@chankov/agent-fleet 0.0.9 → 0.0.10
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/.claude/commands/doctor-agent-fleet.md +12 -7
- package/.claude/commands/setup-agent-fleet.md +7 -15
- package/.opencode/commands/af-doctor-agent-fleet.md +12 -7
- package/.opencode/commands/af-setup-agent-fleet.md +8 -6
- package/.pi/extensions/agent-fleet-update-check/README.md +2 -3
- package/.pi/extensions/btw/README.md +2 -2
- package/.pi/extensions/chrome-devtools-mcp/README.md +3 -6
- package/.pi/extensions/compact-and-continue/README.md +3 -3
- package/.pi/extensions/mcp-bridge/README.md +1 -1
- package/.pi/harnesses/agent-hub/README.md +139 -10
- package/.pi/harnesses/agent-hub/docs-lane.js +122 -0
- package/.pi/harnesses/agent-hub/external-blocker.js +85 -0
- package/.pi/harnesses/agent-hub/index.ts +448 -39
- package/.pi/harnesses/agent-hub/package.json +1 -1
- package/.pi/harnesses/agent-hub/review-findings.js +102 -0
- package/.pi/harnesses/agent-hub/run-budget.js +302 -4
- package/.pi/harnesses/agent-hub/run-namespace.js +87 -0
- package/.pi/harnesses/coms/package.json +1 -1
- package/.pi/harnesses/damage-control-continue/package.json +1 -1
- package/.pi/prompts/af-doctor-agent-fleet.md +13 -6
- package/.pi/prompts/af-setup-agent-fleet.md +7 -15
- package/.versions/0.0.10/.claude/commands/build.md +44 -0
- package/.versions/0.0.10/.claude/commands/code-simplify.md +22 -0
- package/.versions/0.0.10/.claude/commands/design-agent.md +14 -0
- package/.versions/0.0.10/.claude/commands/doctor-agent-fleet.md +22 -0
- package/.versions/0.0.10/.claude/commands/orchestrate.md +112 -0
- package/.versions/0.0.10/.claude/commands/plan.md +16 -0
- package/.versions/0.0.10/.claude/commands/prime.md +22 -0
- package/.versions/0.0.10/.claude/commands/review.md +16 -0
- package/.versions/0.0.10/.claude/commands/set-hermes-telegram.md +15 -0
- package/.versions/0.0.10/.claude/commands/set-hermes-watchdog.md +6 -0
- package/.versions/0.0.10/.claude/commands/setup-agent-fleet.md +17 -0
- package/.versions/0.0.10/.claude/commands/ship.md +72 -0
- package/.versions/0.0.10/.claude/commands/spec.md +15 -0
- package/.versions/0.0.10/.claude/commands/test.md +19 -0
- package/.versions/0.0.10/.claude/commands/webperf.md +32 -0
- package/.versions/0.0.10/.claude/orchestrate-teams.yaml +24 -0
- package/.versions/0.0.10/.opencode/commands/af-build.md +17 -0
- package/.versions/0.0.10/.opencode/commands/af-code-simplify.md +16 -0
- package/.versions/0.0.10/.opencode/commands/af-compound.md +16 -0
- package/.versions/0.0.10/.opencode/commands/af-design-agent.md +15 -0
- package/.versions/0.0.10/.opencode/commands/af-doctor-agent-fleet.md +22 -0
- package/.versions/0.0.10/.opencode/commands/af-orchestrate.md +112 -0
- package/.versions/0.0.10/.opencode/commands/af-plan.md +16 -0
- package/.versions/0.0.10/.opencode/commands/af-prime.md +22 -0
- package/.versions/0.0.10/.opencode/commands/af-review.md +15 -0
- package/.versions/0.0.10/.opencode/commands/af-set-hermes-telegram.md +15 -0
- package/.versions/0.0.10/.opencode/commands/af-set-hermes-watchdog.md +6 -0
- package/.versions/0.0.10/.opencode/commands/af-setup-agent-fleet.md +17 -0
- package/.versions/0.0.10/.opencode/commands/af-ship.md +16 -0
- package/.versions/0.0.10/.opencode/commands/af-spec.md +16 -0
- package/.versions/0.0.10/.opencode/commands/af-test.md +21 -0
- package/.versions/0.0.10/.opencode/commands/af-webperf.md +32 -0
- package/.versions/0.0.10/.opencode/orchestrate-teams.yaml +24 -0
- package/.versions/0.0.10/.pi/agents/dispatch-policy.yaml +32 -0
- package/.versions/0.0.10/.pi/agents/model-profiles.yaml +27 -0
- package/.versions/0.0.10/.pi/agents/peers.yaml +142 -0
- package/.versions/0.0.10/.pi/agents/teams.yaml +41 -0
- package/.versions/0.0.10/.pi/damage-control-rules.yaml +297 -0
- package/.versions/0.0.10/.pi/extensions/agent-fleet-update-check/README.md +57 -0
- package/.versions/0.0.10/.pi/extensions/agent-fleet-update-check/index.ts +161 -0
- package/.versions/0.0.10/.pi/extensions/agent-fleet-update-check/package.json +6 -0
- package/.versions/0.0.10/.pi/extensions/btw/README.md +118 -0
- package/.versions/0.0.10/.pi/extensions/btw/index.ts +917 -0
- package/.versions/0.0.10/.pi/extensions/btw/package.json +6 -0
- package/.versions/0.0.10/.pi/extensions/btw/state.js +179 -0
- package/.versions/0.0.10/.pi/extensions/chrome-devtools-mcp/README.md +55 -0
- package/.versions/0.0.10/.pi/extensions/chrome-devtools-mcp/index.ts +93 -0
- package/.versions/0.0.10/.pi/extensions/chrome-devtools-mcp/package.json +6 -0
- package/.versions/0.0.10/.pi/extensions/compact-and-continue/README.md +42 -0
- package/.versions/0.0.10/.pi/extensions/compact-and-continue/index.ts +120 -0
- package/.versions/0.0.10/.pi/extensions/compact-and-continue/package.json +6 -0
- package/.versions/0.0.10/.pi/extensions/mcp-bridge/README.md +46 -0
- package/.versions/0.0.10/.pi/extensions/mcp-bridge/index.ts +206 -0
- package/.versions/0.0.10/.pi/extensions/mcp-bridge/package.json +6 -0
- package/.versions/0.0.10/.pi/extensions/package-lock.json +1143 -0
- package/.versions/0.0.10/.pi/extensions/package.json +9 -0
- package/.versions/0.0.10/.pi/extensions/pi-voice-stt/README.md +201 -0
- package/.versions/0.0.10/.pi/extensions/pi-voice-stt/config.ts +198 -0
- package/.versions/0.0.10/.pi/extensions/pi-voice-stt/examples/stt.json +35 -0
- package/.versions/0.0.10/.pi/extensions/pi-voice-stt/index.ts +248 -0
- package/.versions/0.0.10/.pi/extensions/pi-voice-stt/package.json +6 -0
- package/.versions/0.0.10/.pi/extensions/pi-voice-stt/providers.ts +214 -0
- package/.versions/0.0.10/.pi/extensions/pi-voice-stt/recorder.ts +158 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/README.md +1001 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/access-approval.ts +135 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/artifacts.js +146 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/assertion-ledger.js +58 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/backend-policy.js +153 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/context-window.js +106 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/delegate.ts +435 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/docs-lane.js +122 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/drift-watchdog.js +211 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/evidence-rules.js +96 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/external-blocker.js +85 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/footer.ts +31 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/helpers.ts +248 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/index.ts +9111 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-control.ts +9 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-invoke-journal.ts +131 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-invoke.ts +92 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-lifecycle.ts +13 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-publisher.ts +59 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-recovery.ts +3 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-runtime.ts +3 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-session-bridge.ts +257 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/package.json +7 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/provider-semaphore.js +138 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/research-retention.js +34 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/research-watchdog.ts +40 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/return-contract.js +293 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/return-extract.js +75 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/review-findings.js +102 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/run-budget.js +479 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/run-namespace.js +87 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/safety-routing.ts +22 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/scope-gate.js +103 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/session-health.js +110 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/spawn.ts +354 -0
