+
Whenever any persona's result contains one or more `NEEDS_RESEARCH: <question>` lines:
|
|
91
|
+
|
|
92
|
+
1. Pause that track.
|
|
93
|
+
2. Dispatch `researcher` (read-only) once per question — in parallel when independent.
|
|
94
|
+
3. Collect the findings.
|
|
95
|
+
4. Resume the paused persona by re-dispatching it with the **original task plus the
|
|
96
|
+
findings inlined**.
|
|
97
|
+
|
|
98
|
+
**Never** answer a `NEEDS_RESEARCH` by guessing.
|
|
99
|
+
|
|
100
|
+
## Step 4 — Reviewer only if present
|
|
101
|
+
|
|
102
|
+
The `default` roster has **no reviewer**. After the final builder task's acceptance criteria
|
|
103
|
+
pass, report completion and **state explicitly that review/verification was not run** and
|
|
104
|
+
which acceptance assertions therefore remain unproven (the user can pick the `full` team or
|
|
105
|
+
run `/review`). When the active team *does* include a reviewer, run it as a normal step and
|
|
106
|
+
require it to report parity across sibling cases, not just the exemplar.
|
|
107
|
+
|
|
108
|
+
## Step 5 — Report
|
|
109
|
+
|
|
110
|
+
Report crisply: **active team**, what changed, which acceptance assertions are **proven (with
|
|
111
|
+
evidence)**, which remain **unproven or failed**, and what's next. Never report "done" while a
|
|
112
|
+
relevant assertion is unproven.
|
|
@@ -0,0 +1,16 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Break work into small verifiable tasks with acceptance criteria and dependency ordering
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
Invoke the agent-fleet:planning-and-task-breakdown skill.
|
|
6
|
+
|
|
7
|
+
Read the existing spec (SPEC.md or equivalent) and the relevant codebase sections. Then:
|
|
8
|
+
|
|
9
|
+
1. Enter plan mode — read only, no code changes
|
|
10
|
+
2. Identify the dependency graph between components
|
|
11
|
+
3. Slice work vertically (one complete path per task, not horizontal layers)
|
|
12
|
+
4. Write tasks with acceptance criteria and verification steps
|
|
13
|
+
5. Add checkpoints between phases
|
|
14
|
+
6. Present the plan for human review
|
|
15
|
+
|
|
16
|
+
Save the plan to the location the `planning-and-task-breakdown` skill defines (default `docs/plans/{area}/PLAN-{prd-name}-{phase}.md`, with the task list embedded — no separate todo file; overridable per project via `.ai/agent-fleet-overrides.md`). Match the project's existing `docs`/`Docs` capitalization.
|
|
@@ -0,0 +1,22 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Load foundational context for the agent-fleet repository
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
# Purpose
|
|
6
|
+
|
|
7
|
+
Orient yourself in **agent-fleet** — a collection of production-grade engineering skills
|
|
8
|
+
for AI coding agents, plus pi extensions, specialist agent personas, and lifecycle
|
|
9
|
+
commands that map to the software development lifecycle.
|
|
10
|
+
|
|
11
|
+
## Workflow
|
|
12
|
+
|
|
13
|
+
1. Run `git ls-files` to see the full project file tree
|
|
14
|
+
2. Read `README.md` and `CLAUDE.md` for the project overview and conventions
|
|
15
|
+
3. Read `docs/skill-anatomy.md` to learn the required skill format
|
|
16
|
+
4. Skim `skills/*/SKILL.md` — the core skills, grouped by lifecycle phase
|
|
17
|
+
(Define → Plan → Build → Verify → Review → Ship)
|
|
18
|
+
5. Read `agents/*.md` — the specialist review personas
|
|
19
|
+
6. Read `docs/pi-extensions.md`, `.pi/extensions/*/README.md` (always-on utilities), and `.pi/harnesses/*/README.md` (selectable session harnesses)
|
|
20
|
+
7. Summarize your understanding: purpose, structure, key files, and entry points
|
|
21
|
+
|
|
22
|
+
Do this directly — read the files yourself rather than delegating to subagents.
|
|
@@ -0,0 +1,16 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Conduct a five-axis code review — correctness, readability, architecture, security, performance
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
Invoke the agent-fleet:code-review-and-quality skill.
