@chankov/agent-fleet 0.0.11 → 1.0.0
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/agent-fleet-update-check/README.md +4 -4
- package/.pi/extensions/btw/README.md +26 -25
- package/.pi/extensions/btw/index.ts +80 -83
- package/.pi/extensions/pi-voice-stt/README.md +4 -3
- package/.pi/extensions/pi-voice-stt/config.ts +1 -1
- package/.pi/harnesses/agent-hub/README.md +106 -54
- package/.pi/harnesses/agent-hub/backend-policy.js +25 -4
- package/.pi/harnesses/agent-hub/footer.ts +4 -0
- package/.pi/harnesses/agent-hub/helpers.ts +18 -0
- package/.pi/harnesses/agent-hub/index.ts +537 -369
- package/.pi/harnesses/agent-hub/monitor-session-bridge.ts +10 -1
- package/.pi/harnesses/agent-hub/package.json +1 -1
- package/.pi/harnesses/agent-hub/peer-spawn-plan.ts +116 -0
- package/.pi/harnesses/agent-hub/posture.ts +103 -0
- package/.pi/harnesses/ask-user-remote/README.md +37 -3
- package/.pi/harnesses/ask-user-remote/index.ts +173 -17
- package/.pi/harnesses/coms/package.json +1 -1
- package/.pi/harnesses/damage-control-continue/package.json +1 -1
- package/.pi/harnesses/lib/fleet-dashboard-ops.ts +118 -0
- package/.pi/harnesses/lib/fleet-dashboard-view.ts +140 -0
- package/.pi/harnesses/lib/fleet-detail-view.ts +43 -0
- package/.pi/harnesses/lib/fleet-overlay.ts +26 -0
- package/.pi/harnesses/lib/fleet-panel.ts +34 -0
- package/.pi/harnesses/lib/fleet-read-model.ts +131 -0
- package/.pi/harnesses/lib/fleet-selection.ts +24 -0
- package/.pi/harnesses/package-lock.json +2011 -0
- package/.pi/harnesses/package.json +1 -0
- package/.versions/0.0.11/.pi/extensions/agent-fleet-update-check/README.md +4 -4
- package/.versions/0.0.11/.pi/extensions/pi-voice-stt/README.md +4 -3
- package/.versions/0.0.11/.pi/extensions/pi-voice-stt/config.ts +1 -1
- package/.versions/0.0.11/.pi/harnesses/agent-hub/monitor-session-bridge.ts +10 -1
- package/.versions/0.0.11/.pi/harnesses/ask-user-remote/README.md +37 -3
- package/.versions/0.0.11/.pi/harnesses/ask-user-remote/index.ts +173 -17
- package/.versions/0.0.11/.pi/harnesses/package-lock.json +2011 -0
- package/.versions/0.0.11/.pi/harnesses/package.json +1 -0
- package/.versions/0.0.11/docs/ARCHITECTURE.md +6 -8
- package/.versions/0.0.11/docs/agent-fleet-setup.md +17 -43
- package/.versions/0.0.11/docs/claude-code-coms-bridge.md +20 -2
- package/.versions/0.0.11/docs/coms-hermes-bridge.md +1 -1
- package/.versions/0.0.11/docs/getting-started.md +26 -237
- package/.versions/0.0.11/docs/npm-install.md +60 -478
- package/.versions/0.0.11/docs/pi-extensions.md +4 -4
- package/.versions/0.0.11/docs/pi-setup.md +37 -551
- package/.versions/0.0.11/hermes/README.md +1 -1
- package/.versions/0.0.11/install-manifest.json +375 -1247
- package/.versions/0.0.11/justfile +13 -6
- package/.versions/0.0.11/manifest-meta.json +543 -134
- package/.versions/0.0.11/scripts/lib/fleet-command.ts +8 -0
- package/.versions/0.0.11/scripts/lib/monitor-env.ts +18 -6
- package/.versions/0.0.11/skills/designing-agents/SKILL.md +1 -1
- package/.versions/0.0.11/skills/designing-agents/pi-harness-authoring.md +1 -1
- package/.versions/1.0.0/.pi/agents/dispatch-policy.yaml +32 -0
- package/.versions/1.0.0/.pi/agents/model-profiles.yaml +27 -0
- package/.versions/1.0.0/.pi/agents/peers.yaml +142 -0
- package/.versions/1.0.0/.pi/agents/teams.yaml +41 -0
- package/.versions/1.0.0/.pi/damage-control-rules.yaml +297 -0
- package/.versions/1.0.0/.pi/extensions/agent-fleet-update-check/README.md +57 -0
- package/.versions/1.0.0/.pi/extensions/agent-fleet-update-check/index.ts +161 -0
- package/.versions/1.0.0/.pi/extensions/agent-fleet-update-check/package.json +6 -0
- package/.versions/1.0.0/.pi/extensions/btw/README.md +120 -0
- package/.versions/1.0.0/.pi/extensions/btw/index.ts +914 -0
- package/.versions/1.0.0/.pi/extensions/btw/package.json +6 -0
- package/.versions/1.0.0/.pi/extensions/btw/state.js +179 -0
- package/.versions/1.0.0/.pi/extensions/chrome-devtools-mcp/README.md +55 -0
- package/.versions/1.0.0/.pi/extensions/chrome-devtools-mcp/index.ts +93 -0
- package/.versions/1.0.0/.pi/extensions/chrome-devtools-mcp/package.json +6 -0
- package/.versions/1.0.0/.pi/extensions/compact-and-continue/README.md +42 -0
- package/.versions/1.0.0/.pi/extensions/compact-and-continue/index.ts +120 -0
- package/.versions/1.0.0/.pi/extensions/compact-and-continue/package.json +6 -0
- package/.versions/1.0.0/.pi/extensions/mcp-bridge/README.md +46 -0
- package/.versions/1.0.0/.pi/extensions/mcp-bridge/index.ts +206 -0
- package/.versions/1.0.0/.pi/extensions/mcp-bridge/package.json +6 -0
- package/.versions/1.0.0/.pi/extensions/package-lock.json +1143 -0
- package/.versions/1.0.0/.pi/extensions/package.json +9 -0
- package/.versions/1.0.0/.pi/extensions/pi-voice-stt/README.md +205 -0
- package/.versions/1.0.0/.pi/extensions/pi-voice-stt/config.ts +198 -0
- package/.versions/1.0.0/.pi/extensions/pi-voice-stt/examples/stt.json +35 -0
- package/.versions/1.0.0/.pi/extensions/pi-voice-stt/index.ts +248 -0
- package/.versions/1.0.0/.pi/extensions/pi-voice-stt/package.json +6 -0
- package/.versions/1.0.0/.pi/extensions/pi-voice-stt/providers.ts +214 -0
- package/.versions/1.0.0/.pi/extensions/pi-voice-stt/recorder.ts +158 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/README.md +1056 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/access-approval.ts +135 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/artifacts.js +146 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/assertion-ledger.js +58 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/backend-policy.js +174 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/context-window.js +106 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/delegate.ts +435 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/docs-lane.js +122 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/drift-watchdog.js +211 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/evidence-rules.js +96 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/external-blocker.js +85 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/footer.ts +35 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/helpers.ts +266 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/index.ts +9279 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/monitor-control.ts +9 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/monitor-invoke-journal.ts +131 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/monitor-invoke.ts +92 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/monitor-lifecycle.ts +13 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/monitor-publisher.ts +59 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/monitor-recovery.ts +3 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/monitor-runtime.ts +3 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/monitor-session-bridge.ts +266 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/package.json +7 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/peer-spawn-plan.ts +116 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/posture.ts +103 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/provider-semaphore.js +138 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/research-retention.js +34 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/research-watchdog.ts +40 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/return-contract.js +293 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/return-extract.js +75 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/review-findings.js +102 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/run-budget.js +479 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/run-namespace.js +87 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/safety-routing.ts +22 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/scope-gate.js +103 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/session-health.js +110 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/spawn.ts +354 -0
- package/.versions/1.0.0/.pi/harnesses/agent-hub/version.ts +42 -0
- package/.versions/1.0.0/.pi/harnesses/ask-user-remote/README.md +53 -0
- package/.versions/1.0.0/.pi/harnesses/ask-user-remote/index.ts +477 -0
- package/.versions/1.0.0/.pi/harnesses/ask-user-remote/race-core.js +106 -0
- package/.versions/1.0.0/.pi/harnesses/coms/README.md +100 -0
- package/.versions/1.0.0/.pi/harnesses/coms/index.ts +1767 -0
- package/.versions/1.0.0/.pi/harnesses/coms/package.json +7 -0
- package/.versions/1.0.0/.pi/harnesses/coms/version.ts +42 -0
- package/.versions/1.0.0/.pi/harnesses/damage-control-continue/README.md +124 -0
- package/.versions/1.0.0/.pi/harnesses/damage-control-continue/index.ts +536 -0
- package/.versions/1.0.0/.pi/harnesses/damage-control-continue/package.json +7 -0
- package/.versions/1.0.0/.pi/harnesses/damage-control-continue/version.ts +42 -0
- package/.versions/1.0.0/.pi/harnesses/lib/coms-registry-entry.ts +94 -0
- package/.versions/1.0.0/.pi/harnesses/lib/damage-control-shared.ts +197 -0
- package/.versions/1.0.0/.pi/harnesses/lib/fleet-dashboard-ops.ts +118 -0
- package/.versions/1.0.0/.pi/harnesses/lib/fleet-dashboard-view.ts +140 -0
- package/.versions/1.0.0/.pi/harnesses/lib/fleet-detail-view.ts +43 -0
- package/.versions/1.0.0/.pi/harnesses/lib/fleet-overlay.ts +26 -0
- package/.versions/1.0.0/.pi/harnesses/lib/fleet-panel.ts +34 -0
- package/.versions/1.0.0/.pi/harnesses/lib/fleet-read-model.ts +131 -0
- package/.versions/1.0.0/.pi/harnesses/lib/fleet-selection.ts +24 -0
- package/.versions/1.0.0/.pi/harnesses/lib/herdr-client.ts +472 -0
- package/.versions/1.0.0/.pi/harnesses/lib/herdr-presence.ts +399 -0
- package/.versions/1.0.0/.pi/harnesses/lib/hermes-monitor-events.ts +136 -0
- package/.versions/1.0.0/.pi/harnesses/lib/hermes-monitor-herdr.ts +28 -0
- package/.versions/1.0.0/.pi/harnesses/lib/hermes-monitor-model.ts +18 -0
- package/.versions/1.0.0/.pi/harnesses/lib/hermes-monitor-registry.ts +6 -0
- package/.versions/1.0.0/.pi/harnesses/lib/hermes-monitor-socket.ts +163 -0
- package/.versions/1.0.0/.pi/harnesses/lib/hermes-monitor-store.ts +31 -0
- package/.versions/1.0.0/.pi/harnesses/lib/spawned-peers.js +190 -0
- package/.versions/1.0.0/.pi/harnesses/package-lock.json +2046 -0
- package/.versions/1.0.0/.pi/harnesses/package.json +10 -0
- package/.versions/1.0.0/.pi/prompts/af-build.md +24 -0
- package/{.claude/commands/code-simplify.md → .versions/1.0.0/.pi/prompts/af-code-simplify.md} +3 -3
- package/{.claude/commands/plan.md → .versions/1.0.0/.pi/prompts/af-plan.md} +1 -1
- package/.versions/{0.0.11/.claude/commands/review.md → 1.0.0/.pi/prompts/af-review.md} +3 -3
- package/.versions/1.0.0/.pi/prompts/af-set-hermes-watchdog.md +6 -0
- package/.versions/1.0.0/.pi/prompts/af-ship.md +17 -0
- package/.versions/{0.0.11/.claude/commands/spec.md → 1.0.0/.pi/prompts/af-spec.md} +1 -1
- package/.versions/{0.0.11/.claude/commands/test.md → 1.0.0/.pi/prompts/af-test.md} +2 -2
- package/.versions/1.0.0/.pi/skills/bowser/SKILL.md +145 -0
- package/.versions/1.0.0/.version +1 -0
- package/.versions/1.0.0/agents/architect.md +24 -0
- package/.versions/1.0.0/agents/bowser.md +27 -0
- package/.versions/1.0.0/agents/builder.md +54 -0
- package/.versions/1.0.0/agents/code-reviewer.md +208 -0
- package/.versions/1.0.0/agents/deep-researcher.md +32 -0
- package/.versions/1.0.0/agents/documenter.md +18 -0
- package/.versions/1.0.0/agents/orchestrator.md +72 -0
- package/.versions/1.0.0/agents/plan-reviewer.md +83 -0
- package/.versions/1.0.0/agents/planner.md +70 -0
- package/.versions/1.0.0/agents/releaser.md +24 -0
- package/.versions/1.0.0/agents/researcher.md +28 -0
- package/.versions/1.0.0/agents/security-auditor.md +167 -0
- package/.versions/1.0.0/agents/test-engineer.md +153 -0
- package/.versions/1.0.0/agents/web-debugger.md +43 -0
- package/.versions/1.0.0/agents/web-performance-auditor.md +193 -0
- package/.versions/1.0.0/codex/CONDUCTOR.md +148 -0
- package/.versions/1.0.0/docs/ARCHITECTURE.md +337 -0
- package/.versions/1.0.0/docs/agent-fleet-setup.md +437 -0
- package/.versions/1.0.0/docs/claude-code-coms-bridge.md +128 -0
- package/.versions/1.0.0/docs/codex-remote-conductor.md +170 -0
- package/.versions/1.0.0/docs/coms-hermes-bridge.md +189 -0
- package/.versions/1.0.0/docs/getting-started.md +98 -0
- package/.versions/1.0.0/docs/npm-install.md +292 -0
- package/.versions/1.0.0/docs/pi-extensions.md +412 -0
- package/.versions/1.0.0/docs/pi-setup.md +74 -0
- package/.versions/1.0.0/docs/skill-anatomy.md +150 -0
- package/.versions/1.0.0/hermes/README.md +347 -0
- package/.versions/1.0.0/hermes/desktop-plugins/agent-fleet-herdr/plugin.js +1291 -0
- package/.versions/1.0.0/hermes/desktop-plugins/agent-fleet-herdr/presentation.js +672 -0
- package/.versions/1.0.0/hermes/desktop-plugins/agent-fleet-monitor/plugin.js +19 -0
- package/.versions/1.0.0/hermes/desktop-plugins/agent-fleet-monitor/state.js +10 -0
- package/.versions/1.0.0/hermes/gates/gate-o-capability.md +8 -0
- package/.versions/1.0.0/hermes/gates/gate-o-validator-fixtures.json +1 -0
- package/.versions/1.0.0/hermes/plugins/agent-fleet-herdr/dashboard/activity.py +770 -0
- package/.versions/1.0.0/hermes/plugins/agent-fleet-herdr/dashboard/coms_registry.py +134 -0
- package/.versions/1.0.0/hermes/plugins/agent-fleet-herdr/dashboard/coms_send.py +350 -0
- package/.versions/1.0.0/hermes/plugins/agent-fleet-herdr/dashboard/herdr_source.py +193 -0
