@chankov/agent-fleet 1.0.0 → 1.0.2
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/agents/model-profiles.yaml +2 -2
- package/.pi/extensions/package-lock.json +77 -45
- package/.pi/harnesses/agent-hub/README.md +116 -16
- package/.pi/harnesses/agent-hub/budget-continuation.ts +73 -0
- package/.pi/harnesses/agent-hub/capability-confirmation.ts +47 -0
- package/.pi/harnesses/agent-hub/capability-packs.ts +180 -0
- package/.pi/harnesses/agent-hub/context-budget-snapshot.ts +105 -0
- package/.pi/harnesses/agent-hub/context-pressure.ts +191 -0
- package/.pi/harnesses/agent-hub/hub-state-audit.js +73 -0
- package/.pi/harnesses/agent-hub/index.ts +1095 -465
- package/.pi/harnesses/agent-hub/package.json +1 -1
- package/.pi/harnesses/agent-hub/posture.ts +72 -17
- package/.pi/harnesses/agent-hub/run-budget.js +73 -13
- package/.pi/harnesses/agent-hub/spawn.ts +14 -2
- package/.pi/harnesses/ask-user-remote/index.ts +59 -4
- package/.pi/harnesses/coms/package.json +1 -1
- package/.pi/harnesses/damage-control-continue/package.json +1 -1
- package/.pi/harnesses/lib/context-budget-child-prompt.ts +179 -0
- package/.pi/harnesses/lib/context-budget-hub-prompt.ts +116 -0
- package/.pi/harnesses/lib/context-budget-view.ts +107 -0
- package/.pi/harnesses/lib/context-budget.ts +114 -0
- package/.pi/harnesses/lib/fleet-dashboard-ops.ts +37 -0
- package/.pi/harnesses/lib/fleet-detail-view.ts +92 -2
- package/.pi/harnesses/package-lock.json +73 -80
- package/.versions/1.0.1/.pi/agents/dispatch-policy.yaml +32 -0
- package/.versions/1.0.1/.pi/agents/model-profiles.yaml +27 -0
- package/.versions/1.0.1/.pi/agents/peers.yaml +142 -0
- package/.versions/1.0.1/.pi/agents/teams.yaml +41 -0
- package/.versions/1.0.1/.pi/damage-control-rules.yaml +297 -0
- package/.versions/1.0.1/.pi/extensions/agent-fleet-update-check/README.md +57 -0
- package/.versions/1.0.1/.pi/extensions/agent-fleet-update-check/index.ts +161 -0
- package/.versions/1.0.1/.pi/extensions/agent-fleet-update-check/package.json +6 -0
- package/.versions/1.0.1/.pi/extensions/btw/README.md +120 -0
- package/.versions/1.0.1/.pi/extensions/btw/index.ts +914 -0
- package/.versions/1.0.1/.pi/extensions/btw/package.json +6 -0
- package/.versions/1.0.1/.pi/extensions/btw/state.js +179 -0
- package/.versions/1.0.1/.pi/extensions/chrome-devtools-mcp/README.md +55 -0
- package/.versions/1.0.1/.pi/extensions/chrome-devtools-mcp/index.ts +93 -0
- package/.versions/1.0.1/.pi/extensions/chrome-devtools-mcp/package.json +6 -0
- package/.versions/1.0.1/.pi/extensions/compact-and-continue/README.md +42 -0
- package/.versions/1.0.1/.pi/extensions/compact-and-continue/index.ts +120 -0
- package/.versions/1.0.1/.pi/extensions/compact-and-continue/package.json +6 -0
- package/.versions/1.0.1/.pi/extensions/mcp-bridge/README.md +46 -0
- package/.versions/1.0.1/.pi/extensions/mcp-bridge/index.ts +206 -0
- package/.versions/1.0.1/.pi/extensions/mcp-bridge/package.json +6 -0
- package/.versions/1.0.1/.pi/extensions/package-lock.json +1143 -0
- package/.versions/1.0.1/.pi/extensions/package.json +9 -0
- package/.versions/1.0.1/.pi/extensions/pi-voice-stt/README.md +205 -0
- package/.versions/1.0.1/.pi/extensions/pi-voice-stt/config.ts +198 -0
- package/.versions/1.0.1/.pi/extensions/pi-voice-stt/examples/stt.json +35 -0
- package/.versions/1.0.1/.pi/extensions/pi-voice-stt/index.ts +248 -0
- package/.versions/1.0.1/.pi/extensions/pi-voice-stt/package.json +6 -0
- package/.versions/1.0.1/.pi/extensions/pi-voice-stt/providers.ts +214 -0
- package/.versions/1.0.1/.pi/extensions/pi-voice-stt/recorder.ts +158 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/README.md +1065 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/access-approval.ts +135 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/artifacts.js +146 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/assertion-ledger.js +58 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/backend-policy.js +174 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/context-window.js +106 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/delegate.ts +435 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/docs-lane.js +122 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/drift-watchdog.js +211 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/evidence-rules.js +96 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/external-blocker.js +85 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/footer.ts +35 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/helpers.ts +266 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/hub-state-audit.js +55 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/index.ts +9343 