|
|
6
|
+
|
|
7
|
+
Review the current changes (staged or recent commits) across all five axes:
|
|
8
|
+
|
|
9
|
+
1. **Correctness** — Does it match the spec? Edge cases handled? Tests adequate?
|
|
10
|
+
2. **Readability** — Clear names? Straightforward logic? Well-organized?
|
|
11
|
+
3. **Architecture** — Follows existing patterns? Clean boundaries? Right abstraction level?
|
|
12
|
+
4. **Security** — Input validated? Secrets safe? Auth checked? (Use security-and-hardening skill)
|
|
13
|
+
5. **Performance** — No N+1 queries? No unbounded ops? (Use performance-optimization skill)
|
|
14
|
+
|
|
15
|
+
Categorize findings as Critical, Important, or Suggestion.
|
|
16
|
+
Output a structured review with specific file:line references and fix recommendations.
|
|
@@ -0,0 +1,15 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Install/status the Hermes liaison or turn its Telegram ask_user bridge on/off
|
|
3
|
+
argument-hint: "<install|status|on|off> [telegram-id] [--profile NAME] [--force] [--restart]"
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
Run the deterministic Agent Fleet controller with the arguments from `$ARGUMENTS`. Supported forms are:
|
|
7
|
+
|
|
8
|
+
```text
|
|
9
|
+
set-hermes-telegram install [--profile NAME] [--force] [--restart]
|
|
10
|
+
set-hermes-telegram status [--profile NAME]
|
|
11
|
+
set-hermes-telegram on <telegram-id[:topic-id]> [--profile NAME]
|
|
12
|
+
set-hermes-telegram off <telegram-id[:topic-id]> [--profile NAME]
|
|
13
|
+
```
|
|
14
|
+
|
|
15
|
+
Use `node bin/cli.js set-hermes-telegram ...` when the checkout-local CLI exists; otherwise use `npx --no-install agent-fleet set-hermes-telegram ...`. Pass parsed values as separately quoted shell arguments. If neither CLI exists, report that Agent Fleet must be installed or updated. Do not reproduce installation or Herdr lifecycle with ad-hoc commands, do not bypass a `--force` refusal, and do not send a test Telegram message. Return the controller output verbatim.
|
|
@@ -0,0 +1,6 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Inspect or safely install the fail-closed Hermes watchdog
|
|
3
|
+
argument-hint: "<status|install|update|uninstall> [--profile NAME] [--force] [--dry-run]"
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
Ask for confirmation before install, update, uninstall, or force. Use only the deterministic Agent Fleet watchdog controller with the supplied separately quoted arguments. `status` is read-only; `--dry-run` writes nothing. Never start/restart a gateway or watcher, change tools, send a message, initiate a watch, or infer Gate O/origin routing. The packaged skill remains journal-only/dormant until independently reviewed live Gate O evidence exists.
|
|
@@ -0,0 +1,17 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Guided setup — install agent-fleet artifacts into a workspace for a chosen coding agent
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
Invoke the agent-fleet:guided-workspace-setup skill and follow it.
|
|
6
|
+
|
|
7
|
+
Run the guided install for a target workspace. If the user passed a workspace path, use it; otherwise ask. Confirm the coding agent (`claude-code` here unless the user says otherwise).
|
|
8
|
+
|
|
9
|
+
The skill is a front-end over the `agent-fleet` CLI's installer engine: `verify --json` supplies the menu (groups, profiles, per-item state), and `install` / `upgrade` / `uninstall` / `doctor --fix` do every write. **Do not copy, symlink, or delete an install target yourself** — the CLI records ownership in `.ai/agent-fleet-state.json`, and anything written by hand is invisible to every later run. Artifacts install as copies; never ask copy-vs-symlink and never pass `--method`.
|
|
10
|
+
|
|
11
|
+
Two things are yours rather than the CLI's: drafting `.ai/agent-fleet-overrides.md` from a scan of the project, and the `pi-voice-stt` provider Q&A.
|
|
12
|
+
|
|
13
|
+
Drive every decision through `AskUserQuestion` (max 4 options per call), never a printed table awaiting a free-text reply. Open with the Express question backed by the manifest's profiles; group screens run only on `Custom`; drill-ins appear only behind `Customise`. Option titles carry `<name> ★ [state]` and descriptions say what picking it does in plain words. Leaving an installed item unpicked keeps it — removal is its own explicit screen and runs `uninstall`. Cancel is a no-op everywhere except the final confirmation.