- package/.versions/1.0.0/hermes/plugins/agent-fleet-herdr/dashboard/manifest.json +4 -0
- package/.versions/1.0.0/hermes/plugins/agent-fleet-herdr/dashboard/plugin_api.py +444 -0
- package/.versions/1.0.0/hermes/plugins/agent-fleet-herdr/dashboard/sessions.py +205 -0
- package/.versions/1.0.0/hermes/plugins/agent-fleet-herdr/dashboard/tasks.py +300 -0
- package/.versions/1.0.0/hermes/plugins/agent-fleet-herdr/dashboard/watch.py +819 -0
- package/.versions/1.0.0/hermes/plugins/agent-fleet-herdr/plugin.yaml +8 -0
- package/.versions/1.0.0/hermes/plugins/agent-fleet-monitor/dashboard/adapter.py +139 -0
- package/.versions/1.0.0/hermes/plugins/agent-fleet-monitor/dashboard/manifest.json +11 -0
- package/.versions/1.0.0/hermes/plugins/agent-fleet-monitor/dashboard/plugin_api.py +50 -0
- package/.versions/1.0.0/hermes/skills/hub-conductor/SKILL.md +84 -0
- package/.versions/1.0.0/hermes/skills/hub-liaison/SKILL.md +84 -0
- package/.versions/1.0.0/hermes/skills/hub-watchdog/SKILL.md +76 -0
- package/.versions/1.0.0/hermes/skills/hub-watchdog/manifest.json +1 -0
- package/.versions/1.0.0/hermes/skills/hub-watchdog/scripts/watchdog.py +249 -0
- package/.versions/1.0.0/hermes/skills/hub-watchdog/scripts/watchdog_actions.py +124 -0
- package/.versions/1.0.0/hermes/skills/hub-watchdog/scripts/watchdog_contract.py +76 -0
- package/.versions/1.0.0/hermes/skills/hub-watchdog/scripts/watchdog_delivery.py +10 -0
- package/.versions/1.0.0/hermes/skills/hub-watchdog/scripts/watchdog_engine.py +128 -0
- package/.versions/1.0.0/hermes/skills/hub-watchdog/scripts/watchdog_judgment.py +41 -0
- package/.versions/1.0.0/hermes/skills/hub-watchdog/scripts/watchdog_recovery.py +103 -0
- package/.versions/1.0.0/hermes/skills/hub-watchdog/scripts/watchdog_state.py +163 -0
- package/.versions/1.0.0/hermes/skills/hub-watchdog/scripts/watchdog_transport.py +138 -0
- package/.versions/1.0.0/hermes/watchdog-tests/__init__.py +0 -0
- package/.versions/1.0.0/hooks/coms-stop-hook.mjs +84 -0
- package/.versions/1.0.0/install-manifest.json +2745 -0
- package/.versions/1.0.0/justfile +272 -0
- package/.versions/1.0.0/manifest-meta.json +882 -0
- package/.versions/1.0.0/references/accessibility-checklist.md +160 -0
- package/.versions/1.0.0/references/definition-of-done.md +67 -0
- package/.versions/1.0.0/references/fleet-coordination-patterns.md +151 -0
- package/.versions/1.0.0/references/observability-checklist.md +91 -0
- package/.versions/1.0.0/references/orchestration-patterns.md +370 -0
- package/.versions/1.0.0/references/performance-checklist.md +153 -0
- package/.versions/1.0.0/references/prompting-patterns.md +380 -0
- package/.versions/1.0.0/references/security-checklist.md +179 -0
- package/.versions/1.0.0/references/testing-patterns.md +236 -0
- package/.versions/1.0.0/scripts/codex-conductor.ts +41 -0
- package/.versions/1.0.0/scripts/codex-remote-control.ts +167 -0
- package/.versions/1.0.0/scripts/coms-claude-bridge.ts +411 -0
- package/.versions/1.0.0/scripts/coms-cli.ts +484 -0
- package/.versions/1.0.0/scripts/coms-hermes-bridge.ts +413 -0
- package/.versions/1.0.0/scripts/fleet.ts +185 -0
- package/.versions/1.0.0/scripts/hermes-monitor-capability-runner.ts +25 -0
- package/.versions/1.0.0/scripts/hermes-monitor-scenario.ts +474 -0
- package/.versions/1.0.0/scripts/hermes-watchdog-capability-probe.ts +45 -0
- package/.versions/1.0.0/scripts/install-hermes-plugin.sh +180 -0
- package/.versions/1.0.0/scripts/lib/claude-bridge-core.ts +210 -0
- package/.versions/1.0.0/scripts/lib/codex-conductor.ts +88 -0
- package/.versions/1.0.0/scripts/lib/codex-remote-control.ts +480 -0
- package/.versions/1.0.0/scripts/lib/coms-envelope.ts +582 -0
- package/.versions/1.0.0/scripts/lib/fake-herdr-server.ts +88 -0
- package/.versions/1.0.0/scripts/lib/fleet-command.ts +266 -0
- package/.versions/1.0.0/scripts/lib/herdr-layout.ts +281 -0
- package/.versions/1.0.0/scripts/lib/hermes-bridge-core.ts +241 -0
- package/.versions/1.0.0/scripts/lib/hermes-monitor-events.ts +1 -0
- package/.versions/1.0.0/scripts/lib/hermes-monitor-herdr.ts +2 -0
- package/.versions/1.0.0/scripts/lib/hermes-monitor-model.ts +3 -0
- package/.versions/1.0.0/scripts/lib/hermes-monitor-registry.ts +2 -0
- package/.versions/1.0.0/scripts/lib/hermes-monitor-socket.ts +2 -0
- package/.versions/1.0.0/scripts/lib/hermes-monitor-store.ts +2 -0
- package/.versions/1.0.0/scripts/lib/monitor-env.ts +146 -0
- package/.versions/1.0.0/scripts/lib/peer-launch.ts +318 -0
- package/.versions/1.0.0/scripts/lib/persona-banner.ts +62 -0
- package/.versions/1.0.0/scripts/lib/spawn-stagger.ts +101 -0
- package/.versions/1.0.0/scripts/lib/team-project.ts +213 -0
- package/.versions/1.0.0/scripts/lib/team-snapshot.ts +147 -0
- package/.versions/1.0.0/scripts/peer-banner.ts +40 -0
- package/.versions/1.0.0/scripts/peer-launch.ts +259 -0
- package/.versions/1.0.0/scripts/team-snapshot.ts +237 -0
- package/.versions/1.0.0/scripts/team-up.ts +406 -0
- package/.versions/1.0.0/skills/_internal/grilling.md +11 -0
- package/.versions/1.0.0/skills/browser-testing-with-devtools/SKILL.md +351 -0
- package/.versions/1.0.0/skills/code-review-and-quality/SKILL.md +381 -0
- package/.versions/1.0.0/skills/compound-learning/SKILL.md +137 -0
- package/.versions/1.0.0/skills/context-engineering/SKILL.md +291 -0
- package/.versions/1.0.0/skills/deprecation-and-migration/SKILL.md +206 -0
- package/.versions/1.0.0/skills/designing-agents/SKILL.md +394 -0
- package/.versions/1.0.0/skills/designing-agents/pi-harness-authoring.md +222 -0
- package/.versions/1.0.0/skills/frontend-ui-engineering/SKILL.md +328 -0
- package/.versions/1.0.0/skills/git-workflow-and-versioning/SKILL.md +316 -0
- package/.versions/1.0.0/skills/idea-refine/SKILL.md +182 -0
- package/.versions/1.0.0/skills/idea-refine/examples.md +238 -0
- package/.versions/1.0.0/skills/idea-refine/frameworks.md +99 -0
- package/.versions/1.0.0/skills/idea-refine/refinement-criteria.md +113 -0
- package/.versions/1.0.0/skills/idea-refine/scripts/idea-refine.sh +15 -0
- package/.versions/1.0.0/skills/incremental-implementation/SKILL.md +287 -0
- package/.versions/1.0.0/skills/interview-me/SKILL.md +226 -0
- package/.versions/1.0.0/skills/orchestration-verification/SKILL.md +181 -0
- package/.versions/1.0.0/skills/peer-coms/SKILL.md +90 -0
- package/.versions/1.0.0/skills/performance-optimization/SKILL.md +350 -0
- package/.versions/1.0.0/skills/planning-and-task-breakdown/SKILL.md +254 -0
- package/.versions/1.0.0/skills/security-and-hardening/SKILL.md +461 -0
- package/.versions/1.0.0/skills/spec-driven-development/SKILL.md +257 -0
- package/.versions/1.0.0/skills/using-agent-skills/SKILL.md +199 -0