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/monitor-control.ts +9 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/monitor-invoke-journal.ts +131 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/monitor-invoke.ts +92 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/monitor-lifecycle.ts +13 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/monitor-publisher.ts +59 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/monitor-recovery.ts +3 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/monitor-runtime.ts +3 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/monitor-session-bridge.ts +266 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/package.json +7 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/peer-spawn-plan.ts +116 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/posture.ts +103 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/provider-semaphore.js +138 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/research-retention.js +34 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/research-watchdog.ts +40 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/return-contract.js +293 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/return-extract.js +75 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/review-findings.js +102 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/run-budget.js +540 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/run-namespace.js +87 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/safety-routing.ts +22 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/scope-gate.js +103 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/session-health.js +110 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/spawn.ts +354 -0
- package/.versions/1.0.1/.pi/harnesses/agent-hub/version.ts +42 -0
- package/.versions/1.0.1/.pi/harnesses/ask-user-remote/README.md +53 -0
- package/.versions/1.0.1/.pi/harnesses/ask-user-remote/index.ts +477 -0
- package/.versions/1.0.1/.pi/harnesses/ask-user-remote/race-core.js +106 -0
- package/.versions/1.0.1/.pi/harnesses/coms/README.md +100 -0
- package/.versions/1.0.1/.pi/harnesses/coms/index.ts +1767 -0
- package/.versions/1.0.1/.pi/harnesses/coms/package.json +7 -0
- package/.versions/1.0.1/.pi/harnesses/coms/version.ts +42 -0
- package/.versions/1.0.1/.pi/harnesses/damage-control-continue/README.md +124 -0
- package/.versions/1.0.1/.pi/harnesses/damage-control-continue/index.ts +536 -0
- package/.versions/1.0.1/.pi/harnesses/damage-control-continue/package.json +7 -0
- package/.versions/1.0.1/.pi/harnesses/damage-control-continue/version.ts +42 -0
- package/.versions/1.0.1/.pi/harnesses/lib/coms-registry-entry.ts +94 -0
- package/.versions/1.0.1/.pi/harnesses/lib/damage-control-shared.ts +197 -0
- package/.versions/1.0.1/.pi/harnesses/lib/fleet-dashboard-ops.ts +155 -0
- package/.versions/1.0.1/.pi/harnesses/lib/fleet-dashboard-view.ts +140 -0
- package/.versions/1.0.1/.pi/harnesses/lib/fleet-detail-view.ts +43 -0
- package/.versions/1.0.1/.pi/harnesses/lib/fleet-overlay.ts +26 -0
- package/.versions/1.0.1/.pi/harnesses/lib/fleet-panel.ts +34 -0
- package/.versions/1.0.1/.pi/harnesses/lib/fleet-read-model.ts +131 -0
- package/.versions/1.0.1/.pi/harnesses/lib/fleet-selection.ts +24 -0
- package/.versions/1.0.1/.pi/harnesses/lib/herdr-client.ts +472 -0
- package/.versions/1.0.1/.pi/harnesses/lib/herdr-presence.ts +399 -0
- package/.versions/1.0.1/.pi/harnesses/lib/hermes-monitor-events.ts +136 -0
- package/.versions/1.0.1/.pi/harnesses/lib/hermes-monitor-herdr.ts +28 -0
- package/.versions/1.0.1/.pi/harnesses/lib/hermes-monitor-model.ts +18 -0
- package/.versions/1.0.1/.pi/harnesses/lib/hermes-monitor-registry.ts +6 -0
- package/.versions/1.0.1/.pi/harnesses/lib/hermes-monitor-socket.ts +163 -0
- package/.versions/1.0.1/.pi/harnesses/lib/hermes-monitor-store.ts +31 -0
- package/.versions/1.0.1/.pi/harnesses/lib/spawned-peers.js +190 -0
- package/.versions/1.0.1/.pi/harnesses/package-lock.json +2046 -0
- package/.versions/1.0.1/.pi/harnesses/package.json +10 -0
- package/.versions/1.0.1/.pi/prompts/af-build.md +24 -0
- package/.versions/1.0.1/.pi/prompts/af-code-simplify.md +22 -0
- package/.versions/1.0.1/.pi/prompts/af-plan.md +16 -0
- package/.versions/1.0.1/.pi/prompts/af-review.md +16 -0
- package/.versions/1.0.1/.pi/prompts/af-set-hermes-telegram.md +15 -0
- package/.versions/1.0.1/.pi/prompts/af-set-hermes-watchdog.md +6 -0
- package/.versions/1.0.1/.pi/prompts/af-ship.md +17 -0
- package/.versions/1.0.1/.pi/prompts/af-spec.md +15 -0
- package/.versions/1.0.1/.pi/prompts/af-test.md +19 -0
- package/.versions/1.0.1/.pi/skills/bowser/SKILL.md +145 -0
- package/.versions/1.0.1/.version +1 -0