|
|
14
|
+
|
|
15
|
+
If `verify` reports findings or broken items, offer `doctor --fix` before the menu — a broken workspace makes the menu lie about what is installed.
|
|
16
|
+
|
|
17
|
+
Print the plan as compact action-grouped lines before confirming, then confirm once with `Apply — and remove the installer commands` (default) / `Apply — keep the installer commands` / `Adjust picks` / `Cancel`. Exit `3` from the CLI means conflicts: show the `.new` files it wrote and let the user decide — never pick a side for them. Relay `operator` and `external` steps verbatim; the CLI performs neither, and neither do you.
|
|
@@ -0,0 +1,72 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Run the pre-launch checklist via parallel fan-out to specialist personas, then synthesize a go/no-go decision
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
Invoke the agent-fleet:shipping-and-launch skill.
|
|
6
|
+
|
|
7
|
+
`/ship` is a **fan-out orchestrator**. It runs three specialist personas in parallel against the current change, then merges their reports into a single go/no-go decision with a rollback plan. The personas operate independently — no shared state, no ordering — which is what makes parallel execution safe and useful here.
|
|
8
|
+
|
|
9
|
+
## Phase A — Parallel fan-out
|
|
10
|
+
|
|
11
|
+
Spawn three subagents concurrently using the Agent tool. **Issue all three Agent tool calls in a single assistant turn so they execute in parallel** — sequential calls defeat the purpose of this command.
|
|
12
|
+
|
|
13
|
+
In Claude Code, each call passes `subagent_type` matching the persona's `name` field:
|
|
14
|
+
|
|
15
|
+
1. **`code-reviewer`** — Run a five-axis review (correctness, readability, architecture, security, performance) on the staged changes or recent commits. Output the standard review template.
|
|
16
|
+
2. **`security-auditor`** — Run a vulnerability and threat-model pass. Check OWASP Top 10, secrets handling, auth/authz, dependency CVEs. Output the standard audit report.
|
|
17
|
+
3. **`test-engineer`** — Analyze test coverage for the change. Identify gaps in happy path, edge cases, error paths, and concurrency scenarios. Output the standard coverage analysis.
|
|
18
|
+
|
|
19
|
+
In other harnesses without an Agent tool, invoke each persona's system prompt sequentially and treat their outputs as if returned in parallel — the merge phase still works.
|
|
20
|
+
|
|
21
|
+
Constraints (from Claude Code's subagent model):
|
|
22
|
+
- Subagents cannot spawn other subagents — do not let one persona delegate to another.
|
|
23
|
+
- Each subagent gets its own context window and returns only its report to this main session.
|
|
24
|
+
- If you need teammates that talk to each other instead of just reporting back, use Claude Code Agent Teams and reference these personas as teammate types (see `references/orchestration-patterns.md`).
|
|
25
|
+
|
|
26
|
+
**Persona resolution.** If you've defined your own `code-reviewer`, `security-auditor`, or `test-engineer` in `.claude/agents/` or `~/.claude/agents/`, those take precedence over this plugin's versions — `/ship` picks up your customizations automatically. This is intentional: plugin subagents sit at the bottom of Claude Code's scope priority table, so user-level definitions win by design.
|
|
27
|
+
|
|
28
|
+
## Phase B — Merge in main context
|
|
29
|
+
|
|
30
|
+
Once all three reports are back, the main agent (not a sub-persona) synthesizes them:
|
|
31
|
+
|
|
32
|
+
1. **Code Quality** — Aggregate Critical/Important findings from `code-reviewer` and any failing tests, lint, or build output. Resolve duplicates between reviewers.
|
|
33
|
+
2. **Security** — Promote any Critical/High `security-auditor` findings to launch blockers. Cross-reference with `code-reviewer`'s security axis.
|
|
34
|
+
3. **Performance** — Pull from `code-reviewer`'s performance axis; cross-check Core Web Vitals if applicable.
|
|
35
|
+
4. **Accessibility** — Verify keyboard nav, screen reader support, contrast (not covered by the three personas — handle directly here, or invoke the accessibility checklist).
|
|
36
|
+
5. **Infrastructure** — Env vars, migrations, monitoring, feature flags. Verify directly.