- package/.versions/1.0.0/systemd/user/agent-fleet-codex-remote-control.service.in +23 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/LICENSE +21 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/README.md +11 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/api-and-interface-design/SKILL.md +294 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/browser-testing-with-devtools/SKILL.md +317 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/ci-cd-and-automation/SKILL.md +390 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/code-review-and-quality/SKILL.md +396 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/code-simplification/SKILL.md +331 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/context-engineering/SKILL.md +289 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/debugging-and-error-recovery/SKILL.md +300 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/deprecation-and-migration/SKILL.md +247 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/documentation-and-adrs/SKILL.md +278 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/doubt-driven-development/SKILL.md +243 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/frontend-ui-engineering/SKILL.md +328 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/git-workflow-and-versioning/SKILL.md +355 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/idea-refine/SKILL.md +178 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/idea-refine/examples.md +238 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/idea-refine/frameworks.md +99 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/idea-refine/refinement-criteria.md +113 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/idea-refine/scripts/idea-refine.sh +15 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/incremental-implementation/SKILL.md +249 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/interview-me/SKILL.md +225 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/observability-and-instrumentation/SKILL.md +203 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/performance-optimization/SKILL.md +350 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/planning-and-task-breakdown/SKILL.md +234 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/security-and-hardening/SKILL.md +467 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/shipping-and-launch/SKILL.md +310 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/source-driven-development/SKILL.md +194 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/spec-driven-development/SKILL.md +206 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/test-driven-development/SKILL.md +383 -0
- package/.versions/1.0.0/vendor/agent-skills-upstream/skills/using-agent-skills/SKILL.md +191 -0
- package/CHANGELOG.md +142 -0
- package/README.md +117 -79
- package/agents/orchestrator.md +1 -1
- package/bin/cli.js +289 -359
- package/bin/force-patch-changesets.js +18 -2
- package/bin/lib/apply.js +86 -32
- package/bin/lib/desired.js +87 -0
- package/bin/lib/detect-agent.js +22 -38
- package/bin/lib/doctor.js +283 -33
- package/bin/lib/features.js +78 -0
- package/bin/lib/manifest.js +127 -48
- package/bin/lib/overrides.js +35 -0
- package/bin/lib/personas.js +37 -0
- package/bin/lib/plan.js +18 -9
- package/bin/lib/purge.js +11 -0
- package/bin/lib/reconcile.js +68 -0
- package/bin/lib/scan.js +24 -0
- package/bin/lib/state.js +25 -1
- package/bin/lib/stt-wizard.js +33 -0
- package/bin/lib/transaction.js +149 -0
- package/bin/lib/tui.js +71 -0
- package/bin/lib/verify.js +9 -26
- package/bin/snapshot-version.js +3 -6
- package/docs/ARCHITECTURE.md +55 -21
- package/docs/MIGRATION-agent-fleet.md +222 -0
- package/docs/agent-fleet-setup.md +124 -64
- package/docs/claude-code-coms-bridge.md +21 -2
- package/docs/coms-hermes-bridge.md +1 -1
- package/docs/getting-started.md +61 -217
- package/docs/npm-install.md +207 -429
- package/docs/pi-extensions.md +85 -41
- package/docs/pi-setup.md +48 -545
- package/hermes/README.md +1 -1
- package/install-manifest.json +385 -1255
- package/justfile +45 -27
- package/manifest-meta.json +544 -134
- package/node_modules/pi-ask-user/README.md +43 -5
- package/node_modules/pi-ask-user/index.ts +630 -75
- package/node_modules/pi-ask-user/package.json +1 -1
- package/package.json +5 -11
- package/scripts/coms-claude-bridge.ts +10 -0
- package/scripts/fleet.ts +107 -90
- package/scripts/lib/claude-bridge-core.ts +45 -0
- package/scripts/lib/fleet-command.ts +170 -15
- package/scripts/lib/monitor-env.ts +18 -6
- package/scripts/lib/peer-launch.ts +6 -2
- package/scripts/lib/team-project.ts +24 -4
- package/scripts/team-up.ts +57 -11
- package/skills/designing-agents/SKILL.md +1 -1
- package/skills/designing-agents/pi-harness-authoring.md +3 -3
- package/.claude/commands/build.md +0 -44
- package/.claude/commands/design-agent.md +0 -14
- package/.claude/commands/doctor-agent-fleet.md +0 -22
- package/.claude/commands/orchestrate.md +0 -112
- package/.claude/commands/prime.md +0 -22
- package/.claude/commands/review.md +0 -16
- package/.claude/commands/set-hermes-telegram.md +0 -15
- package/.claude/commands/set-hermes-watchdog.md +0 -6
- package/.claude/commands/setup-agent-fleet.md +0 -17
- package/.claude/commands/ship.md +0 -72
- package/.claude/commands/spec.md +0 -15
- package/.claude/commands/test.md +0 -19
- package/.claude/commands/webperf.md +0 -32
- package/.claude/orchestrate-teams.yaml +0 -24
- package/.opencode/commands/af-build.md +0 -17
- package/.opencode/commands/af-code-simplify.md +0 -16
- package/.opencode/commands/af-compound.md +0 -16
- package/.opencode/commands/af-design-agent.md +0 -15
- package/.opencode/commands/af-doctor-agent-fleet.md +0 -22
- package/.opencode/commands/af-orchestrate.md +0 -112
- package/.opencode/commands/af-plan.md +0 -16
- package/.opencode/commands/af-prime.md +0 -22
- package/.opencode/commands/af-review.md +0 -15
- package/.opencode/commands/af-set-hermes-watchdog.md +0 -6
- package/.opencode/commands/af-setup-agent-fleet.md +0 -17
- package/.opencode/commands/af-ship.md +0 -16
- package/.opencode/commands/af-spec.md +0 -16
- package/.opencode/commands/af-test.md +0 -21
- package/.opencode/commands/af-webperf.md +0 -32
- package/.opencode/orchestrate-teams.yaml +0 -24
- package/.pi/prompts/af-doctor-agent-fleet.md +0 -22
- package/.pi/prompts/af-setup-agent-fleet.md +0 -19
- package/.versions/0.0.1/.opencode/commands/af-doctor-agent-fleet.md +0 -15
- package/.versions/0.0.1/.opencode/commands/af-setup-agent-fleet.md +0 -15
- package/.versions/0.0.1/skills/guided-workspace-setup/SKILL.md +0 -506
- package/.versions/0.0.10/.opencode/commands/af-doctor-agent-fleet.md +0 -22