- package/.versions/1.0.1/agents/architect.md +24 -0
- package/.versions/1.0.1/agents/bowser.md +27 -0
- package/.versions/1.0.1/agents/builder.md +54 -0
- package/.versions/1.0.1/agents/code-reviewer.md +208 -0
- package/.versions/1.0.1/agents/deep-researcher.md +32 -0
- package/.versions/1.0.1/agents/documenter.md +18 -0
- package/.versions/1.0.1/agents/orchestrator.md +72 -0
- package/.versions/1.0.1/agents/plan-reviewer.md +83 -0
- package/.versions/1.0.1/agents/planner.md +70 -0
- package/.versions/1.0.1/agents/releaser.md +24 -0
- package/.versions/1.0.1/agents/researcher.md +28 -0
- package/.versions/1.0.1/agents/security-auditor.md +167 -0
- package/.versions/1.0.1/agents/test-engineer.md +153 -0
- package/.versions/1.0.1/agents/web-debugger.md +43 -0
- package/.versions/1.0.1/agents/web-performance-auditor.md +193 -0
- package/.versions/1.0.1/bin/catalog/harness-runtime-closure.json +38 -0
- package/.versions/1.0.1/codex/CONDUCTOR.md +148 -0
- package/.versions/1.0.1/docs/ARCHITECTURE.md +337 -0
- package/.versions/1.0.1/docs/agent-fleet-setup.md +437 -0
- package/.versions/1.0.1/docs/claude-code-coms-bridge.md +128 -0
- package/.versions/1.0.1/docs/codex-remote-conductor.md +170 -0
- package/.versions/1.0.1/docs/coms-hermes-bridge.md +189 -0
- package/.versions/1.0.1/docs/getting-started.md +98 -0
- package/.versions/1.0.1/docs/npm-install.md +292 -0
- package/.versions/1.0.1/docs/pi-extensions.md +412 -0
- package/.versions/1.0.1/docs/pi-setup.md +74 -0
- package/.versions/1.0.1/docs/skill-anatomy.md +150 -0
- package/.versions/1.0.1/hermes/README.md +347 -0
- package/.versions/1.0.1/hermes/desktop-plugins/agent-fleet-herdr/plugin.js +1291 -0
- package/.versions/1.0.1/hermes/desktop-plugins/agent-fleet-herdr/presentation.js +672 -0
- package/.versions/1.0.1/hermes/desktop-plugins/agent-fleet-monitor/plugin.js +19 -0
- package/.versions/1.0.1/hermes/desktop-plugins/agent-fleet-monitor/state.js +10 -0
- package/.versions/1.0.1/hermes/gates/gate-o-capability.md +8 -0
- package/.versions/1.0.1/hermes/gates/gate-o-validator-fixtures.json +1 -0
- package/.versions/1.0.1/hermes/plugins/agent-fleet-herdr/dashboard/activity.py +770 -0
- package/.versions/1.0.1/hermes/plugins/agent-fleet-herdr/dashboard/coms_registry.py +134 -0
- package/.versions/1.0.1/hermes/plugins/agent-fleet-herdr/dashboard/coms_send.py +350 -0
- package/.versions/1.0.1/hermes/plugins/agent-fleet-herdr/dashboard/herdr_source.py +193 -0
- package/.versions/1.0.1/hermes/plugins/agent-fleet-herdr/dashboard/manifest.json +4 -0
- package/.versions/1.0.1/hermes/plugins/agent-fleet-herdr/dashboard/plugin_api.py +444 -0
- package/.versions/1.0.1/hermes/plugins/agent-fleet-herdr/dashboard/sessions.py +205 -0
- package/.versions/1.0.1/hermes/plugins/agent-fleet-herdr/dashboard/tasks.py +300 -0
- package/.versions/1.0.1/hermes/plugins/agent-fleet-herdr/dashboard/watch.py +819 -0
- package/.versions/1.0.1/hermes/plugins/agent-fleet-herdr/plugin.yaml +8 -0
- package/.versions/1.0.1/hermes/plugins/agent-fleet-monitor/dashboard/adapter.py +139 -0
- package/.versions/1.0.1/hermes/plugins/agent-fleet-monitor/dashboard/manifest.json +11 -0
- package/.versions/1.0.1/hermes/plugins/agent-fleet-monitor/dashboard/plugin_api.py +50 -0
- package/.versions/1.0.1/hermes/skills/hub-conductor/SKILL.md +84 -0
- package/.versions/1.0.1/hermes/skills/hub-liaison/SKILL.md +84 -0
- package/.versions/1.0.1/hermes/skills/hub-watchdog/SKILL.md +76 -0
- package/.versions/1.0.1/hermes/skills/hub-watchdog/manifest.json +1 -0
- package/.versions/1.0.1/hermes/skills/hub-watchdog/scripts/watchdog.py +249 -0
- package/.versions/1.0.1/hermes/skills/hub-watchdog/scripts/watchdog_actions.py +124 -0
- package/.versions/1.0.1/hermes/skills/hub-watchdog/scripts/watchdog_contract.py +76 -0
- package/.versions/1.0.1/hermes/skills/hub-watchdog/scripts/watchdog_delivery.py +10 -0
- package/.versions/1.0.1/hermes/skills/hub-watchdog/scripts/watchdog_engine.py +128 -0
- package/.versions/1.0.1/hermes/skills/hub-watchdog/scripts/watchdog_judgment.py +41 -0
- package/.versions/1.0.1/hermes/skills/hub-watchdog/scripts/watchdog_recovery.py +103 -0
- package/.versions/1.0.1/hermes/skills/hub-watchdog/scripts/watchdog_state.py +163 -0
- package/.versions/1.0.1/hermes/skills/hub-watchdog/scripts/watchdog_transport.py +138 -0
- package/.versions/1.0.1/hermes/watchdog-tests/__init__.py +0 -0
- package/.versions/1.0.1/hooks/coms-stop-hook.mjs +84 -0
- package/.versions/1.0.1/install-manifest.json +2745 -0
- package/.versions/1.0.1/justfile +272 -0
- package/.versions/1.0.1/manifest-meta.json +882 -0
- package/.versions/1.0.1/references/accessibility-checklist.md +160 -0
- package/.versions/1.0.1/references/definition-of-done.md +67 -0