|
|
37
|
+
6. **Documentation** — README, ADRs, changelog. Verify directly.
|
|
38
|
+
|
|
39
|
+
## Phase C — Decision and rollback
|
|
40
|
+
|
|
41
|
+
Produce a single output:
|
|
42
|
+
|
|
43
|
+
```markdown
|
|
44
|
+
## Ship Decision: GO | NO-GO
|
|
45
|
+
|
|
46
|
+
### Blockers (must fix before ship)
|
|
47
|
+
- [Source persona: Critical finding + file:line]
|
|
48
|
+
|
|
49
|
+
### Recommended fixes (should fix before ship)
|
|
50
|
+
- [Source persona: Important finding + file:line]
|
|
51
|
+
|
|
52
|
+
### Acknowledged risks (shipping anyway)
|
|
53
|
+
- [Risk + mitigation]
|
|
54
|
+
|
|
55
|
+
### Rollback plan
|
|
56
|
+
- Trigger conditions: [what signals would prompt rollback]
|
|
57
|
+
- Rollback procedure: [exact steps]
|
|
58
|
+
- Recovery time objective: [target]
|
|
59
|
+
|
|
60
|
+
### Specialist reports (full)
|
|
61
|
+
- [code-reviewer report]
|
|
62
|
+
- [security-auditor report]
|
|
63
|
+
- [test-engineer report]
|
|
64
|
+
```
|
|
65
|
+
|
|
66
|
+
## Rules
|
|
67
|
+
|
|
68
|
+
1. The three Phase A personas run in parallel — never sequentially.
|
|
69
|
+
2. Personas do not call each other. The main agent merges in Phase B.
|
|
70
|
+
3. The rollback plan is mandatory before any GO decision.
|
|
71
|
+
4. If any persona returns a Critical finding, the default verdict is NO-GO unless the user explicitly accepts the risk.
|
|
72
|
+
5. **Skip the fan-out only if all of the following are true:** the change touches 2 files or fewer, the diff is under 50 lines, and it does not touch auth, payments, data access, or config/env. Otherwise, default to fan-out. `/ship` is designed for production-bound changes — when the blast radius is non-trivial, run the parallel review even if the diff looks small.
|
|
@@ -0,0 +1,15 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Start spec-driven development — write a structured specification before writing code
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
Invoke the agent-fleet:spec-driven-development skill.
|
|
6
|
+
|
|
7
|
+
Begin by understanding what the user wants to build. Ask clarifying questions about:
|
|
8
|
+
1. The objective and target users
|
|
9
|
+
2. Core features and acceptance criteria
|
|
10
|
+
3. Tech stack preferences and constraints
|
|
11
|
+
4. Known boundaries (what to always do, ask first about, and never do)
|
|
12
|
+
|
|
13
|
+
Then generate a structured spec covering all six core areas: objective, commands, project structure, code style, testing strategy, and boundaries.
|
|
14
|
+
|
|
15
|
+
Save the spec to the location the `spec-driven-development` skill defines (default `docs/prds/{area}/PRD{n}-{topic}.md`; overridable per project via `.ai/agent-fleet-overrides.md`). Confirm with the user before proceeding.
|
|
@@ -0,0 +1,19 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Run TDD workflow — write failing tests, implement, verify. For bugs, use the Prove-It pattern.
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
Invoke the agent-fleet:test-driven-development skill.
|
|
6
|
+
|
|
7
|
+
For new features:
|
|
8
|
+
1. Write tests that describe the expected behavior (they should FAIL)
|
|
9
|
+
2. Implement the code to make them pass
|
|
10
|
+
3. Refactor while keeping tests green
|
|
11
|
+
|
|
12
|
+
For bug fixes (Prove-It pattern):
|
|
13
|
+
1. Write a test that reproduces the bug (must FAIL)
|
|
14
|
+
2. Confirm the test fails
|
|
15
|
+
3. Implement the fix
|
|
16
|
+
4. Confirm the test passes
|
|
17
|
+
5. Run the full test suite for regressions
|
|
18
|
+
|
|
19
|
+
For browser-related issues, also invoke agent-fleet:browser-testing-with-devtools to verify with Chrome DevTools MCP.
|
|
@@ -0,0 +1,32 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Run a web performance audit via the web-performance-auditor persona
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
`/webperf` targets web applications specifically. Do not use it for utility libraries, CLIs, or server-only code with no browser-facing output.