- package/.versions/0.0.10/.opencode/commands/af-setup-agent-fleet.md +0 -17
- package/.versions/0.0.10/.pi/prompts/af-doctor-agent-fleet.md +0 -22
- package/.versions/0.0.10/.pi/prompts/af-setup-agent-fleet.md +0 -19
- package/.versions/0.0.10/skills/guided-workspace-setup/SKILL.md +0 -226
- package/.versions/0.0.11/.claude/commands/build.md +0 -44
- package/.versions/0.0.11/.claude/commands/code-simplify.md +0 -22
- package/.versions/0.0.11/.claude/commands/design-agent.md +0 -14
- package/.versions/0.0.11/.claude/commands/doctor-agent-fleet.md +0 -22
- package/.versions/0.0.11/.claude/commands/orchestrate.md +0 -112
- package/.versions/0.0.11/.claude/commands/plan.md +0 -16
- package/.versions/0.0.11/.claude/commands/prime.md +0 -22
- package/.versions/0.0.11/.claude/commands/set-hermes-telegram.md +0 -15
- package/.versions/0.0.11/.claude/commands/set-hermes-watchdog.md +0 -6
- package/.versions/0.0.11/.claude/commands/setup-agent-fleet.md +0 -17
- package/.versions/0.0.11/.claude/commands/ship.md +0 -72
- package/.versions/0.0.11/.claude/commands/webperf.md +0 -32
- package/.versions/0.0.11/.claude/orchestrate-teams.yaml +0 -24
- package/.versions/0.0.11/.opencode/commands/af-build.md +0 -17
- package/.versions/0.0.11/.opencode/commands/af-code-simplify.md +0 -16
- package/.versions/0.0.11/.opencode/commands/af-compound.md +0 -16
- package/.versions/0.0.11/.opencode/commands/af-design-agent.md +0 -15
- package/.versions/0.0.11/.opencode/commands/af-doctor-agent-fleet.md +0 -22
- package/.versions/0.0.11/.opencode/commands/af-orchestrate.md +0 -112
- package/.versions/0.0.11/.opencode/commands/af-plan.md +0 -16
- package/.versions/0.0.11/.opencode/commands/af-prime.md +0 -22
- package/.versions/0.0.11/.opencode/commands/af-review.md +0 -15
- package/.versions/0.0.11/.opencode/commands/af-set-hermes-telegram.md +0 -15
- package/.versions/0.0.11/.opencode/commands/af-set-hermes-watchdog.md +0 -6
- package/.versions/0.0.11/.opencode/commands/af-setup-agent-fleet.md +0 -17
- package/.versions/0.0.11/.opencode/commands/af-ship.md +0 -16
- package/.versions/0.0.11/.opencode/commands/af-spec.md +0 -16
- package/.versions/0.0.11/.opencode/commands/af-test.md +0 -21
- package/.versions/0.0.11/.opencode/commands/af-webperf.md +0 -32
- package/.versions/0.0.11/.opencode/orchestrate-teams.yaml +0 -24
- package/.versions/0.0.11/.pi/prompts/af-doctor-agent-fleet.md +0 -22
- package/.versions/0.0.11/.pi/prompts/af-setup-agent-fleet.md +0 -19
- package/.versions/0.0.11/docs/opencode-setup.md +0 -281
- package/.versions/0.0.11/hooks/SIMPLIFY-IGNORE.md +0 -90
- package/.versions/0.0.11/hooks/hooks.json +0 -14
- package/.versions/0.0.11/hooks/session-start.sh +0 -74
- package/.versions/0.0.11/hooks/simplify-ignore.sh +0 -302
- package/.versions/0.0.11/skills/guided-workspace-setup/SKILL.md +0 -226
- package/.versions/0.0.4/.opencode/commands/af-doctor-agent-fleet.md +0 -17
- package/.versions/0.0.4/.opencode/commands/af-setup-agent-fleet.md +0 -15
- package/.versions/0.0.4/skills/guided-workspace-setup/SKILL.md +0 -535
- package/.versions/0.0.4/skills/guided-workspace-setup/companion-manifest.json +0 -33
- package/.versions/0.0.5/.opencode/commands/af-doctor-agent-fleet.md +0 -17
- package/.versions/0.0.5/.opencode/commands/af-setup-agent-fleet.md +0 -15
- package/.versions/0.0.5/skills/guided-workspace-setup/SKILL.md +0 -542
- package/.versions/0.0.5/skills/guided-workspace-setup/companion-manifest.json +0 -35
- package/.versions/0.0.6/.opencode/commands/af-doctor-agent-fleet.md +0 -17
- package/.versions/0.0.6/.opencode/commands/af-setup-agent-fleet.md +0 -15
- package/.versions/0.0.6/.pi/prompts/af-doctor-agent-fleet.md +0 -15
- package/.versions/0.0.6/.pi/prompts/af-setup-agent-fleet.md +0 -27
- package/.versions/0.0.6/skills/guided-workspace-setup/SKILL.md +0 -544
- package/.versions/0.0.6/skills/guided-workspace-setup/companion-manifest.json +0 -35
- package/.versions/0.0.7/.opencode/commands/af-doctor-agent-fleet.md +0 -17
- package/.versions/0.0.7/.opencode/commands/af-setup-agent-fleet.md +0 -15
- package/.versions/0.0.7/.pi/prompts/af-doctor-agent-fleet.md +0 -15
- package/.versions/0.0.7/.pi/prompts/af-setup-agent-fleet.md +0 -27
- package/.versions/0.0.7/skills/guided-workspace-setup/SKILL.md +0 -544
- package/.versions/0.0.7/skills/guided-workspace-setup/companion-manifest.json +0 -35
- package/.versions/0.0.8/.opencode/commands/af-doctor-agent-fleet.md +0 -17
- package/.versions/0.0.8/.opencode/commands/af-setup-agent-fleet.md +0 -15
- package/.versions/0.0.8/.pi/prompts/af-doctor-agent-fleet.md +0 -15
- package/.versions/0.0.8/.pi/prompts/af-setup-agent-fleet.md +0 -27
- package/.versions/0.0.8/skills/guided-workspace-setup/SKILL.md +0 -544
- package/.versions/0.0.8/skills/guided-workspace-setup/companion-manifest.json +0 -36
- package/.versions/0.0.9/.opencode/commands/af-doctor-agent-fleet.md +0 -17
- package/.versions/0.0.9/.opencode/commands/af-setup-agent-fleet.md +0 -15
- package/.versions/0.0.9/.pi/prompts/af-doctor-agent-fleet.md +0 -15
- package/.versions/0.0.9/.pi/prompts/af-setup-agent-fleet.md +0 -27
- package/.versions/0.0.9/skills/guided-workspace-setup/SKILL.md +0 -544
- package/bin/lib/bootstrap.js +0 -323
- package/bin/lib/transform-persona.js +0 -180
- package/docs/opencode-setup.md +0 -281
- package/hooks/SIMPLIFY-IGNORE.md +0 -90
- package/hooks/hooks.json +0 -14
- package/hooks/session-start.sh +0 -74
- package/hooks/simplify-ignore.sh +0 -302
- package/skills/guided-workspace-setup/SKILL.md +0 -226
- /package/.versions/0.0.10/{skills/guided-workspace-setup/companion-manifest.json → bin/catalog/harness-runtime-closure.json} +0 -0
- /package/.versions/0.0.11/{skills/guided-workspace-setup/companion-manifest.json → bin/catalog/harness-runtime-closure.json} +0 -0
- /package/{.opencode/commands → .versions/1.0.0/.pi/prompts}/af-set-hermes-telegram.md +0 -0
- /package/.versions/{0.0.9/skills/guided-workspace-setup/companion-manifest.json → 1.0.0/bin/catalog/harness-runtime-closure.json} +0 -0
- /package/{skills/guided-workspace-setup/companion-manifest.json → bin/catalog/harness-runtime-closure.json} +0 -0
|
@@ -1,17 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
description: Guided setup — install agent-fleet artifacts into a workspace for a chosen coding agent
|
|
3
|
-
---
|
|
4
|
-
|
|
5
|
-
Invoke the `guided-workspace-setup` skill via the `skill` tool 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 (`opencode` 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. Personas land in `.opencode/agent/<name>.md` as generated files; the CLI handles that too. 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 (pi workspaces only).