- package/.versions/0.0.10/.pi/harnesses/agent-hub/version.ts +42 -0
- package/.versions/0.0.10/.pi/harnesses/ask-user-remote/README.md +19 -0
- package/.versions/0.0.10/.pi/harnesses/ask-user-remote/index.ts +321 -0
- package/.versions/0.0.10/.pi/harnesses/ask-user-remote/race-core.js +106 -0
- package/.versions/0.0.10/.pi/harnesses/coms/README.md +100 -0
- package/.versions/0.0.10/.pi/harnesses/coms/index.ts +1767 -0
- package/.versions/0.0.10/.pi/harnesses/coms/package.json +7 -0
- package/.versions/0.0.10/.pi/harnesses/coms/version.ts +42 -0
- package/.versions/0.0.10/.pi/harnesses/damage-control-continue/README.md +124 -0
- package/.versions/0.0.10/.pi/harnesses/damage-control-continue/index.ts +536 -0
- package/.versions/0.0.10/.pi/harnesses/damage-control-continue/package.json +7 -0
- package/.versions/0.0.10/.pi/harnesses/damage-control-continue/version.ts +42 -0
- package/.versions/0.0.10/.pi/harnesses/lib/coms-registry-entry.ts +94 -0
- package/.versions/0.0.10/.pi/harnesses/lib/damage-control-shared.ts +197 -0
- package/.versions/0.0.10/.pi/harnesses/lib/herdr-client.ts +472 -0
- package/.versions/0.0.10/.pi/harnesses/lib/herdr-presence.ts +399 -0
- package/.versions/0.0.10/.pi/harnesses/lib/hermes-monitor-events.ts +136 -0
- package/.versions/0.0.10/.pi/harnesses/lib/hermes-monitor-herdr.ts +28 -0
- package/.versions/0.0.10/.pi/harnesses/lib/hermes-monitor-model.ts +18 -0
- package/.versions/0.0.10/.pi/harnesses/lib/hermes-monitor-registry.ts +6 -0
- package/.versions/0.0.10/.pi/harnesses/lib/hermes-monitor-socket.ts +163 -0
- package/.versions/0.0.10/.pi/harnesses/lib/hermes-monitor-store.ts +31 -0
- package/.versions/0.0.10/.pi/harnesses/lib/spawned-peers.js +190 -0
- package/.versions/0.0.10/.pi/harnesses/package-lock.json +35 -0
- package/.versions/0.0.10/.pi/harnesses/package.json +9 -0
- package/.versions/0.0.10/.pi/prompts/af-build.md +24 -0
- package/.versions/0.0.10/.pi/prompts/af-code-simplify.md +22 -0
- package/.versions/0.0.10/.pi/prompts/af-doctor-agent-fleet.md +22 -0
- package/.versions/0.0.10/.pi/prompts/af-plan.md +16 -0
- package/.versions/0.0.10/.pi/prompts/af-review.md +16 -0
- package/.versions/0.0.10/.pi/prompts/af-set-hermes-telegram.md +15 -0
- package/.versions/0.0.10/.pi/prompts/af-set-hermes-watchdog.md +6 -0
- package/.versions/0.0.10/.pi/prompts/af-setup-agent-fleet.md +19 -0
- package/.versions/0.0.10/.pi/prompts/af-ship.md +17 -0
- package/.versions/0.0.10/.pi/prompts/af-spec.md +15 -0
- package/.versions/0.0.10/.pi/prompts/af-test.md +19 -0
- package/.versions/0.0.10/.pi/skills/bowser/SKILL.md +145 -0
- package/.versions/0.0.10/.version +1 -0
- package/.versions/0.0.10/agents/architect.md +24 -0
- package/.versions/0.0.10/agents/bowser.md +27 -0
- package/.versions/0.0.10/agents/builder.md +54 -0
- package/.versions/0.0.10/agents/code-reviewer.md +208 -0
- package/.versions/0.0.10/agents/deep-researcher.md +32 -0
- package/.versions/0.0.10/agents/documenter.md +18 -0
- package/.versions/0.0.10/agents/orchestrator.md +72 -0
- package/.versions/0.0.10/agents/plan-reviewer.md +83 -0
- package/.versions/0.0.10/agents/planner.md +70 -0
- package/.versions/0.0.10/agents/releaser.md +24 -0
- package/.versions/0.0.10/agents/researcher.md +28 -0
- package/.versions/0.0.10/agents/security-auditor.md +167 -0
- package/.versions/0.0.10/agents/test-engineer.md +153 -0
- package/.versions/0.0.10/agents/web-debugger.md +43 -0
- package/.versions/0.0.10/agents/web-performance-auditor.md +193 -0
- package/.versions/0.0.10/codex/CONDUCTOR.md +148 -0
- package/.versions/0.0.10/docs/ARCHITECTURE.md +303 -0
- package/.versions/0.0.10/docs/agent-fleet-setup.md +377 -0
- package/.versions/0.0.10/docs/claude-code-coms-bridge.md +109 -0
- package/.versions/0.0.10/docs/codex-remote-conductor.md +170 -0
- package/.versions/0.0.10/docs/coms-hermes-bridge.md +189 -0
- package/.versions/0.0.10/docs/getting-started.md +254 -0
- package/.versions/0.0.10/docs/npm-install.md +514 -0
- package/.versions/0.0.10/docs/opencode-setup.md +281 -0
- package/.versions/0.0.10/docs/pi-extensions.md +363 -0
- package/.versions/0.0.10/docs/pi-setup.md +571 -0
- package/.versions/0.0.10/docs/skill-anatomy.md +150 -0
- package/.versions/0.0.10/hermes/README.md +347 -0
- package/.versions/0.0.10/hermes/desktop-plugins/agent-fleet-herdr/plugin.js +1291 -0
- package/.versions/0.0.10/hermes/desktop-plugins/agent-fleet-herdr/presentation.js +672 -0
- package/.versions/0.0.10/hermes/desktop-plugins/agent-fleet-monitor/plugin.js +19 -0
- package/.versions/0.0.10/hermes/desktop-plugins/agent-fleet-monitor/state.js +10 -0
- package/.versions/0.0.10/hermes/gates/gate-o-capability.md +8 -0
- package/.versions/0.0.10/hermes/gates/gate-o-validator-fixtures.json +1 -0
- package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/activity.py +770 -0
- package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/coms_registry.py +134 -0
- package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/coms_send.py +350 -0
- package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/herdr_source.py +193 -0
- package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/manifest.json +4 -0
- package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/plugin_api.py +444 -0
- package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/sessions.py +205 -0
- package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/tasks.py +300 -0
- package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/watch.py +819 -0
- package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/plugin.yaml +8 -0
- package/.versions/0.0.10/hermes/plugins/agent-fleet-monitor/dashboard/adapter.py +139 -0
- package/.versions/0.0.10/hermes/plugins/agent-fleet-monitor/dashboard/manifest.json +11 -0
- package/.versions/0.0.10/hermes/plugins/agent-fleet-monitor/dashboard/plugin_api.py +50 -0
- package/.versions/0.0.10/hermes/skills/hub-conductor/SKILL.md +84 -0
- package/.versions/0.0.10/hermes/skills/hub-liaison/SKILL.md +84 -0
- package/.versions/0.0.10/hermes/skills/hub-watchdog/SKILL.md +76 -0
- package/.versions/0.0.10/hermes/skills/hub-watchdog/manifest.json +1 -0
- package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog.py +249 -0
- package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_actions.py +124 -0
- package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_contract.py +76 -0
- package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_delivery.py +10 -0
- package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_engine.py +128 -0
- package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_judgment.py +41 -0
- package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_recovery.py +103 -0
- package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_state.py +163 -0
- package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_transport.py +138 -0
- package/.versions/0.0.10/hermes/watchdog-tests/__init__.py +0 -0
- package/.versions/0.0.10/hooks/SIMPLIFY-IGNORE.md +90 -0
- package/.versions/0.0.10/hooks/coms-stop-hook.mjs +84 -0
- package/.versions/0.0.10/hooks/hooks.json +14 -0
- package/.versions/0.0.10/hooks/session-start.sh +74 -0
- package/.versions/0.0.10/hooks/simplify-ignore.sh +302 -0
- package/.versions/0.0.10/install-manifest.json +3615 -0
- package/.versions/0.0.10/justfile +254 -0
- package/.versions/0.0.10/manifest-meta.json +472 -0
- package/.versions/0.0.10/references/accessibility-checklist.md +160 -0
- package/.versions/0.0.10/references/definition-of-done.md +67 -0
- package/.versions/0.0.10/references/fleet-coordination-patterns.md +151 -0
- package/.versions/0.0.10/references/observability-checklist.md +91 -0
- package/.versions/0.0.10/references/orchestration-patterns.md +370 -0
- package/.versions/0.0.10/references/performance-checklist.md +153 -0
- package/.versions/0.0.10/references/prompting-patterns.md +380 -0
- package/.versions/0.0.10/references/security-checklist.md +179 -0
- package/.versions/0.0.10/references/testing-patterns.md +236 -0
- package/.versions/0.0.10/scripts/codex-conductor.ts +41 -0
- package/.versions/0.0.10/scripts/codex-remote-control.ts +167 -0