- package/.versions/1.0.1/references/fleet-coordination-patterns.md +151 -0
- package/.versions/1.0.1/references/observability-checklist.md +91 -0
- package/.versions/1.0.1/references/orchestration-patterns.md +370 -0
- package/.versions/1.0.1/references/performance-checklist.md +153 -0
- package/.versions/1.0.1/references/prompting-patterns.md +380 -0
- package/.versions/1.0.1/references/security-checklist.md +179 -0
- package/.versions/1.0.1/references/testing-patterns.md +236 -0
- package/.versions/1.0.1/scripts/codex-conductor.ts +41 -0
- package/.versions/1.0.1/scripts/codex-remote-control.ts +167 -0
- package/.versions/1.0.1/scripts/coms-claude-bridge.ts +411 -0
- package/.versions/1.0.1/scripts/coms-cli.ts +484 -0
- package/.versions/1.0.1/scripts/coms-hermes-bridge.ts +413 -0
- package/.versions/1.0.1/scripts/fleet.ts +185 -0
- package/.versions/1.0.1/scripts/hermes-monitor-capability-runner.ts +25 -0
- package/.versions/1.0.1/scripts/hermes-monitor-scenario.ts +474 -0
- package/.versions/1.0.1/scripts/hermes-watchdog-capability-probe.ts +45 -0
- package/.versions/1.0.1/scripts/install-hermes-plugin.sh +180 -0
- package/.versions/1.0.1/scripts/lib/claude-bridge-core.ts +210 -0
- package/.versions/1.0.1/scripts/lib/codex-conductor.ts +88 -0
- package/.versions/1.0.1/scripts/lib/codex-remote-control.ts +480 -0
- package/.versions/1.0.1/scripts/lib/coms-envelope.ts +582 -0
- package/.versions/1.0.1/scripts/lib/fake-herdr-server.ts +88 -0
- package/.versions/1.0.1/scripts/lib/fleet-command.ts +266 -0
- package/.versions/1.0.1/scripts/lib/herdr-layout.ts +281 -0
- package/.versions/1.0.1/scripts/lib/hermes-bridge-core.ts +241 -0
- package/.versions/1.0.1/scripts/lib/hermes-monitor-events.ts +1 -0
- package/.versions/1.0.1/scripts/lib/hermes-monitor-herdr.ts +2 -0
- package/.versions/1.0.1/scripts/lib/hermes-monitor-model.ts +3 -0
- package/.versions/1.0.1/scripts/lib/hermes-monitor-registry.ts +2 -0
- package/.versions/1.0.1/scripts/lib/hermes-monitor-socket.ts +2 -0
- package/.versions/1.0.1/scripts/lib/hermes-monitor-store.ts +2 -0
- package/.versions/1.0.1/scripts/lib/monitor-env.ts +146 -0
- package/.versions/1.0.1/scripts/lib/peer-launch.ts +318 -0
- package/.versions/1.0.1/scripts/lib/persona-banner.ts +62 -0
- package/.versions/1.0.1/scripts/lib/spawn-stagger.ts +101 -0
- package/.versions/1.0.1/scripts/lib/team-project.ts +213 -0
- package/.versions/1.0.1/scripts/lib/team-snapshot.ts +147 -0
- package/.versions/1.0.1/scripts/peer-banner.ts +40 -0
- package/.versions/1.0.1/scripts/peer-launch.ts +259 -0
- package/.versions/1.0.1/scripts/team-snapshot.ts +237 -0
- package/.versions/1.0.1/scripts/team-up.ts +406 -0
- package/.versions/1.0.1/skills/_internal/grilling.md +11 -0
- package/.versions/1.0.1/skills/browser-testing-with-devtools/SKILL.md +351 -0
- package/.versions/1.0.1/skills/code-review-and-quality/SKILL.md +381 -0
- package/.versions/1.0.1/skills/compound-learning/SKILL.md +137 -0
- package/.versions/1.0.1/skills/context-engineering/SKILL.md +291 -0
- package/.versions/1.0.1/skills/deprecation-and-migration/SKILL.md +206 -0
- package/.versions/1.0.1/skills/designing-agents/SKILL.md +394 -0
- package/.versions/1.0.1/skills/designing-agents/pi-harness-authoring.md +222 -0
- package/.versions/1.0.1/skills/frontend-ui-engineering/SKILL.md +328 -0
- package/.versions/1.0.1/skills/git-workflow-and-versioning/SKILL.md +316 -0
- package/.versions/1.0.1/skills/idea-refine/SKILL.md +182 -0
- package/.versions/1.0.1/skills/idea-refine/examples.md +238 -0
- package/.versions/1.0.1/skills/idea-refine/frameworks.md +99 -0
- package/.versions/1.0.1/skills/idea-refine/refinement-criteria.md +113 -0
- package/.versions/1.0.1/skills/idea-refine/scripts/idea-refine.sh +15 -0
- package/.versions/1.0.1/skills/incremental-implementation/SKILL.md +287 -0
- package/.versions/1.0.1/skills/interview-me/SKILL.md +226 -0
- package/.versions/1.0.1/skills/orchestration-verification/SKILL.md +181 -0
- package/.versions/1.0.1/skills/peer-coms/SKILL.md +90 -0
- package/.versions/1.0.1/skills/performance-optimization/SKILL.md +350 -0
- package/.versions/1.0.1/skills/planning-and-task-breakdown/SKILL.md +254 -0
- package/.versions/1.0.1/skills/security-and-hardening/SKILL.md +461 -0
- package/.versions/1.0.1/skills/spec-driven-development/SKILL.md +257 -0
- package/.versions/1.0.1/skills/using-agent-skills/SKILL.md +199 -0