|
|
12
|
-
|
|
13
|
-
With a native select widget, open with the Express question backed by the manifest's profiles, then run group screens only on `Custom`, with drill-ins behind `Customise`. Without one, print a compact table and take a text reply. Option titles carry `<name> ★ [state]`; 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 and wait for explicit confirmation before anything is written. 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.
|
|
@@ -1,22 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
description: Scan agent-fleet install targets for broken symlinks, stale persona references, and overrides-file problems, then offer repairs
|
|
3
|
-
---
|
|
4
|
-
|
|
5
|
-
Load and follow the `guided-workspace-setup` skill's repair path — without running the rest of the install flow. Use this when the user wants the repair pass on its own; `/af-setup-agent-fleet` offers the same thing as soon as it finds prior install state.
|
|
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 prompt'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 `ask_user` single-select (or a plain text question without the widget) — *"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.
|
|
@@ -1,19 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
description: Guided setup — install agent-fleet artifacts into a workspace for a chosen coding agent
|
|
3
|
-
---
|
|
4
|
-
|
|
5
|
-
Load and follow the `guided-workspace-setup` skill before proceeding.
|
|
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 (`pi` 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. The harness/extension closures (Fleet Core, the `justfile` managed region, the `.pi/agents` configs, the runtime script closure) are manifest data, so the CLI already pulls them in; you do not restate or reassemble them. 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 (`.ai/stt.json` names env vars; the key goes in a gitignored `.env`).
|
|
12
|
-
|
|
13
|
-
**Bootstrap `pi-ask-user` first.** Before the menu, check whether the interaction package is available (bundled by `@chankov/agent-fleet`, recorded as a project package, or global). If it is missing, offer `pi install -l npm:pi-ask-user`, then **stop the pass** and ask the user to reload pi and re-run `/af-setup-agent-fleet` — the widget is not callable until then. Fall back to a text menu in this pass only if the user declines.
|
|
14
|
-
|
|
15
|
-
Drive every decision through the `ask_user` widget: ≤ 9 options and ≤ 8 `context` lines per call, options carrying the data (never a table in `context`). 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]`, 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.
|
|
16
|
-
|
|
17
|
-
If `verify` reports findings or broken items, offer `doctor --fix` before the menu — a broken workspace makes the menu lie about what is installed.
|
|
18
|
-
|
|
19
|
-
Print the plan as compact action-grouped lines before confirming, then confirm with one `displayMode: "inline"` single-select: `Apply — and remove the installer commands` (default) / `Apply — keep the installer commands` / `Adjust picks` / `Cancel`. Ask before passing `--allow-exec` (the `npm ci` steps). Exit `3` means conflicts: show the `.new` files the CLI 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.
|
|
@@ -1,226 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: guided-workspace-setup
|
|
3
|
-
description: Guides installation of agent-fleet artifacts into a target workspace. Use when onboarding a project to agent-fleet, when installing skills, commands, prompts, personas, or pi extensions for a chosen coding agent, or when a workspace needs its setup files configured.
|
|
4
|
-
---
|
|
5
|
-
|
|
6
|
-
# Guided Workspace Setup
|
|
7
|
-
|
|
8
|
-
## Overview
|
|
9
|
-
|
|
10
|
-
A conversational front-end over the `agent-fleet` CLI's deterministic installer. The CLI decides
|
|
11
|
-
paths, states, merges, ownership, and writes — this skill asks the questions a program cannot
|
|
12
|
-
answer: which artifacts this project wants, what belongs in its overrides file, and which speech
|
|
13
|
-
provider to configure. Everything else is `agent-fleet <verb> --json`.
|
|
14
|
-
|
|
15
|
-
**You never write an install target yourself.** No copying, no symlinking, no path tables, no
|
|
16
|
-
merge rules. If you find yourself about to write into `.claude/`, `.opencode/`, `.pi/`, or the
|
|
17
|
-
`justfile`, you are in the wrong place — call the CLI.
|
|
18
|
-
|
|
19
|
-
## When to Use
|
|
20
|
-
|
|
21
|
-
- Onboarding a project to agent-fleet, or changing which artifacts it uses
|
|
22
|
-
- Re-running setup to add, upgrade, repair, or remove artifacts
|
|
23
|
-
- Authoring or revising `.ai/agent-fleet-overrides.md`
|
|
24
|
-
|
|
25
|
-
**NOT for:** authoring new skills or personas (`designing-agents`); editing artifacts inside the
|
|
26
|
-
agent-fleet repo itself; general rules-file tuning (`context-engineering`).
|
|
27
|
-
|
|
28
|
-
## Process
|
|
29
|
-
|
|
30
|
-
### 1. Resolve the source root and agent
|
|
31
|
-
|
|
32
|
-
Run the CLI from the agent-fleet package the user actually installed:
|
|
33
|
-
|
|
34
|
-
1. `<workspace>/.ai/.agent-fleet-bootstrap.json` → its `sourceRoot`. Authoritative; written by
|
|
35
|
-
`npx @chankov/agent-fleet init`. If the path no longer exists, say so and go to 3.
|
|
36
|
-
2. This `SKILL.md`'s realpath, if it is a symlink. Never its *workspace* location — bootstrap
|
|
37
|
-
copies the file into `.pi/skills/…`, so that path is the target, not the source.
|
|
38
|
-
3. Ask. **Never scan the filesystem for agent-fleet clones** — it finds forks and stale checkouts,
|
|
39
|
-
not the package the user installed from.
|
|
40
|
-
|
|
41
|
-
Confirm the workspace path exists. The agent (`claude-code` / `opencode` / `pi`) comes from the
|
|
42
|
-
recorded state; pass `--agent` only to override it.
|
|
43
|
-
|
|
44
|
-
### 2. Read the workspace's current state
|
|
45
|
-
|
|
46
|
-
```
|
|
47
|
-
node <source-root>/bin/cli.js verify --workspace <workspace> [--agent <agent>] --json
|
|
48
|
-
```
|
|
49
|
-
|
|
50
|
-
One command, everything you need: `groups` (menu headings, agent-filtered), `profiles` (the
|
|
51
|
-
shortcuts), and `items` — each with `id`, `group`, `subcategory`, `title`, `summary`,
|
|
52
|
-
`recommended`, `consent`, `owned`, and `state`. Plus `findings`, `recordedVersion`, and
|
|
53
|
-
`summary.versionDrift`.
|
|
54
|
-
|
|
55
|
-
The states are the CLI's, not yours: `absent`, `up-to-date`, `linked`, `outdated`, `modified`,
|
|
56
|
-
`conflict`, `missing`, `broken-link`, `foreign-link`, `partial`, `gone`, `not-applicable`.
|
|
57
|
-
Do not compute, guess, or re-derive them.
|
|
58
|
-
|
|
59
|
-
If `findings` is non-empty or any item is broken, offer `doctor --fix` before the menu — a broken
|
|
60
|
-
workspace makes the menu lie about what is installed.
|
|
61
|
-
|
|
62
|
-
### 3. Ask what to install
|
|
63
|
-
|
|
64
|
-
Present the `items` grouped by `group`, chunked by `subcategory`. Interaction mode:
|
|
65
|
-
|
|
66
|
-
- **pi** → the `ask_user` widget from the external `pi-ask-user` package. If it is missing, offer
|
|
67
|
-
to install it (`pi install -l npm:pi-ask-user`), then **stop the pass** and ask the user to
|
|
68
|
-
reload and re-run — the widget is not callable until then. If they decline, use the text
|
|
69
|
-
fallback.
|
|
70
|
-
- **claude-code** → `AskUserQuestion` (max 4 options per call).
|
|
71
|
-
- **anything else** → print a compact table and take a text reply.