- package/.versions/0.0.10/scripts/coms-claude-bridge.ts +401 -0
- package/.versions/0.0.10/scripts/coms-cli.ts +484 -0
- package/.versions/0.0.10/scripts/coms-hermes-bridge.ts +413 -0
- package/.versions/0.0.10/scripts/fleet.ts +168 -0
- package/.versions/0.0.10/scripts/hermes-monitor-capability-runner.ts +25 -0
- package/.versions/0.0.10/scripts/hermes-monitor-scenario.ts +474 -0
- package/.versions/0.0.10/scripts/hermes-watchdog-capability-probe.ts +45 -0
- package/.versions/0.0.10/scripts/install-hermes-plugin.sh +180 -0
- package/.versions/0.0.10/scripts/lib/claude-bridge-core.ts +165 -0
- package/.versions/0.0.10/scripts/lib/codex-conductor.ts +88 -0
- package/.versions/0.0.10/scripts/lib/codex-remote-control.ts +480 -0
- package/.versions/0.0.10/scripts/lib/coms-envelope.ts +582 -0
- package/.versions/0.0.10/scripts/lib/fake-herdr-server.ts +88 -0
- package/.versions/0.0.10/scripts/lib/fleet-command.ts +111 -0
- package/.versions/0.0.10/scripts/lib/herdr-layout.ts +281 -0
- package/.versions/0.0.10/scripts/lib/hermes-bridge-core.ts +241 -0
- package/.versions/0.0.10/scripts/lib/hermes-monitor-events.ts +1 -0
- package/.versions/0.0.10/scripts/lib/hermes-monitor-herdr.ts +2 -0
- package/.versions/0.0.10/scripts/lib/hermes-monitor-model.ts +3 -0
- package/.versions/0.0.10/scripts/lib/hermes-monitor-registry.ts +2 -0
- package/.versions/0.0.10/scripts/lib/hermes-monitor-socket.ts +2 -0
- package/.versions/0.0.10/scripts/lib/hermes-monitor-store.ts +2 -0
- package/.versions/0.0.10/scripts/lib/monitor-env.ts +120 -0
- package/.versions/0.0.10/scripts/lib/peer-launch.ts +314 -0
- package/.versions/0.0.10/scripts/lib/persona-banner.ts +62 -0
- package/.versions/0.0.10/scripts/lib/spawn-stagger.ts +101 -0
- package/.versions/0.0.10/scripts/lib/team-project.ts +193 -0
- package/.versions/0.0.10/scripts/lib/team-snapshot.ts +147 -0
- package/.versions/0.0.10/scripts/peer-banner.ts +40 -0
- package/.versions/0.0.10/scripts/peer-launch.ts +259 -0
- package/.versions/0.0.10/scripts/team-snapshot.ts +237 -0
- package/.versions/0.0.10/scripts/team-up.ts +360 -0
- package/.versions/0.0.10/skills/_internal/grilling.md +11 -0
- package/.versions/0.0.10/skills/browser-testing-with-devtools/SKILL.md +351 -0
- package/.versions/0.0.10/skills/code-review-and-quality/SKILL.md +381 -0
- package/.versions/0.0.10/skills/compound-learning/SKILL.md +137 -0
- package/.versions/0.0.10/skills/context-engineering/SKILL.md +291 -0
- package/.versions/0.0.10/skills/deprecation-and-migration/SKILL.md +206 -0
- package/.versions/0.0.10/skills/designing-agents/SKILL.md +394 -0
- package/.versions/0.0.10/skills/designing-agents/pi-harness-authoring.md +222 -0
- package/.versions/0.0.10/skills/frontend-ui-engineering/SKILL.md +328 -0
- package/.versions/0.0.10/skills/git-workflow-and-versioning/SKILL.md +316 -0
- package/.versions/0.0.10/skills/guided-workspace-setup/SKILL.md +226 -0
- package/.versions/0.0.10/skills/guided-workspace-setup/companion-manifest.json +38 -0
- package/.versions/0.0.10/skills/idea-refine/SKILL.md +182 -0
- package/.versions/0.0.10/skills/idea-refine/examples.md +238 -0
- package/.versions/0.0.10/skills/idea-refine/frameworks.md +99 -0
- package/.versions/0.0.10/skills/idea-refine/refinement-criteria.md +113 -0
- package/.versions/0.0.10/skills/idea-refine/scripts/idea-refine.sh +15 -0
- package/.versions/0.0.10/skills/incremental-implementation/SKILL.md +287 -0
- package/.versions/0.0.10/skills/interview-me/SKILL.md +226 -0
- package/.versions/0.0.10/skills/orchestration-verification/SKILL.md +181 -0
- package/.versions/0.0.10/skills/peer-coms/SKILL.md +90 -0
- package/.versions/0.0.10/skills/performance-optimization/SKILL.md +350 -0
- package/.versions/0.0.10/skills/planning-and-task-breakdown/SKILL.md +254 -0
- package/.versions/0.0.10/skills/security-and-hardening/SKILL.md +461 -0
- package/.versions/0.0.10/skills/spec-driven-development/SKILL.md +257 -0
- package/.versions/0.0.10/skills/using-agent-skills/SKILL.md +199 -0
- package/.versions/0.0.10/systemd/user/agent-fleet-codex-remote-control.service.in +23 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/LICENSE +21 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/README.md +11 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/api-and-interface-design/SKILL.md +294 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/browser-testing-with-devtools/SKILL.md +317 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/ci-cd-and-automation/SKILL.md +390 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/code-review-and-quality/SKILL.md +396 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/code-simplification/SKILL.md +331 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/context-engineering/SKILL.md +289 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/debugging-and-error-recovery/SKILL.md +300 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/deprecation-and-migration/SKILL.md +247 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/documentation-and-adrs/SKILL.md +278 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/doubt-driven-development/SKILL.md +243 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/frontend-ui-engineering/SKILL.md +328 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/git-workflow-and-versioning/SKILL.md +355 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/idea-refine/SKILL.md +178 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/idea-refine/examples.md +238 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/idea-refine/frameworks.md +99 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/idea-refine/refinement-criteria.md +113 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/idea-refine/scripts/idea-refine.sh +15 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/incremental-implementation/SKILL.md +249 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/interview-me/SKILL.md +225 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/observability-and-instrumentation/SKILL.md +203 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/performance-optimization/SKILL.md +350 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/planning-and-task-breakdown/SKILL.md +234 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/security-and-hardening/SKILL.md +467 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/shipping-and-launch/SKILL.md +310 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/source-driven-development/SKILL.md +194 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/spec-driven-development/SKILL.md +206 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/test-driven-development/SKILL.md +383 -0
- package/.versions/0.0.10/vendor/agent-skills-upstream/skills/using-agent-skills/SKILL.md +191 -0
- package/CHANGELOG.md +103 -0
- package/README.md +22 -5
- package/agents/code-reviewer.md +4 -0
- package/agents/orchestrator.md +7 -1
- package/agents/plan-reviewer.md +22 -1
- package/bin/build-manifest.js +68 -0
- package/bin/cli.js +679 -49
- package/bin/lib/apply.js +641 -0
- package/bin/lib/manifest.js +731 -0
- package/bin/lib/merge-forms.js +106 -0
- package/bin/lib/plan.js +569 -0
- package/bin/lib/state.js +213 -0
- package/bin/lib/verify.js +576 -0
- package/bin/snapshot-version.js +5 -0
- package/docs/ARCHITECTURE.md +52 -11
- package/docs/agent-fleet-setup.md +59 -48
- package/docs/getting-started.md +29 -6
- package/docs/npm-install.md +208 -31
- package/docs/opencode-setup.md +32 -0
- package/docs/pi-extensions.md +17 -10
- package/docs/pi-setup.md +164 -69
- package/install-manifest.json +3615 -0
- package/manifest-meta.json +472 -0
- package/package.json +8 -3
- package/skills/browser-testing-with-devtools/SKILL.md +3 -4
- package/skills/guided-workspace-setup/SKILL.md +172 -490
- package/skills/planning-and-task-breakdown/SKILL.md +18 -0
- package/skills/spec-driven-development/SKILL.md +12 -0
|
@@ -1,12 +1,13 @@
|
|
|
1
1
|
# Agent Fleet — Project Files
|
|
2
2
|
|
|
3
|
-
agent-fleet keeps
|
|
4
|
-
|
|
3
|
+
agent-fleet keeps a few small files in a project's `.ai/` directory. They have
|
|
4
|
+
different readers and different lifetimes, so they are kept separate.