- package/.versions/1.0.1/systemd/user/agent-fleet-codex-remote-control.service.in +23 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/LICENSE +21 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/README.md +11 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/api-and-interface-design/SKILL.md +294 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/browser-testing-with-devtools/SKILL.md +317 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/ci-cd-and-automation/SKILL.md +390 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/code-review-and-quality/SKILL.md +396 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/code-simplification/SKILL.md +331 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/context-engineering/SKILL.md +289 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/debugging-and-error-recovery/SKILL.md +300 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/deprecation-and-migration/SKILL.md +247 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/documentation-and-adrs/SKILL.md +278 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/doubt-driven-development/SKILL.md +243 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/frontend-ui-engineering/SKILL.md +328 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/git-workflow-and-versioning/SKILL.md +355 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/idea-refine/SKILL.md +178 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/idea-refine/examples.md +238 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/idea-refine/frameworks.md +99 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/idea-refine/refinement-criteria.md +113 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/idea-refine/scripts/idea-refine.sh +15 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/incremental-implementation/SKILL.md +249 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/interview-me/SKILL.md +225 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/observability-and-instrumentation/SKILL.md +203 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/performance-optimization/SKILL.md +350 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/planning-and-task-breakdown/SKILL.md +234 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/security-and-hardening/SKILL.md +467 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/shipping-and-launch/SKILL.md +310 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/source-driven-development/SKILL.md +194 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/spec-driven-development/SKILL.md +206 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/test-driven-development/SKILL.md +383 -0
- package/.versions/1.0.1/vendor/agent-skills-upstream/skills/using-agent-skills/SKILL.md +191 -0
- package/.versions/1.0.2/.pi/agents/dispatch-policy.yaml +32 -0
- package/.versions/1.0.2/.pi/agents/model-profiles.yaml +27 -0
- package/.versions/1.0.2/.pi/agents/peers.yaml +142 -0
- package/.versions/1.0.2/.pi/agents/teams.yaml +41 -0
- package/.versions/1.0.2/.pi/damage-control-rules.yaml +297 -0
- package/.versions/1.0.2/.pi/extensions/agent-fleet-update-check/README.md +57 -0
- package/.versions/1.0.2/.pi/extensions/agent-fleet-update-check/index.ts +161 -0
- package/.versions/1.0.2/.pi/extensions/agent-fleet-update-check/package.json +6 -0
- package/.versions/1.0.2/.pi/extensions/btw/README.md +120 -0
- package/.versions/1.0.2/.pi/extensions/btw/index.ts +914 -0
- package/.versions/1.0.2/.pi/extensions/btw/package.json +6 -0
- package/.versions/1.0.2/.pi/extensions/btw/state.js +179 -0
- package/.versions/1.0.2/.pi/extensions/chrome-devtools-mcp/README.md +55 -0
- package/.versions/1.0.2/.pi/extensions/chrome-devtools-mcp/index.ts +93 -0
- package/.versions/1.0.2/.pi/extensions/chrome-devtools-mcp/package.json +6 -0
- package/.versions/1.0.2/.pi/extensions/compact-and-continue/README.md +42 -0
- package/.versions/1.0.2/.pi/extensions/compact-and-continue/index.ts +120 -0
- package/.versions/1.0.2/.pi/extensions/compact-and-continue/package.json +6 -0
- package/.versions/1.0.2/.pi/extensions/mcp-bridge/README.md +46 -0
- package/.versions/1.0.2/.pi/extensions/mcp-bridge/index.ts +206 -0
- package/.versions/1.0.2/.pi/extensions/mcp-bridge/package.json +6 -0
- package/.versions/1.0.2/.pi/extensions/package-lock.json +1175 -0
- package/.versions/1.0.2/.pi/extensions/package.json +9 -0
- package/.versions/1.0.2/.pi/extensions/pi-voice-stt/README.md +205 -0
- package/.versions/1.0.2/.pi/extensions/pi-voice-stt/config.ts +198 -0
- package/.versions/1.0.2/.pi/extensions/pi-voice-stt/examples/stt.json +35 -0
- package/.versions/1.0.2/.pi/extensions/pi-voice-stt/index.ts +248 -0
- package/.versions/1.0.2/.pi/extensions/pi-voice-stt/package.json +6 -0
- package/.versions/1.0.2/.pi/extensions/pi-voice-stt/providers.ts +214 -0