|
|
72
|
-
|
|
73
|
-
Screen budget: ≤ 8 context lines, ≤ 9 options per call (≤ 4 on `AskUserQuestion`). Options carry
|
|
74
|
-
the data — `{title, description}`, never a table pasted into `context`. Titles are
|
|
75
|
-
`<title> ★ [state]`; descriptions say what picking it does in plain words ("update available",
|
|
76
|
-
"locally modified — installing overwrites your edits"). Long material (diffs, changelog, the plan)
|
|
77
|
-
prints as agent text *before* the call, with `displayMode: "inline"` so it stays visible.
|
|
78
|
-
|
|
79
|
-
Open with one Express single-select that can resolve the whole menu — the `profiles` map supplies
|
|
80
|
-
the shortcuts (`recommended`, `full`, `minimal`, `pi-fleet-core`, …). Group screens run only on
|
|
81
|
-
`Custom`. Cancel is a no-op everywhere except the final confirmation.
|
|
82
|
-
|
|
83
|
-
**Selection never removes.** Leaving an installed item unpicked keeps it. Removal is its own
|
|
84
|
-
explicit screen, and it runs `uninstall --items`.
|
|
85
|
-
|
|
86
|
-
### 4. Offer project overrides *(this is genuinely yours)*
|
|
87
|
-
|
|
88
|
-
Scan the workspace — language, framework, test runner, dev server, rule-file trees, doc entry
|
|
89
|
-
points — and propose draft sections for `.ai/agent-fleet-overrides.md`:
|
|
90
|
-
`spec-driven-development`, `planning-and-task-breakdown`, `browser-testing-with-devtools`,
|
|
91
|
-
`git-workflow-and-versioning`, and for `pi` with `agent-hub` selected, `## agent-hub` (a legacy
|
|
92
|
-
`## agent-team` section keeps its name — preserve, never duplicate).
|
|
93
|
-
|
|
94
|
-
In `## agent-hub`, offer `language:` (default `English`, preserving any existing value) and the
|
|
95
|
-
project-knowledge keys **only when the scan finds matching material** — `rules:` for a rule-file
|
|
96
|
-
tree (`.ai/rules/`, `docs/rules/`, `.cursor/rules/`; point at the tree root, which resolves
|
|
97
|
-
index-first), `docs:` for canonical WHAT/WHY entry points. An empty guess sends every specialist
|
|
98
|
-
hunting for files that are not there.
|
|
99
|
-
|
|
100
|
-
Terse `key: value` lines only — the lifecycle skills and `agent-hub` parse this file on every run.
|
|
101
|
-
Reference env-var *names*; secrets stay in a gitignored `.env`. When any section names env vars,
|
|
102
|
-
offer an `## env` section with `required: <NAME>[, <NAME>]`. Schema: `docs/agent-fleet-setup.md`.
|
|
103
|
-
|
|
104
|
-
Print each draft as agent text, then ask `Accept` / `Edit` / `Skip` per section (or one
|
|
105
|
-
multi-select when there are more than two). This file is yours to write directly — it is not an
|
|
106
|
-
install target.
|
|
107
|
-
|
|
108
|
-
### 5. Configure `pi-voice-stt`, if selected *(also genuinely yours)*
|
|
109
|
-
|
|
110
|
-
The extension is a no-op until a provider is configured, and the CLI reports it as an operator
|
|
111
|
-
step rather than inventing one. Offer — never force — the Q&A:
|
|
112
|
-
|
|
113
|
-
- **Azure Speech** (`type: azure`) — resource endpoint, optional `locales` for per-phrase language
|
|
114
|
-
ID (e.g. `["bg-BG","en-US"]`). Env: `AZURE_SPEECH_KEY`, `AZURE_SPEECH_ENDPOINT`.
|
|
115
|
-
- **Azure OpenAI Whisper** (`type: azure-openai`) — best for mixed-language speech. `endpoint`,
|
|
116
|
-
Whisper `deployment`, `apiVersion` (default `2024-10-21`). Use the legacy data-plane host
|
|
117
|
-
`https://<resource>.openai.azure.com` (or `…cognitiveservices.azure.com`) — transcription 404s
|
|
118
|
-
on the Foundry `…services.ai.azure.com` host. Env: `AZURE_OPENAI_API_KEY`,
|
|
119
|
-
`AZURE_OPENAI_ENDPOINT`; offer `apiKeyEnv: AZURE_SPEECH_KEY` when the key is shared.
|
|
120
|
-
- **OpenAI-compatible** (`type: openai`) — `baseUrl` (default `https://api.openai.com/v1`; a
|
|
121
|
-
`http://127.0.0.1:*/v1` loopback is fine for local whisper), `model` (default `whisper-1`).
|
|
122
|
-
Env: `OPENAI_API_KEY`.
|
|
123
|
-
|
|
124
|
-
Write `<workspace>/.ai/stt.json` with the non-secret config and `apiKeyEnv` — **never a key
|
|
125
|
-
value** — and append the referenced names to the repo-root `.env` as empty placeholders only if
|
|
126
|
-
absent, never overwriting. Ensure `.env` is gitignored. On removal, delete `stt.json` only if
|
|
127
|
-
unedited; never touch `.env`.
|
|
128
|
-
|
|
129
|
-
### 6. Apply
|
|
130
|
-
|
|
131
|
-
```
|
|
132
|
-
node <source-root>/bin/cli.js install --workspace <ws> --agent <a> \
|
|
133
|
-
--profile <name> | --items <id,…> [--allow-exec] --yes --json
|
|
134
|
-
```
|
|
135
|
-
|
|
136
|
-
`upgrade` for a version bump (three-way merge, preserves local edits, `--accept-theirs` /
|
|
137
|
-
`--accept-ours` for conflicts), `uninstall --items <id,…>` for removals, `doctor --fix` for
|
|
138
|
-
repairs. Add `--dry-run` first when the user wants to see the plan; `--json` requires `--yes`.
|
|
139
|
-
|
|
140
|
-
Print the plan as compact action-grouped lines before the confirm — `Add (N): …`,
|
|
141
|
-
`Refresh (N): …` (append *overwrites local edits* when the plan reports `overwrites`),
|
|
142
|
-
`Remove (N): …`, `Keep (N)` as a count, `Method:`. When `versionDrift` is set, lead with
|
|
143
|
-
**"Changes since v<recorded> → v<current>"** and short bullets from `CHANGELOG.md`. Then one
|
|
144
|
-
`inline` single-select: `Apply — and remove the installer commands` (default) /
|
|
145
|
-
`Apply — keep the installer commands` / `Adjust picks` / `Cancel`.
|
|
146
|
-
|
|
147
|
-
Exit codes are the contract: `0` done, `1` error, `2` findings, `3` conflicts. On `3`, the CLI
|
|
148
|
-
wrote `<file>.new` beside each conflicted file and touched nothing else — show the list and let
|
|
149
|
-
the user resolve, or re-run with `--accept-theirs` / `--accept-ours`.
|
|
150
|
-
|
|
151
|
-
Artifacts install as copies. There is no copy-vs-symlink question to ask — symlinks exist only
|
|
152
|
-
inside an agent-fleet checkout, and a workspace that recorded them before that is migrated to
|
|
153
|
-
copies by the CLI on this run. Never offer the choice, and never pass `--method`.
|
|
154
|
-
|
|
155
|
-
`--allow-exec` covers the `npm ci` steps for `.pi/extensions` and `.pi/harnesses`; ask before
|
|
156
|
-
passing it. `external` and `operator` actions carry their own instructions in the plan output —
|
|
157
|
-
relay them verbatim; the CLI performs none of them, and neither do you.