|
|
6
|
+
|
|
7
|
+
## Determine the mode
|
|
8
|
+
|
|
9
|
+
**Deep mode** — activate when any of these is available:
|
|
10
|
+
- A Lighthouse JSON report file (e.g. `npx lighthouse <url> --output json --output-path ./report.json`, or `npx -p chrome-devtools-mcp chrome-devtools lighthouse_audit --output-format=json` from the Chrome DevTools MCP CLI)
|
|
11
|
+
- A PageSpeed Insights JSON response (includes Lighthouse + CrUX)
|
|
12
|
+
- A CrUX API response (requires `CRUX_API_KEY` or `GOOGLE_API_KEY`)
|
|
13
|
+
- A DevTools performance trace
|
|
14
|
+
- A live URL plus the `chrome-devtools` MCP server configured in the harness (the agent can capture metrics directly via `lighthouse_audit` and `performance_*` tools)
|
|
15
|
+
- The Chrome DevTools MCP CLI invoked locally (via `npx -p chrome-devtools-mcp chrome-devtools <tool>` or after `npm i -g chrome-devtools-mcp`) — the user runs commands like `chrome-devtools lighthouse_audit --output-format=json` and passes the JSON output to the agent
|
|
16
|
+
|
|
17
|
+
**Quick mode** — default when none of the above are available. The agent scans source code for structural anti-patterns and labels every finding as `potential impact`.
|
|
18
|
+
|
|
19
|
+
## Run the audit
|
|
20
|
+
|
|
21
|
+
Spawn the `web-performance-auditor` subagent. Pass it explicitly:
|
|
22
|
+
|
|
23
|
+
- The files, components, or diff under review
|
|
24
|
+
- Any artifact paths (Lighthouse JSON, PSI JSON, CrUX response, trace) or pasted JSON content
|
|
25
|
+
- The target URL or page name when known
|
|
26
|
+
- A note on which mode you expect (Quick or Deep), so the agent surfaces missing inputs if Deep was intended
|
|
27
|
+
|
|
28
|
+
The subagent returns a scorecard (only populated with sourced values), a ranked list of findings, positive observations, and proactive recommendations.
|
|
29
|
+
|
|
30
|
+
## Output
|
|
31
|
+
|
|
32
|
+
Return the full audit report to the user. No synthesis or merge step is needed — this is a single-persona command.
|
|
@@ -0,0 +1,24 @@
|
|
|
1
|
+
# Teams for /orchestrate. The main session reads this file and routes the
|
|
2
|
+
# named team as a ROSTER (runtime-decided order), not a fixed pipeline.
|
|
3
|
+
#
|
|
4
|
+
# Rules the /orchestrate command relies on:
|
|
5
|
+
# 1. First key is the default team (used when no team argument is given).
|
|
6
|
+
# 2. researcher / deep-researcher are NOT listed — they are always available
|
|
7
|
+
# out-of-band for NEEDS_RESEARCH dispatch (mirrors pi's spawn_research).
|
|
8
|
+
# 3. Every listed persona must exist in .claude/agents/ or it is skipped with
|
|
9
|
+
# a warning.
|
|
10
|
+
#
|
|
11
|
+
# Switch at runtime: /orchestrate <team> "<task>" (parallels pi's /agents-team).
|
|
12
|
+
|
|
13
|
+
default:
|
|
14
|
+
- planner
|
|
15
|
+
- builder
|
|
16
|
+
|
|
17
|
+
full:
|
|
18
|
+
- planner
|
|
19
|
+
- plan-reviewer
|
|
20
|
+
- builder
|
|
21
|
+
- code-reviewer
|
|
22
|
+
|
|
23
|
+
hotfix:
|
|
24
|
+
- builder
|
|
@@ -0,0 +1,17 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Implement the next task incrementally - build, test, verify, commit
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
Invoke the `incremental-implementation` skill and the `test-driven-development` skill via the `skill` tool.
|
|
6
|
+
|
|
7
|
+
Pick the next pending task from the plan. For each task:
|
|
8
|
+
|
|
9
|
+
1. Read the task's acceptance criteria.
|
|
10
|
+
2. Load relevant context: existing code, patterns, and types.
|
|
11
|
+
3. Write a failing test for the expected behavior.
|
|
12
|
+
4. Implement the minimum code to pass the test.
|
|
13
|
+
5. Run the relevant test suite to check for regressions.
|
|
14
|
+
6. Run the build to verify compilation.
|
|
15
|
+
7. Mark the task complete and move to the next one.
|
|
16
|
+
|
|
17
|
+
If any step fails, invoke the `debugging-and-error-recovery` skill via the `skill` tool.