|
|
5
5
|
|
|
6
6
|
| File | Read by | When |
|
|
7
7
|
|------|---------|------|
|
|
8
8
|
| `.ai/agent-fleet-overrides.md` | `spec-driven-development`, `planning-and-task-breakdown`, `browser-testing-with-devtools`, `git-workflow-and-versioning`, `compound-learning` (the `rules:`/`docs:` keys of `## agent-hub`), `agent-hub` pi harness | Every run of those skills / every session start of the harness |
|
|
9
|
-
| `.ai/agent-fleet-
|
|
9
|
+
| `.ai/agent-fleet-state.json` | the `agent-fleet` CLI (`install`, `upgrade`, `uninstall`, `verify`, `doctor`) | Every plan and every apply |
|
|
10
|
+
| `.ai/agent-fleet-setup.md` | humans — rendered from the state file, never parsed back | Rewritten on every apply |
|
|
10
11
|
| `.ai/stt.json` *(optional)* | `pi-voice-stt` extension | Every pi session start, when the extension is installed |
|
|
11
12
|
|
|
12
13
|
The `.ai/stt.json` file is present only when the optional `pi-voice-stt` voice-dictation
|
|
@@ -15,7 +16,8 @@ extension has been configured (by guided setup or by hand). Like the overrides f
|
|
|
15
16
|
live in a gitignored root `.env`. See [pi-voice-stt config](#ai-sttjson) below.
|
|
16
17
|
|
|
17
18
|
Keep them split: the overrides file is loaded into context constantly, so it
|
|
18
|
-
must stay minimal; the install record is
|
|
19
|
+
must stay minimal; the install record is read only by the CLI, so it can be
|
|
20
|
+
large.
|
|
19
21
|
|
|
20
22
|
## The overrides file — `.ai/agent-fleet-overrides.md`
|
|
21
23
|
|
|
@@ -166,55 +168,61 @@ otherwise, never mid-run), and its **values never appear in `--dry-run`
|
|
|
166
168
|
output** — only the path. Keep these files gitignored exactly like the root
|
|
167
169
|
`.env` this section describes.
|
|
168
170
|
|
|
169
|
-
## The
|
|
171
|
+
## The install record — `.ai/agent-fleet-state.json` and `.ai/agent-fleet-setup.md`
|
|
170
172
|
|
|
171
|
-
|
|
172
|
-
|
|
173
|
-
|
|
174
|
-
|
|
173
|
+
Two files, one source of truth. `.ai/agent-fleet-state.json` is what the
|
|
174
|
+
installer writes and the only thing it reads back: agent, method, package
|
|
175
|
+
version, source root, and one entry per installed item with a per-file sha256
|
|
176
|
+
(or, in symlink mode, the resolved link target). `.ai/agent-fleet-setup.md` is
|
|
177
|
+
**rendered from it** on every apply and never parsed back, so the two cannot
|
|
178
|
+
disagree — it exists for humans and for older readers that still look for
|
|
179
|
+
`version:` and `agent:`.
|
|
175
180
|
|
|
176
|
-
|
|
177
|
-
|
|
178
|
-
|
|
179
|
-
| `install-status` | Installed artifacts, their targets, and the method (`copy` or `symlink`) |
|
|
180
|
-
| `doctor-runs` | One line per doctor pass (preflight / postflight, repaired / deleted / skipped counts) |
|
|
181
|
-
| `verification` | Checks confirming the install |
|
|
181
|
+
Ownership is the point of the state file. An entry means "agent-fleet installed
|
|
182
|
+
this"; anything not listed is never removed or overwritten. That lookup is what
|
|
183
|
+
replaced the prose ownership rule the setup skill used to carry.
|
|
182
184
|
|
|
183
|
-
|
|
185
|
+
| State-file field | Meaning |
|
|
186
|
+
|---|---|
|
|
187
|
+
| `agent`, `method`, `sourceRoot` | How and from where this workspace was installed |
|
|
188
|
+
| `packageVersion` | The version that performed the last apply — the merge base for the next `upgrade` |
|
|
189
|
+
| `items` | One entry per installed artifact: strategy, method, files with hashes, JSON key paths |
|
|
190
|
+
| `externalPackages` | Packages the user was told to install; recorded, never installed for them |
|
|
191
|
+
| `events` | Last few applies (verb, version, action count, conflicts) |
|
|
192
|
+
|
|
193
|
+
**No secrets, ever.** Only env-var *names* may appear — for example in the
|
|
194
|
+
`pi-voice-stt` record. A test asserts nothing value-shaped is persisted.
|
|
184
195
|
|
|
185
|
-
|
|
186
|
-
performed the install (e.g. `version: 1.4.2`). It drives the version-aware
|
|
187
|
-
update flow — on every re-run, `guided-workspace-setup` compares this against
|
|
188
|
-
the current package version and:
|
|
196
|
+
### The recorded version and the three-way merge
|
|
189
197
|
|
|
190
|
-
|
|
191
|
-
|
|
192
|
-
|
|
193
|
-
3. Surfaces the result in the install menu using these `Status` values:
|
|
198
|
+
`packageVersion` drives `upgrade`. For each installed artifact the engine
|
|
199
|
+
compares three sides: *source@recorded* from the package's `.versions/<x.y.z>/`
|
|
200
|
+
snapshot tree, the installed copy on disk, and *source@current*.
|
|
194
201
|
|
|
195
|
-
|
|
|
202
|
+
| Outcome | What happens |
|
|
196
203
|
|---|---|
|
|
197
|
-
|
|
|
198
|
-
|
|
|
199
|
-
|
|
|
200
|
-
|
|
|
204
|
+
| Only the source moved | Clean refresh |
|
|
205
|
+
| Only your copy moved | Kept — `upgrade` never eats a local edit |
|
|
206
|
+
| Both moved, to different content | **Conflict**: the incoming version is written as `<file>.new`, your file is untouched, the run exits `3` |
|
|
207
|
+
| Retired upstream | Proposed for removal by name, subject to the ownership rule |
|
|
201
208
|
|
|
202
|
-
|
|
203
|
-
`.versions
|
|
204
|
-
|
|
205
|
-
|
|
206
|
-
prompts for an explicit baseline.
|
|
209
|
+
If the snapshot is missing (an unpublished local build, or a version older than
|
|
210
|
+
`.versions/` retention), the comparison degrades to two-way, the installed copy
|
|
211
|
+
is treated as canonical, and `verify` says so as an advisory finding rather than
|
|
212
|
+
pretending a diff exists.
|
|
207
213
|
|
|
208
|
-
### Pre-
|
|
214
|
+
### Pre-engine workspaces
|
|
209
215
|
|
|
210
|
-
A workspace
|
|
211
|
-
|
|
212
|
-
|
|
213
|
-
|
|
216
|
+
A workspace with only `.ai/agent-fleet-setup.md` and no state file predates the
|
|
217
|
+
installer engine. `verify` reads what it can from the markdown (`agent:`,
|
|
218
|
+
`version:`), reports `stateSource: "legacy-record"`, and `upgrade` says plainly
|
|
219
|
+
that ownership cannot be read back — run `install` once to reconstruct the state
|
|
220
|
+
file first. A workspace with no `version:` at all is pre-versioning: there is no
|
|
221
|
+
recorded baseline, so no three-way merge is attempted.
|
|
214
222
|
|
|
215
|
-
Commit
|
|
216
|
-
so
|
|
217
|
-
instead `.gitignore`
|
|
223
|
+
Commit these files if the team should share install state — keep paths relative
|
|
224
|
+
so they stay portable. A self-referencing checkout (agent-fleet itself) may
|
|
225
|
+
instead `.gitignore` them, since their recorded paths are local to one machine.
|
|
218
226
|
|
|
219
227
|
## The `/orchestrate` command and its team config
|
|
220
228
|
|
|
@@ -310,18 +318,20 @@ required: <ENV_VAR_NAME>[, <ANOTHER_NAME>]
|
|
|
310
318
|
|
|
311
319
|
### `.ai/agent-fleet-setup.md`
|
|
312
320
|
|
|
313
|
-
|
|
321
|
+
Rendered from `.ai/agent-fleet-state.json` by every apply, for humans to read.