|
|
158
|
-
|
|
159
|
-
### 7. Clean up and report
|
|
160
|
-
|
|
161
|
-
Unless the user chose to keep them:
|
|
162
|
-
|
|
163
|
-
```
|
|
164
|
-
node <source-root>/bin/cli.js cleanup-installer --agent <agent> --workspace <workspace>
|
|
165
|
-
```
|
|
166
|
-
|
|
167
|
-
Then `verify` once more and report what changed, plus the one-line cleanup outcome
|
|
168
|
-
("Installer slash commands removed — `npx @chankov/agent-fleet init` restores them", or the
|
|
169
|
-
retained command names). Point the user at `.ai/agent-fleet-overrides.md` and suggest loading
|
|
170
|
-
`using-agent-skills` first next session.
|
|
171
|
-
|
|
172
|
-
## Common Rationalizations
|
|
173
|
-
|
|
174
|
-
| Rationalization | Reality |
|
|
175
|
-
|---|---|
|
|
176
|
-
| "I'll copy this one file myself — calling the CLI for it is overkill." | Then it is not recorded in `.ai/agent-fleet-state.json`, so `verify` calls it unowned, `upgrade` skips it, and `uninstall` refuses to remove it. The state file is what makes any of this reversible. |
|
|
177
|
-
| "The installed file looks different from the source, so it's modified." | `modified`, `outdated`, and `conflict` are three different answers with three different consequences, and they need the recorded hash and the version snapshot to tell apart. Read `state` from `verify --json`. |
|
|
178
|
-
| "The user picked a narrower profile, so I'll remove what's no longer in it." | Selection never removes. Removal is `uninstall` with named items, and only after an explicit remove screen. |
|
|
179
|
-
| "The plan says `conflict` — I'll take the new version, it's newer." | Exit `3` means both sides changed. The `.new` file exists so a human decides. `--accept-theirs` is the user's call to make, not yours. |
|
|
180
|
-
| "I'll run `npm ci` for the extensions — it's obviously needed." | It is an `exec` item, gated on `--allow-exec`. Running commands in someone's repo is a consent boundary, not a formality. |
|
|
181
|
-
| "The Hermes plugin just needs a symlink into the profile directory — I can do that." | Operator items exist because their targets are outside the workspace: a Hermes profile, a user systemd unit, a running gateway. Relay the declared steps; perform none of them. |
|
|
182
|
-
| "The user is on `pi` and `pi-ask-user` is missing — I'll use the text fallback." | Offer the install-then-reload bootstrap first. A ~50-row menu through plain text is the experience that widget exists to replace. Fall back only if they decline. |
|
|
183
|
-
| "I installed `pi-ask-user`, so I'll keep going in the same pass." | It is not callable until pi reloads. Stop, ask them to reload and re-run. |
|
|
184
|
-
| "The user didn't tick that installed item in the drill-in, so remove it." | Not selecting means keep as-is. An accidental non-pick must never delete anything. |
|
|
185
|
-
| "They pressed `esc` — I'll take the defaults and continue." | Cancel is skip/no-op on every screen except the final confirm, where it means do not apply. |
|
|
186
|
-
| "I'll write the install detail into the overrides file too — one place is simpler." | Every skill and every `agent-hub` session loads the overrides file. Install detail lives in the state file, which nothing loads at runtime. |
|
|
187
|
-
| "There's no rule-file tree, but `rules:` looks incomplete without a value." | An invented path sends every specialist hunting for files that do not exist. Skip the key. |
|
|
188
|
-
| "The user asked for symlinks so `git pull` updates everything." | Symlinks are checkout-only now: outside one, the link target has to stay put forever, an npx cache clean breaks every link at once, and a source `git pull` rewrites artifacts nobody agreed to change. `agent-fleet upgrade` gives the same freshness with a real three-way merge. Say that, don't pass `--method`. |
|
|
189
|
-
| "I'll put the Azure key in `stt.json` — it's in `.ai/`, that's fine." | `.ai/` is committed. The config names an env var; the value lives in a gitignored `.env`. |
|
|
190
|
-
|
|
191
|
-
## Red Flags
|
|
192
|
-
|
|
193
|
-
- Any write by this skill into `.claude/`, `.opencode/`, `.pi/`, `agents/`, or the `justfile` —
|
|
194
|
-
those are the CLI's, exclusively. Only `.ai/agent-fleet-overrides.md` and `.ai/stt.json` are yours.
|
|
195
|
-
- An item state computed by eye instead of read from `verify --json`.
|
|
196
|
-
- A path table, merge rule, or removal-ownership rule restated in the conversation — all three
|
|
197
|
-
live in code, and a second copy will drift from it.
|
|
198
|
-
- `--json` used without `--yes`, or a plan applied without printing it first.
|
|
199
|
-
- A markdown table pasted into a widget call's `question` or `context`, or a screen over budget.
|
|
200
|
-
- The `pi-ask-user` bootstrap skipped on `pi`, or the pass continued after installing it.
|
|
201
|
-
- An artifact removed without an explicit remove screen, or `esc` treated as consent.
|
|
202
|
-
- Exit `3` handled by picking a side instead of showing the `.new` files.
|
|
203
|
-
- `operator` or `external` steps performed instead of relayed.
|
|
204
|
-
- A key value written into `.ai/stt.json`, or `.env` overwritten rather than appended to.
|
|
205
|
-
- Source root found by scanning the filesystem, or taken from `SKILL.md`'s workspace location.
|
|
206
|
-
|
|
207
|
-
## Verification
|
|
208
|
-
|
|
209
|
-
- [ ] Source root came from the bootstrap marker, `SKILL.md`'s realpath, or the user — never a scan.
|
|
210
|
-
- [ ] Every item state, group, and profile came from `verify --json`.
|
|
211
|
-
- [ ] Broken items and findings were offered `doctor --fix` before the menu.
|
|
212
|
-
- [ ] The menu opened with the Express question; group screens ran only on `Custom`; every screen
|
|
213
|
-
stayed within budget, with options carrying the data.
|
|
214
|
-
- [ ] On `pi`, `pi-ask-user` was present or its install-then-reload bootstrap was offered, and the
|
|
215
|
-
pass stopped after installing it.
|
|
216
|
-
- [ ] Nothing was written to an install target except by the CLI, and the plan was printed before
|
|
217
|
-
the single confirmation.
|
|
218
|
-
- [ ] `--allow-exec` was passed only after asking; `operator` / `external` steps were relayed verbatim.
|
|
219
|
-
- [ ] No copy-vs-symlink question was asked and no `--method` flag was passed.
|
|
220
|
-
- [ ] A `3` exit was surfaced as conflicts with their `.new` files, not resolved by guessing.
|
|
221
|
-
- [ ] `.ai/agent-fleet-overrides.md` holds terse `key: value` sections and nothing else; `rules:` /
|
|
222
|
-
`docs:` were offered only when the scan found matching material.
|
|
223
|
-
- [ ] `.ai/stt.json` names env vars and holds no key values; `.env` was appended to, gitignored,
|
|
224
|
-
and never overwritten.
|
|
225
|
-
- [ ] `cleanup-installer` ran unless the user kept the installer commands, and the report says which.
|
|
226
|
-
- [ ] The final `verify` exited `0`.
|
|
@@ -1,44 +0,0 @@
|
|
|
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.
|
|
@@ -1,22 +0,0 @@
|
|
|
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.
|
|
@@ -1,14 +0,0 @@
|
|
|
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).
|
|
@@ -1,22 +0,0 @@
|
|
|
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.
|
|
@@ -1,112 +0,0 @@
|
|
|
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.
|
|
@@ -1,16 +0,0 @@
|
|
|
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.
|
|
@@ -1,22 +0,0 @@
|
|
|
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.
|
|
@@ -1,15 +0,0 @@
|
|
|
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.
|
|
@@ -1,6 +0,0 @@
|
|
|
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.
|
|
@@ -1,17 +0,0 @@
|
|
|
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.
|