- package/.versions/1.0.2/.pi/extensions/pi-voice-stt/recorder.ts +158 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/README.md +1156 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/access-approval.ts +135 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/artifacts.js +146 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/assertion-ledger.js +58 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/backend-policy.js +174 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/budget-continuation.ts +73 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/capability-confirmation.ts +47 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/capability-packs.ts +180 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/context-budget-snapshot.ts +105 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/context-pressure.ts +191 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/context-window.js +106 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/delegate.ts +435 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/docs-lane.js +122 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/drift-watchdog.js +211 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/evidence-rules.js +96 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/external-blocker.js +85 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/footer.ts +35 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/helpers.ts +266 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/hub-state-audit.js +73 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/index.ts +9909 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/monitor-control.ts +9 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/monitor-invoke-journal.ts +131 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/monitor-invoke.ts +92 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/monitor-lifecycle.ts +13 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/monitor-publisher.ts +59 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/monitor-recovery.ts +3 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/monitor-runtime.ts +3 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/monitor-session-bridge.ts +266 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/package.json +7 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/peer-spawn-plan.ts +116 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/posture.ts +158 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/provider-semaphore.js +138 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/research-retention.js +34 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/research-watchdog.ts +40 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/return-contract.js +293 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/return-extract.js +75 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/review-findings.js +102 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/run-budget.js +539 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/run-namespace.js +87 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/safety-routing.ts +22 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/scope-gate.js +103 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/session-health.js +110 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/spawn.ts +366 -0
- package/.versions/1.0.2/.pi/harnesses/agent-hub/version.ts +42 -0
- package/.versions/1.0.2/.pi/harnesses/ask-user-remote/README.md +53 -0
- package/.versions/1.0.2/.pi/harnesses/ask-user-remote/index.ts +532 -0
- package/.versions/1.0.2/.pi/harnesses/ask-user-remote/race-core.js +106 -0
- package/.versions/1.0.2/.pi/harnesses/coms/README.md +100 -0
- package/.versions/1.0.2/.pi/harnesses/coms/index.ts +1767 -0
- package/.versions/1.0.2/.pi/harnesses/coms/package.json +7 -0
- package/.versions/1.0.2/.pi/harnesses/coms/version.ts +42 -0
- package/.versions/1.0.2/.pi/harnesses/damage-control-continue/README.md +124 -0
- package/.versions/1.0.2/.pi/harnesses/damage-control-continue/index.ts +536 -0
- package/.versions/1.0.2/.pi/harnesses/damage-control-continue/package.json +7 -0
- package/.versions/1.0.2/.pi/harnesses/damage-control-continue/version.ts +42 -0
- package/.versions/1.0.2/.pi/harnesses/lib/coms-registry-entry.ts +94 -0
- package/.versions/1.0.2/.pi/harnesses/lib/context-budget-child-prompt.ts +179 -0
- package/.versions/1.0.2/.pi/harnesses/lib/context-budget-hub-prompt.ts +116 -0
- package/.versions/1.0.2/.pi/harnesses/lib/context-budget-view.ts +107 -0
- package/.versions/1.0.2/.pi/harnesses/lib/context-budget.ts +114 -0
- package/.versions/1.0.2/.pi/harnesses/lib/damage-control-shared.ts +197 -0
- package/.versions/1.0.2/.pi/harnesses/lib/fixtures/context-budget-profiles.json +11 -0
- package/.versions/1.0.2/.pi/harnesses/lib/fixtures/hub-prompt-operator.legacy.txt +73 -0