|
|
322
|
+
Edit the workspace, not this file — the next apply overwrites it.
|
|
314
323
|
|
|
315
324
|
```markdown
|
|
316
325
|
# Agent Fleet — Workspace Setup
|
|
317
326
|
#
|
|
318
|
-
#
|
|
327
|
+
# Generated from .ai/agent-fleet-state.json by `agent-fleet install`.
|
|
328
|
+
# Edit the workspace, not this file: it is rewritten on every apply.
|
|
319
329
|
|
|
320
330
|
## workspace-summary
|
|
321
331
|
agent: claude-code
|
|
322
332
|
method: copy
|
|
323
333
|
version: 1.4.2
|
|
324
|
-
|
|
334
|
+
source: /home/you/.npm/_npx/<hash>/node_modules/@chankov/agent-fleet
|
|
325
335
|
|
|
326
336
|
## install-status
|
|
327
337
|
skills: [spec-driven-development, test-driven-development, code-review-and-quality]
|
|
@@ -329,12 +339,13 @@ commands: [spec, plan, build]
|
|
|
329
339
|
personas: [code-reviewer]
|
|
330
340
|
extensions: []
|
|
331
341
|
harnesses: []
|
|
332
|
-
|
|
342
|
+
companions: [skills-internal-grilling]
|
|
343
|
+
external: []
|
|
333
344
|
updated: 2026-05-22
|
|
334
345
|
|
|
335
346
|
## verification
|
|
336
|
-
-
|
|
337
|
-
- No secrets are stored in this file.
|
|
347
|
+
- 21 item(s) recorded; run `agent-fleet verify` to check them against disk.
|
|
348
|
+
- No secrets are stored in this file or in .ai/agent-fleet-state.json.
|
|
338
349
|
```
|
|
339
350
|
|
|
340
351
|
### `.ai/stt.json`
|
package/docs/getting-started.md
CHANGED
|
@@ -13,10 +13,27 @@ Each skill is a Markdown file (`SKILL.md`) that describes a specific engineering
|
|
|
13
13
|
| Audience | Path | Why |
|
|
14
14
|
|---|---|---|
|
|
15
15
|
| **Most users** — you want to use the skills in your projects | `npx @chankov/agent-fleet init` | One command; semver updates; cross-platform; no source dir to babysit. See [docs/npm-install.md](npm-install.md). |
|
|
16
|
+
| **You already know what you want** — or you're scripting a fresh repo | `npx @chankov/agent-fleet install --agent <a> --profile recommended --yes` | The CLI does every write itself: no coding agent, no model, no prompts. |
|
|
16
17
|
| **Claude Code users** — you live in Claude Code and want plugin-managed updates | `/plugin marketplace add chankov/agent-fleet` | Best UX inside Claude Code; marketplace handles the lifecycle. |
|
|
17
|
-
| **Skill authors / contributors** — you want to edit the skills
|
|
18
|
+
| **Skill authors / contributors** — you want to edit the skills themselves | `git clone` + work in the checkout | Inside an agent-fleet checkout `--method symlink` is available, so editing an installed artifact edits the source. |
|
|
18
19
|
|
|
19
|
-
|
|
20
|
+
`init` is the conversational front-end; `install` is the engine underneath it.
|
|
21
|
+
Both end up in the same place — the same manifest, the same install record, the
|
|
22
|
+
same three-way merge on the next `upgrade`. None of the paths is being deprecated.
|
|
23
|
+
|
|
24
|
+
### Installing without an agent
|
|
25
|
+
|
|
26
|
+
```bash
|
|
27
|
+
npx @chankov/agent-fleet install --agent pi --profile recommended --yes
|
|
28
|
+
npx @chankov/agent-fleet verify # read-only report: recorded × on disk × shipped
|
|
29
|
+
npx @chankov/agent-fleet upgrade --dry-run # what a refresh would change
|
|
30
|
+
```
|
|
31
|
+
|
|
32
|
+
Profiles: `minimal`, `recommended`, `full`, `pi-fleet-core`, `hermes-plugins`,
|
|
33
|
+
`codex-bridge`. Pick individual artifacts instead with `--items skill:test-driven-development,persona:code-reviewer`.
|
|
34
|
+
Every verb takes `--dry-run` and `--json`. **Artifacts install as copies** —
|
|
35
|
+
refresh them with `agent-fleet upgrade`, which keeps local edits and writes an
|
|
36
|
+
incoming conflict beside your file as `<file>.new`.
|
|
20
37
|
|
|
21
38
|
## Optional: see the fleet in Hermes Desktop
|
|
22
39
|
|
|
@@ -74,15 +91,21 @@ The runtime contract is generated under `$HOME/.local/state/agent-fleet/codex-co
|
|
|
74
91
|
|
|
75
92
|
## Quick Start (Any Agent)
|
|
76
93
|
|
|
77
|
-
|
|
94
|
+
The CLI installs into `claude-code`, `opencode`, and `pi` workspaces. For **any
|
|
95
|
+
other** agent it has no target paths to write to, so the skills are loaded by
|
|
96
|
+
hand — that is what this section covers.
|
|
97
|
+
|
|
98
|
+
### 1. Get the files
|
|
78
99
|
|
|
79
100
|
```bash
|
|
101
|
+
npm install --save-dev @chankov/agent-fleet # or:
|
|
80
102
|
git clone https://github.com/chankov/agent-fleet.git
|
|
81
103
|
```
|
|
82
104
|
|
|
83
|
-
>
|
|
84
|
-
>
|
|
85
|
-
>
|
|
105
|
+
> The npm path puts the package contents in `node_modules/@chankov/agent-fleet/`.
|
|
106
|
+
> Use whichever of the two you have wherever this guide says "the agent-fleet repo."
|
|
107
|
+
> Don't use `agent-fleet install` here — it writes to `.claude/`, `.opencode/`, or
|
|
108
|
+
> `.pi/`, which an agent outside those three won't read.
|
|
86
109
|
|
|
87
110
|
### 2. Choose a skill
|
|
88
111
|
|
package/docs/npm-install.md
CHANGED
|
@@ -1,10 +1,12 @@
|
|
|
1
1
|
# npm install path
|
|
2
2
|
|
|
3
3
|
The `@chankov/agent-fleet` package ships every skill, persona, slash command,
|
|
4
|
-
and pi extension as installable content, plus
|
|
5
|
-
|
|
6
|
-
|
|
7
|
-
|
|
4
|
+
and pi extension as installable content, plus the CLI that installs them. The
|
|
5
|
+
CLI is the whole installer: it decides paths, computes per-item state, performs
|
|
6
|
+
the three-way merge, and does every write, so a complete install needs no coding
|
|
7
|
+
agent and no model. The `guided-workspace-setup` skill is a conversational
|
|
8
|
+
front-end over it — it asks which artifacts a project wants and drafts the
|
|
9
|
+
overrides file; the CLI does the rest.
|
|
8
10
|
|
|
9
11
|
## Package name vs CLI name
|
|
10
12
|
|
|
@@ -43,7 +45,7 @@ inside your agent.
|
|
|
43
45
|
|
|
44
46
|
### First-class pi package
|
|
45
47
|
|
|
46
|
-
For pi users who want package-native loading instead of copied
|
|
48
|
+
For pi users who want package-native loading instead of copied setup artifacts:
|
|
47
49
|
|
|
48
50
|
```bash
|
|
49
51
|
# Project-scoped; writes .pi/settings.json
|
|
@@ -57,7 +59,7 @@ The pi package manifest exposes this repo's skills, pi runtime skills, lifecycle
|
|
|
57
59
|
|
|
58
60
|
It intentionally does not auto-expose this repo's own `.pi/extensions` or harness directories; install those through guided setup or the pi setup docs so their runtime dependencies are handled explicitly. `pi-codex-image-gen` is also not bundled or required; guided setup may offer it as an optional suggested external npm/pi package when package installation is available, and installs it only if selected (`pi install -l npm:pi-codex-image-gen`). Minimal setup works without it.
|
|
59
61
|
|
|
60
|
-
The package also ships assets for the **experimental Linux Codex Remote-Control conductor** (`codex/`, `systemd/`, lifecycle/wrapper scripts, recipes, and runbook). Guided setup copies
|
|
62
|
+
The package also ships assets for the **experimental Linux Codex Remote-Control conductor** (`codex/`, `systemd/`, lifecycle/wrapper scripts, recipes, and runbook). Guided setup copies those assets with selected pi harnesses but never enables systemd, edits Codex config, starts a service, or pairs a phone. Those remain explicit operator actions and support only Codex CLI `0.144.x`; see [codex-remote-conductor.md](codex-remote-conductor.md). Its managed runtime contract is created later under `$HOME/.local/state/agent-fleet/codex-conductor/`, not inside the npm package or target checkout.