|
|
@@ -0,0 +1,16 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Simplify code for clarity and maintainability without changing behavior
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
Invoke the `code-simplification` skill via the `skill` tool.
|
|
6
|
+
|
|
7
|
+
Simplify recently changed code, or the scope specified in `$ARGUMENTS`, while preserving exact behavior:
|
|
8
|
+
|
|
9
|
+
1. Read the project's agent instructions and study project conventions.
|
|
10
|
+
2. Identify the target code: recent changes unless a broader scope is specified.
|
|
11
|
+
3. Understand the code's purpose, callers, edge cases, and test coverage before touching it.
|
|
12
|
+
4. Scan for simplification opportunities: deep nesting, long functions, nested ternaries, generic names, duplicated logic, or dead code.
|
|
13
|
+
5. Apply each simplification incrementally and run relevant tests after each change.
|
|
14
|
+
6. Verify tests pass, the build succeeds, and the diff is clean.
|
|
15
|
+
|
|
16
|
+
If tests fail after a simplification, revert only that simplification and reconsider. Invoke `code-review-and-quality` via the `skill` tool to review the result.
|
|
@@ -0,0 +1,16 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Capture this session's lessons into the project's rules and docs — compound engineering pass
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
Invoke the `compound-learning` skill via the `skill` tool.
|
|
6
|
+
|
|
7
|
+
Capture this session's lessons into the project's own rules (HOW) and docs (WHAT/WHY), optionally focused on `$ARGUMENTS`:
|
|
8
|
+
|
|
9
|
+
1. Resolve the targets: read `.ai/agent-fleet-overrides.md` — the `## agent-hub` (legacy `## agent-team`) section's `rules:` and `docs:` keys name the rule folders and documentation entry points. If absent, locate an existing rules/docs tree and confirm it with the user; never invent a new tree.
|
|
10
|
+
2. Gather the evidence: this conversation (user corrections, decisions, rejected approaches), the session's `git diff` / `git log`, and any review findings produced during the session.
|
|
11
|
+
3. Extract at most 5 candidate lessons — each one imperative sentence plus a one-line Why (the failure it prevents) and a one-line Evidence (what happened this session). Classify each as rule, doc, or neither; the default verdict is neither.
|
|
12
|
+
4. Dedupe index-first: read the rules tree's `README.md`/`index.md` manifest, grep for existing coverage, and prefer sharpening an existing rule in place over adding a new one.
|
|
13
|
+
5. Propose the surviving lessons — target file, Why, Evidence, and the exact diff — and wait for approval. The user filters preferences-of-the-moment from durable policy.
|
|
14
|
+
6. Apply the approved diffs as minimal edits to existing files (at most 1 new file, registered in the tree's index), verify links and indexes still resolve, and report the changes file by file.
|
|
15
|
+
|
|
16
|
+
Run this at the end of a session, before the context is gone. If nothing rises to a lesson, say so and stop — compounding a smooth session produces filler.
|
|
@@ -0,0 +1,15 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Design and write a new agent persona, workflow skill, or pi harness
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
Invoke the `designing-agents` skill via the `skill` tool.
|
|
6
|
+
|
|
7
|
+
Begin by understanding what the user wants to author:
|
|
8
|
+
|
|
9
|
+
1. Is this a persona (a role or lens the agent adopts), a skill (a repeatable workflow with gated steps and verification), or a pi harness (a TypeScript pi extension that reshapes the session)?
|
|
10
|
+
2. What is the one-sentence purpose and when should it be invoked?
|
|
11
|
+
3. What framework or steps should it follow?
|
|
12
|
+
4. What are the explicit non-goals and scope limits?
|
|
13
|
+
5. What output shape should a typical invocation produce?
|
|
14
|
+
|
|
15
|
+
Then scan the target location — `agents/`, `skills/`, or `.pi/harnesses/` — for overlap. Draft the artifact using the matching template, verify the draft against prompting guidance when available, and confirm with the user before writing the file(s).
|