- package/.versions/1.0.2/.pi/harnesses/lib/fixtures/hub-prompt-orchestrator.legacy.txt +73 -0
- package/.versions/1.0.2/.pi/harnesses/lib/fleet-dashboard-ops.ts +155 -0
- package/.versions/1.0.2/.pi/harnesses/lib/fleet-dashboard-view.ts +140 -0
- package/.versions/1.0.2/.pi/harnesses/lib/fleet-detail-view.ts +133 -0
- package/.versions/1.0.2/.pi/harnesses/lib/fleet-overlay.ts +26 -0
- package/.versions/1.0.2/.pi/harnesses/lib/fleet-panel.ts +34 -0
- package/.versions/1.0.2/.pi/harnesses/lib/fleet-read-model.ts +131 -0
- package/.versions/1.0.2/.pi/harnesses/lib/fleet-selection.ts +24 -0
- package/.versions/1.0.2/.pi/harnesses/lib/herdr-client.ts +472 -0
- package/.versions/1.0.2/.pi/harnesses/lib/herdr-presence.ts +399 -0
- package/.versions/1.0.2/.pi/harnesses/lib/hermes-monitor-events.ts +136 -0
- package/.versions/1.0.2/.pi/harnesses/lib/hermes-monitor-herdr.ts +28 -0
- package/.versions/1.0.2/.pi/harnesses/lib/hermes-monitor-model.ts +18 -0
- package/.versions/1.0.2/.pi/harnesses/lib/hermes-monitor-registry.ts +6 -0
- package/.versions/1.0.2/.pi/harnesses/lib/hermes-monitor-socket.ts +163 -0
- package/.versions/1.0.2/.pi/harnesses/lib/hermes-monitor-store.ts +31 -0
- package/.versions/1.0.2/.pi/harnesses/lib/spawned-peers.js +190 -0
- package/.versions/1.0.2/.pi/harnesses/package-lock.json +2039 -0
- package/.versions/1.0.2/.pi/harnesses/package.json +10 -0
- package/.versions/1.0.2/.pi/prompts/af-build.md +24 -0
- package/.versions/1.0.2/.pi/prompts/af-code-simplify.md +22 -0
- package/.versions/1.0.2/.pi/prompts/af-plan.md +16 -0
- package/.versions/1.0.2/.pi/prompts/af-review.md +16 -0
- package/.versions/1.0.2/.pi/prompts/af-set-hermes-telegram.md +15 -0
- package/.versions/1.0.2/.pi/prompts/af-set-hermes-watchdog.md +6 -0
- package/.versions/1.0.2/.pi/prompts/af-ship.md +17 -0
- package/.versions/1.0.2/.pi/prompts/af-spec.md +15 -0
- package/.versions/1.0.2/.pi/prompts/af-test.md +19 -0
- package/.versions/1.0.2/.pi/skills/bowser/SKILL.md +145 -0
- package/.versions/1.0.2/.version +1 -0
- package/.versions/1.0.2/agents/architect.md +24 -0
- package/.versions/1.0.2/agents/bowser.md +27 -0
- package/.versions/1.0.2/agents/builder.md +54 -0
- package/.versions/1.0.2/agents/code-reviewer.md +208 -0
- package/.versions/1.0.2/agents/deep-researcher.md +32 -0
- package/.versions/1.0.2/agents/documenter.md +18 -0
- package/.versions/1.0.2/agents/orchestrator.md +20 -0
- package/.versions/1.0.2/agents/plan-reviewer.md +83 -0
- package/.versions/1.0.2/agents/planner.md +70 -0
- package/.versions/1.0.2/agents/releaser.md +24 -0
- package/.versions/1.0.2/agents/researcher.md +28 -0
- package/.versions/1.0.2/agents/security-auditor.md +167 -0
- package/.versions/1.0.2/agents/test-engineer.md +153 -0
- package/.versions/1.0.2/agents/web-debugger.md +43 -0
- package/.versions/1.0.2/agents/web-performance-auditor.md +193 -0
- package/.versions/1.0.2/bin/catalog/harness-runtime-closure.json +38 -0
- package/.versions/1.0.2/codex/CONDUCTOR.md +148 -0
- package/.versions/1.0.2/docs/ARCHITECTURE.md +369 -0
- package/.versions/1.0.2/docs/agent-fleet-setup.md +468 -0
- package/.versions/1.0.2/docs/claude-code-coms-bridge.md +128 -0
- package/.versions/1.0.2/docs/codex-remote-conductor.md +170 -0
- package/.versions/1.0.2/docs/coms-hermes-bridge.md +189 -0
- package/.versions/1.0.2/docs/getting-started.md +98 -0
- package/.versions/1.0.2/docs/npm-install.md +292 -0
- package/.versions/1.0.2/docs/pi-extensions.md +439 -0
- package/.versions/1.0.2/docs/pi-setup.md +74 -0
- package/.versions/1.0.2/docs/skill-anatomy.md +150 -0
- package/.versions/1.0.2/hermes/README.md +347 -0
- package/.versions/1.0.2/hermes/desktop-plugins/agent-fleet-herdr/plugin.js +1291 -0
- package/.versions/1.0.2/hermes/desktop-plugins/agent-fleet-herdr/presentation.js +672 -0
- package/.versions/1.0.2/hermes/desktop-plugins/agent-fleet-monitor/plugin.js +19 -0
- package/.versions/1.0.2/hermes/desktop-plugins/agent-fleet-monitor/state.js +10 -0
- package/.versions/1.0.2/hermes/gates/gate-o-capability.md +8 -0
- package/.versions/1.0.2/hermes/gates/gate-o-validator-fixtures.json +1 -0
- package/.versions/1.0.2/hermes/plugins/agent-fleet-herdr/dashboard/activity.py +770 -0
- package/.versions/1.0.2/hermes/plugins/agent-fleet-herdr/dashboard/coms_registry.py +134 -0
- package/.versions/1.0.2/hermes/plugins/agent-fleet-herdr/dashboard/coms_send.py +350 -0
- package/.versions/1.0.2/hermes/plugins/agent-fleet-herdr/dashboard/herdr_source.py +193 -0
- package/.versions/1.0.2/hermes/plugins/agent-fleet-herdr/dashboard/manifest.json +4 -0
- package/.versions/1.0.2/hermes/plugins/agent-fleet-herdr/dashboard/plugin_api.py +444 -0