|
|
61
63
|
|
|
62
64
|
## Commands
|
|
63
65
|
|
|
@@ -85,9 +87,8 @@ are always overwritten because they're scaffolding, not user data.
|
|
|
85
87
|
After the setup workflow finishes its install pass, **the bootstrap files
|
|
86
88
|
are removed by default** so they don't clutter your agent's slash-command
|
|
87
89
|
list. Re-run `npx @chankov/agent-fleet init` whenever you want the runtime's
|
|
88
|
-
setup command back
|
|
89
|
-
|
|
90
|
-
`keep-installer: true` in `.ai/agent-fleet-setup.md`.
|
|
90
|
+
setup command back, or pick the "keep the installer commands" option at the
|
|
91
|
+
setup flow's confirmation to leave them in place.
|
|
91
92
|
|
|
92
93
|
### How the skill finds the source package
|
|
93
94
|
|
|
@@ -116,47 +117,213 @@ never scans your filesystem for other agent-fleet repos — that would
|
|
|
116
117
|
silently pick up forks, stale checkouts, or dev clones that aren't what
|
|
117
118
|
you installed.
|
|
118
119
|
|
|
119
|
-
The marker is removed by the same
|
|
120
|
-
slash commands.
|
|
120
|
+
The marker is removed by the same end-of-setup cleanup that removes the
|
|
121
|
+
slash commands (`agent-fleet cleanup-installer`).
|
|
121
122
|
|
|
122
123
|
| Flag | Default | Purpose |
|
|
123
124
|
|------|---------|---------|
|
|
124
125
|
| `--agent <claude-code\|opencode\|pi>` | auto-detect | Skip the agent prompt |
|
|
125
|
-
| `--method <copy\|symlink>` | `copy` | Default install method passed to the skill |
|
|
126
126
|
| `--workspace <path>` | `cwd` | Target workspace |
|
|
127
127
|
| `--launch` | off | Shell into the coding agent after init (best effort) |
|
|
128
128
|
|
|
129
129
|
```bash
|
|
130
130
|
npx @chankov/agent-fleet init --agent claude-code
|
|
131
|
-
npx @chankov/agent-fleet init --workspace ~/projects/foo
|
|
131
|
+
npx @chankov/agent-fleet init --workspace ~/projects/foo
|
|
132
132
|
```
|
|
133
133
|
|
|
134
134
|
### `npx @chankov/agent-fleet doctor`
|
|
135
135
|
|
|
136
|
-
|
|
137
|
-
|
|
138
|
-
|
|
136
|
+
Finds and repairs breakage. Two sources, one report:
|
|
137
|
+
|
|
138
|
+
- **Recorded items** that are missing, dangling, or linked outside the source
|
|
139
|
+
root. These are repaired through the *same* `apply()` path `install` writes
|
|
140
|
+
with — a repaired file is byte-identical to a freshly installed one, which is
|
|
141
|
+
the structural reason setup and repair cannot drift apart.
|
|
142
|
+
- **The scan**, for what the install record cannot own: broken symlinks in a
|
|
143
|
+
pre-engine workspace, and stale persona names in `.pi/agents/*.yaml`
|
|
144
|
+
(`reviewer` → `code-reviewer`, `red-team` → `security-auditor`).
|
|
145
|
+
|
|
146
|
+
Overrides problems and malformed `peers.yaml` entries are **advisory** —
|
|
147
|
+
reported, never auto-fixed, because the fix is always a hand edit.
|
|
139
148
|
|
|
140
149
|
| Flag | Default | Purpose |
|
|
141
150
|
|------|---------|---------|
|
|
142
151
|
| `--workspace <path>` | `cwd` | Target workspace |
|
|
143
|
-
| `--
|
|
144
|
-
| `--
|
|
152
|
+
| `--agent <name>` | recorded → detected | Override the agent whose targets are checked |
|
|
153
|
+
| `--fix` | off | Apply the repairs without prompting |
|
|
154
|
+
| `--dry-run` | off | Report only; never write, never prompt |
|
|
155
|
+
| `--json` | off | Emit the machine report on stdout |
|
|
156
|
+
| `--yes` / `-y` | off | Alias for `--fix` |
|
|
157
|
+
|
|
158
|
+
| Exit code | Meaning |
|
|
159
|
+
|-----------|---------|
|
|
160
|
+
| `0` | nothing to repair |
|
|
161
|
+
| `1` | could not run |
|
|
162
|
+
| `2` | repairable issues found, advisories present, or a repair failed |
|
|
145
163
|
|
|
146
164
|
```bash
|
|
147
165
|
npx @chankov/agent-fleet doctor --workspace ~/projects/foo --dry-run
|
|
148
|
-
npx @chankov/agent-fleet doctor
|
|
166
|
+
npx @chankov/agent-fleet doctor --fix
|
|
167
|
+
```
|
|
168
|
+
|
|
169
|
+
### `npx @chankov/agent-fleet verify`
|
|
170
|
+
|
|
171
|
+
Read-only report of the workspace against `install-manifest.json` — the
|
|
172
|
+
generated catalogue of every installable artifact. Compares three things per
|
|
173
|
+
item: what `.ai/agent-fleet-state.json` records, what is on disk, and what the
|
|
174
|
+
current package ships. Writes nothing and fixes nothing.
|
|
175
|
+
|
|
176
|
+
| Flag | Default | Purpose |
|
|
177
|
+
|------|---------|---------|
|
|
178
|
+
| `--workspace <path>` | `cwd` | Target workspace |
|
|
179
|
+
| `--agent <name>` | recorded → detected | Override the agent whose targets are checked |
|
|
180
|
+
| `--json` | off | Emit the machine report on stdout |
|
|
181
|
+
| `--no-doctor` | off | Skip the symlink/persona/overrides scan |
|
|
182
|
+
|
|
183
|
+
| Exit code | Meaning |
|
|
184
|
+
|-----------|---------|
|
|
185
|
+
| `0` | no broken items, no problem findings |
|
|
186
|
+
| `1` | could not run (bad flags, missing manifest, unreadable workspace) |
|
|
187
|
+
| `2` | problem findings, or items in a broken state |
|
|
188
|
+
|
|
189
|
+
Item states: `absent`, `linked`, `up-to-date`, `outdated`, `modified`,
|
|
190
|
+
`partial`, `conflict`, `missing`, `broken-link`, `foreign-link`, `gone`.
|
|
191
|
+
An available upgrade (`outdated`) and a deliberate local edit (`modified`) are
|
|
192
|
+
reported but do **not** fail the run — neither is a broken workspace.
|
|
193
|
+
Findings are likewise split into `problem` and `advisory`; only problems
|
|
194
|
+
affect the exit code.
|
|
195
|
+
|
|
196
|
+
```bash
|
|
197
|
+
npx @chankov/agent-fleet verify
|
|
198
|
+
npx @chankov/agent-fleet verify --agent pi --json
|
|
199
|
+
```
|
|
200
|
+
|
|
201
|
+
`--json` is also the interface `guided-workspace-setup` builds its menu from:
|
|
202
|
+
the report carries `groups` (agent-filtered headings), `profiles` (the
|
|
203
|
+
shortcuts), and per-item `subcategory`, `title`, `summary`, `recommended`,
|
|
204
|
+
`owned`, and `state` — everything a selection screen needs, from one command.
|
|
205
|
+
|
|
206
|
+
The manifest itself is generated from the repository tree, never hand-written:
|
|
207
|
+
|
|
208
|
+
```bash
|
|
209
|
+
node bin/build-manifest.js # regenerate install-manifest.json
|
|
210
|
+
node bin/build-manifest.js --check # fail if the committed copy is stale
|
|
149
211
|
```
|
|
150
212
|
|
|
213
|
+
### `npx @chankov/agent-fleet install` / `upgrade` / `uninstall`
|
|
214
|
+
|
|
215
|
+
Three verbs over the same manifest, differing only in which action classes they
|
|
216
|
+
admit. `install` acts on a selection you name; `upgrade` acts on whatever the
|
|
217
|
+
workspace already has; `uninstall` removes what the state file records.
|
|
218
|
+
|
|
219
|
+
All three write the machine state file `.ai/agent-fleet-state.json` and render
|
|
220
|
+
`.ai/agent-fleet-setup.md` from it. No coding agent and no model is involved at
|
|
221
|
+
any point.
|
|
222
|
+
|
|
223
|
+
| Flag | Applies to | Purpose |
|
|
224
|
+
|------|-----------|---------|
|
|
225
|
+
| `--profile <name[,name]>` | install | Named selections, unioned |
|
|
226
|
+
| `--items <id[,id]>` | install, uninstall | Explicit item ids |
|
|
227
|
+
| `--all` | uninstall | Remove everything the state file records |
|
|
228
|
+
| `-y, --yes` | all | Apply without the confirmation prompt |
|
|
229
|
+
| `--allow-exec` | install, upgrade | Include items that run a command |
|
|
230
|
+
| `--accept-theirs` / `--accept-ours` | install, upgrade | Resolve conflicts non-interactively |
|
|
231
|
+
| `--dry-run` | all | Print the plan, write nothing |
|
|
232
|
+
| `--json` | all | Emit the machine plan/result on stdout (needs `--yes` or `--dry-run`) |
|
|
233
|
+
|
|
234
|
+
| Exit code | Meaning |
|
|
235
|
+
|-----------|---------|
|
|
236
|
+
| `0` | applied, or nothing to do |
|
|
237
|
+
| `1` | could not plan, or a step failed partway |
|
|
238
|
+
| `3` | conflicts — changed both locally and upstream |
|
|
239
|
+
|
|
240
|
+
```bash
|
|
241
|
+
npx @chankov/agent-fleet install --agent pi --profile recommended --yes
|
|
242
|
+
npx @chankov/agent-fleet install --items skill:test-driven-development --dry-run
|
|
243
|
+
npx @chankov/agent-fleet upgrade --dry-run
|
|
244
|
+
npx @chankov/agent-fleet upgrade --yes --accept-ours
|
|
245
|
+
npx @chankov/agent-fleet uninstall --items skill:peer-coms --yes
|
|
246
|
+
npx @chankov/agent-fleet uninstall --all --dry-run
|
|
247
|
+
```
|
|
248
|
+
|
|
249
|
+
Installing into a brand-new repository takes one command and no LLM:
|
|
250
|
+
|
|
251
|
+
```bash
|
|
252
|
+
npx @chankov/agent-fleet@latest install --agent pi --profile recommended --yes
|
|
253
|
+
```
|
|
254
|
+
|
|
255
|
+
Run it without `--profile`, `--items`, or `--yes` in a terminal and it asks
|
|
256
|
+
which profile to use; piped or scripted, it requires the flags rather than
|
|
257
|
+
guessing a catalogue for you.
|
|
258
|
+
|
|
259
|
+
Profiles available: `minimal`, `recommended`, `full`, `pi-fleet-core`,
|
|
260
|
+
`hermes-plugins`, `codex-bridge`.
|
|
261
|
+
|
|
262
|
+
**The two verbs treat a local edit differently, on purpose.** Selecting an item
|
|
263
|
+
in `install` is your consent to overwrite your edits to it — those items are
|
|
264
|
+
listed as `overwrites` in the plan. `upgrade` carries no such consent, so a file
|
|
265
|
+
you edited is preserved (`keep`) whenever the source did not also move. When
|
|
266
|
+
*both* changed, it is a conflict: the incoming version is written beside yours
|
|
267
|
+
as `<file>.new`, your file is left exactly as it is, and the run exits `3`.
|
|
268
|
+
|
|
269
|
+
Files shared with you — the `justfile` managed region and `.claude/settings.json`
|
|
270
|
+
— are only partly ours. Recipes outside the `agent-fleet:harnesses` sentinels
|
|
271
|
+
and settings keys we did not write are never read as drift and never rewritten.
|
|
272
|
+
|
|
273
|
+
A selection never removes anything — installing a narrower profile keeps what is
|
|
274
|
+
already there. Upgrade never widens the install either; newly catalogued
|
|
275
|
+
artifacts are counted as available and added only by an explicit `install`.
|
|
276
|
+
|
|
277
|
+
**Artifacts are installed as copies, always.** `--method symlink` is accepted only when the
|
|
278
|
+
workspace is itself an agent-fleet checkout (its `package.json` names `@chankov/agent-fleet`) —
|
|
279
|
+
the one place where editing an installed artifact is *meant* to edit the source. Anywhere else a
|
|
280
|
+
symlink install is a trap: the link target can never move again, an npx cache clean breaks every
|
|
281
|
+
link at once, a `git pull` in the source silently rewrites artifacts the workspace never agreed to
|
|
282
|
+
change, and Windows needs Developer Mode. A copy plus `agent-fleet upgrade` gives the same
|
|
283
|
+
freshness with a real three-way merge behind it.
|
|
284
|
+
|
|
285
|
+
A workspace that recorded `symlink` before this restriction is not left half-supported: `verify`
|
|
286
|
+
reports it as an advisory finding, and the next `install` or `upgrade` re-materialises every
|
|
287
|
+
linked item as a real file and flips the recorded method to `copy`. An explicit
|
|
288
|
+
`--method symlink` outside a checkout is refused rather than silently downgraded.
|
|
289
|
+
|
|
290
|
+
**`uninstall` is bound by the ownership rule.** Only paths recorded in
|
|
291
|
+
`.ai/agent-fleet-state.json` are eligible, and a recorded file whose bytes no
|
|
292
|
+
longer match what we wrote is kept and listed as skipped. Removing an item takes
|
|
293
|
+
its companions with it *unless* another installed item still needs them, and an
|
|
294
|
+
item another installed item pins is refused by name — so removing one pi
|
|
295
|
+
extension cannot delete the `package.json` five others run from, and removing
|
|
296
|
+
`damage-control-continue` while `agent-hub` is installed is refused rather than
|
|
297
|
+
silently leaving the hub without its safety harness. Removing the last pi
|
|
298
|
+
harness strips the `agent-fleet:harnesses` region from the `justfile` and leaves
|
|
299
|
+
the rest of the file alone.
|
|
300
|
+
|
|
301
|
+
**Some items the engine will not apply, by design.** Each carries a `consent`
|
|
302
|
+
class: `file` (plain writes, covered by `--yes`), `exec` (runs a command,
|
|
303
|
+
requires `--allow-exec`), `external` (a package you install yourself), and
|
|
304
|
+
`operator` (a Hermes profile, a user systemd unit, device pairing). Operator and
|
|
305
|
+
external items print their declared steps in the plan and are never performed —
|
|
306
|
+
including by `--yes`:
|
|
307
|
+
|
|
308
|
+
```bash
|
|
309
|
+
npx @chankov/agent-fleet install --agent pi --profile hermes-plugins --dry-run
|
|
310
|
+
npx @chankov/agent-fleet install --agent pi --profile codex-bridge --dry-run
|
|
311
|
+
```
|
|
312
|
+
|
|
313
|
+
Both print the exact command list for a human to run and touch nothing. Their
|
|
314
|
+
targets are outside the workspace, which is the one place the engine is allowed
|
|
315
|
+
to write — so they stay reported rather than automated, and no out-of-workspace
|
|
316
|
+
path ever enters the state file.
|
|
317
|
+
|
|
151
318
|
### `npx @chankov/agent-fleet update`
|
|
152
319
|
|
|
153
320
|
Reads the workspace's `.ai/agent-fleet-setup.md`, compares the recorded
|
|
154
321
|
package version against the installed package version, and **re-installs the
|
|
155
322
|
runtime's setup command** so it is always available after an update.
|
|
156
323
|
`guided-workspace-setup` removes the installer command at the end of a run by
|
|
157
|
-
default
|
|
158
|
-
|
|
159
|
-
|
|
324
|
+
default, so a workspace that has completed setup once would otherwise have no
|
|
325
|
+
command to hand off to. The actual refresh then runs inside the coding agent via
|
|
326
|
+
that command — or, with no agent at all, via `upgrade`.
|
|
160
327
|
|
|
161
328
|
The agent and install method are recovered from the bootstrap marker written
|
|
162
329
|
at init time; if that marker was cleaned up too, `update` auto-detects the
|
|
@@ -244,25 +411,35 @@ npm is the recommended path for most users. The other two stay supported:
|
|
|
244
411
|
|
|
245
412
|
- **[Claude Code plugin marketplace](../README.md#quick-start)** — best UX
|
|
246
413
|
inside Claude Code. Same skills, marketplace-managed updates.
|
|
247
|
-
- **Git clone
|
|
248
|
-
|
|
249
|
-
|
|
414
|
+
- **Git clone** — best for skill authors and contributors. Clone the repo and
|
|
415
|
+
work in it directly; inside an agent-fleet checkout `--method symlink` is
|
|
416
|
+
available, so an edit to an installed artifact edits the source. For any other
|
|
417
|
+
workspace, install copies and run `agent-fleet upgrade` after a `git pull`.
|
|
250
418
|
|
|
251
419
|
All three paths converge on the same `guided-workspace-setup` skill — the
|
|
252
420
|
difference is only in how the source files reach the workspace.
|
|
253
421
|
|
|
254
422
|
## CI usage
|
|
255
423
|
|
|
256
|
-
|
|
257
|
-
the agent when detection is ambiguous). For CI, pass `--agent` explicitly:
|
|
424
|
+
Every verb is scriptable, and a complete install needs no agent and no model:
|
|
258
425
|
|
|
259
426
|
```bash
|
|
260
|
-
|
|
427
|
+
mkdir fresh-repo && cd fresh-repo && git init
|
|
428
|
+
npx --yes @chankov/agent-fleet@latest install --agent pi --profile recommended --yes
|
|
429
|
+
npx --yes @chankov/agent-fleet@latest verify
|
|
261
430
|
```
|
|
262
431
|
|
|
263
|
-
`
|
|
264
|
-
|
|
265
|
-
|
|
432
|
+
Gate on the exit codes: `verify` exits `2` on drift or problem findings,
|
|
433
|
+
`upgrade` exits `3` when a file changed both locally and upstream, and `doctor`
|
|
434
|
+
exits `2` when anything repairable is left. `--json` puts the machine report on
|
|
435
|
+
stdout and nothing else.
|
|
436
|
+
|
|
437
|
+
Running the same install twice produces zero actions on the second run — that
|
|
438
|
+
is asserted by test, not left to discipline.
|
|
439
|
+
|
|
440
|
+
The conversational flow (`init` → the runtime's setup command) stays interactive
|
|
441
|
+
by design; its confirmation gates exist so a human approves every write. Pass
|
|
442
|
+
`--agent` explicitly to `init` in CI so it never prompts.
|
|
266
443
|
|
|
267
444
|
## Receiving update notifications
|
|
268
445
|
|
package/docs/opencode-setup.md
CHANGED
|
@@ -27,6 +27,38 @@ This more closely matches how Claude Code behaves in practice, while still allow
|
|
|
27
27
|
|
|
28
28
|
## Installation
|
|
29
29
|
|
|
30
|
+
### Recommended — the `agent-fleet` CLI (project-scoped)
|
|
31
|
+
|
|
32
|
+
The CLI writes OpenCode's targets directly: `.opencode/skills/`, `.opencode/commands/`,
|
|
33
|
+
and `.opencode/agent/` (personas transformed to `mode: subagent` on the way in).
|
|
34
|
+
|
|
35
|
+
```bash
|
|
36
|
+
cd /path/to/your-project
|
|
37
|
+
|
|
38
|
+
# Guided: bootstraps the installer command, then run /af-setup-agent-fleet in OpenCode
|
|
39
|
+
npx @chankov/agent-fleet init --agent opencode
|
|
40
|
+
|
|
41
|
+
# Or straight to it — no agent, no model, no prompts:
|
|
42
|
+
npx @chankov/agent-fleet install --agent opencode --profile recommended --yes
|
|
43
|
+
npx @chankov/agent-fleet verify --agent opencode
|
|
44
|
+
```
|
|
45
|
+
|
|
46
|
+
Refresh after a package update with `npx @chankov/agent-fleet upgrade` — it
|
|
47
|
+
three-way merges against the version recorded in `.ai/agent-fleet-state.json`,
|
|
48
|
+
so your local edits survive and a genuine conflict lands beside your file as
|
|
49
|
+
`<file>.new` (exit `3`) instead of overwriting it. Artifacts install as **copies**;
|
|
50
|
+
`agent-fleet doctor --fix` repairs anything that goes missing or dangling.
|
|
51
|
+
|
|
52
|
+
Profiles: `minimal`, `recommended`, `full`. Narrow it with
|
|
53
|
+
`--items skill:code-review-and-quality,command:review,persona:code-reviewer`, and
|
|
54
|
+
preview any verb with `--dry-run`. Full reference: [npm-install.md](npm-install.md).
|
|
55
|
+
|
|
56
|
+
### Manual global install (advanced)
|
|
57
|
+
|
|
58
|
+
Use this only when you want the skills available in **every** OpenCode session on
|
|
59
|
+
the machine regardless of project — the CLI installs per workspace and does not
|
|
60
|
+
write to `~/.config/opencode/`.
|
|
61
|
+
|
|
30
62
|
1. Clone the repository:
|
|
31
63
|
|
|
32
64
|
```bash
|
package/docs/pi-extensions.md
CHANGED
|
@@ -60,9 +60,11 @@ same CLI flags would abort startup with duplicate registrations. So the harnesse
|
|
|
60
60
|
- through the unified `justfile` interface — `just fleet`, `just fleet hub`, `just fleet peer <name>`, `just fleet team <preset>`, …
|
|
61
61
|
- or directly — `pi -e .pi/harnesses/<name>/index.ts` (advanced use; you must compose safety/utilities yourself)
|
|
62
62
|
|
|
63
|
-
When you consume this repo from another project,
|
|
64
|
-
|
|
65
|
-
|
|
63
|
+
When you consume this repo from another project, install the harness you want into
|
|
64
|
+
*its* `.pi/harnesses/` (`agent-fleet install --agent pi --items pi-harness:agent-hub`,
|
|
65
|
+
or the `pi-fleet-core` profile for the whole stack) and load it via that project's
|
|
66
|
+
`justfile` region, or point `pi -e` at the harness file directly — never drop the
|
|
67
|
+
harnesses into `.pi/extensions/`, and never load all of them at once. The supported multi-harness
|
|
66
68
|
exception is loading `damage-control-continue` and `ask-user-remote` before `agent-hub` for a guarded hub session (see
|
|
67
69
|
[pi-setup.md](pi-setup.md#optional-pi-extensions)).
|
|
68
70
|
|
|
@@ -82,10 +84,14 @@ just --list # shows the single public `fleet` entry point
|
|
|
82
84
|
|
|
83
85
|
`just install` runs `npm install` for both dependency roots: `.pi/extensions/` for the
|
|
84
86
|
utilities (`@modelcontextprotocol/sdk`, `typebox`) and `.pi/harnesses/` for the harnesses
|
|
85
|
-
(`@sinclair/typebox`, `yaml`).
|
|
86
|
-
|
|
87
|
-
|
|
88
|
-
|
|
87
|
+
(`@sinclair/typebox`, `yaml`). That is the **clone** path. In a target workspace the
|
|
88
|
+
installer handles it: the manifests are copied in as companions, and `agent-fleet install
|
|
89
|
+
--allow-exec` runs `npm ci --prefix .pi/extensions` and `npm ci --prefix .pi/harnesses`
|
|
90
|
+
for you (without `--allow-exec` those two steps are printed in the plan and skipped, for
|
|
91
|
+
you to run by hand). The extension dependencies are also root production dependencies of
|
|
92
|
+
the published `@chankov/agent-fleet` package, so a pi-package install resolves them from
|
|
93
|
+
the package's real path. The `@mariozechner/pi-*` packages are provided by the pi runtime
|
|
94
|
+
itself.
|
|
89
95
|
|
|
90
96
|
---
|
|
91
97
|
|
|
@@ -105,9 +111,10 @@ surface, requirements, and per-extension upstream changes.
|
|
|
105
111
|
### Migration: retired hard-stop harness
|
|
106
112
|
|
|
107
113
|
The former `.pi/harnesses/damage-control/` hard-stop harness and its standalone recipe
|
|
108
|
-
are retired. Refresh pi harnesses with
|
|
109
|
-
|
|
110
|
-
and
|
|
114
|
+
are retired. Refresh pi harnesses with `agent-fleet upgrade` (or guided setup, which
|
|
115
|
+
calls it): removal is bound by the ownership rule, so only an unchanged, recorded copy
|
|
116
|
+
goes — user-modified and unowned copies are preserved, and the managed `justfile` region
|
|
117
|
+
is refreshed without touching recipes outside the sentinels. Use `damage-control-continue` for standalone and
|
|
111
118
|
Agent Hub safety; missing child safety now fails closed instead of falling back or spawning
|
|
112
119
|
unguarded.
|
|
113
120
|
|