- package/.versions/1.0.2/hermes/plugins/agent-fleet-herdr/dashboard/sessions.py +205 -0
- package/.versions/1.0.2/hermes/plugins/agent-fleet-herdr/dashboard/tasks.py +300 -0
- package/.versions/1.0.2/hermes/plugins/agent-fleet-herdr/dashboard/watch.py +819 -0
- package/.versions/1.0.2/hermes/plugins/agent-fleet-herdr/plugin.yaml +8 -0
- package/.versions/1.0.2/hermes/plugins/agent-fleet-monitor/dashboard/adapter.py +139 -0
- package/.versions/1.0.2/hermes/plugins/agent-fleet-monitor/dashboard/manifest.json +11 -0
- package/.versions/1.0.2/hermes/plugins/agent-fleet-monitor/dashboard/plugin_api.py +50 -0
- package/.versions/1.0.2/hermes/skills/hub-conductor/SKILL.md +84 -0
- package/.versions/1.0.2/hermes/skills/hub-liaison/SKILL.md +84 -0
- package/.versions/1.0.2/hermes/skills/hub-watchdog/SKILL.md +76 -0
- package/.versions/1.0.2/hermes/skills/hub-watchdog/manifest.json +1 -0
- package/.versions/1.0.2/hermes/skills/hub-watchdog/scripts/watchdog.py +249 -0
- package/.versions/1.0.2/hermes/skills/hub-watchdog/scripts/watchdog_actions.py +124 -0
- package/.versions/1.0.2/hermes/skills/hub-watchdog/scripts/watchdog_contract.py +76 -0
- package/.versions/1.0.2/hermes/skills/hub-watchdog/scripts/watchdog_delivery.py +10 -0
- package/.versions/1.0.2/hermes/skills/hub-watchdog/scripts/watchdog_engine.py +128 -0
- package/.versions/1.0.2/hermes/skills/hub-watchdog/scripts/watchdog_judgment.py +41 -0
- package/.versions/1.0.2/hermes/skills/hub-watchdog/scripts/watchdog_recovery.py +103 -0
- package/.versions/1.0.2/hermes/skills/hub-watchdog/scripts/watchdog_state.py +163 -0
- package/.versions/1.0.2/hermes/skills/hub-watchdog/scripts/watchdog_transport.py +138 -0
- package/.versions/1.0.2/hermes/watchdog-tests/__init__.py +0 -0
- package/.versions/1.0.2/hooks/coms-stop-hook.mjs +84 -0
- package/.versions/1.0.2/install-manifest.json +2745 -0
- package/.versions/1.0.2/justfile +272 -0
- package/.versions/1.0.2/manifest-meta.json +882 -0
- package/.versions/1.0.2/references/accessibility-checklist.md +160 -0
- package/.versions/1.0.2/references/definition-of-done.md +67 -0
- package/.versions/1.0.2/references/fleet-coordination-patterns.md +151 -0
- package/.versions/1.0.2/references/observability-checklist.md +91 -0
- package/.versions/1.0.2/references/orchestration-patterns.md +370 -0
- package/.versions/1.0.2/references/performance-checklist.md +153 -0
- package/.versions/1.0.2/references/prompting-patterns.md +380 -0
- package/.versions/1.0.2/references/security-checklist.md +179 -0
- package/.versions/1.0.2/references/testing-patterns.md +236 -0
- package/.versions/1.0.2/scripts/codex-conductor.ts +41 -0
- package/.versions/1.0.2/scripts/codex-remote-control.ts +167 -0
- package/.versions/1.0.2/scripts/coms-claude-bridge.ts +411 -0
- package/.versions/1.0.2/scripts/coms-cli.ts +484 -0
- package/.versions/1.0.2/scripts/coms-hermes-bridge.ts +413 -0
- package/.versions/1.0.2/scripts/fleet.ts +185 -0
- package/.versions/1.0.2/scripts/hermes-monitor-capability-runner.ts +25 -0
- package/.versions/1.0.2/scripts/hermes-monitor-scenario.ts +474 -0
- package/.versions/1.0.2/scripts/hermes-watchdog-capability-probe.ts +45 -0
- package/.versions/1.0.2/scripts/install-hermes-plugin.sh +180 -0
- package/.versions/1.0.2/scripts/lib/claude-bridge-core.ts +210 -0
- package/.versions/1.0.2/scripts/lib/codex-conductor.ts +88 -0
- package/.versions/1.0.2/scripts/lib/codex-remote-control.ts +480 -0
- package/.versions/1.0.2/scripts/lib/coms-envelope.ts +582 -0
- package/.versions/1.0.2/scripts/lib/fake-herdr-server.ts +88 -0
- package/.versions/1.0.2/scripts/lib/fleet-command.ts +266 -0
- package/.versions/1.0.2/scripts/lib/herdr-layout.ts +281 -0
- package/.versions/1.0.2/scripts/lib/hermes-bridge-core.ts +241 -0
- package/.versions/1.0.2/scripts/lib/hermes-monitor-events.ts +1 -0
- package/.versions/1.0.2/scripts/lib/hermes-monitor-herdr.ts +2 -0
- package/.versions/1.0.2/scripts/lib/hermes-monitor-model.ts +3 -0
- package/.versions/1.0.2/scripts/lib/hermes-monitor-registry.ts +2 -0
- package/.versions/1.0.2/scripts/lib/hermes-monitor-socket.ts +2 -0
- package/.versions/1.0.2/scripts/lib/hermes-monitor-store.ts +2 -0
- package/.versions/1.0.2/scripts/lib/monitor-env.ts +146 -0
- package/.versions/1.0.2/scripts/lib/peer-launch.ts +318 -0
- package/.versions/1.0.2/scripts/lib/persona-banner.ts +62 -0
- package/.versions/1.0.2/scripts/lib/spawn-stagger.ts +101 -0
- package/.versions/1.0.2/scripts/lib/team-project.ts +213 -0
- package/.versions/1.0.2/scripts/lib/team-snapshot.ts +147 -0
- package/.versions/1.0.2/scripts/peer-banner.ts +40 -0
- package/.versions/1.0.2/scripts/peer-launch.ts +259 -0
- package/.versions/1.0.2/scripts/team-snapshot.ts +237 -0
- package/.versions/1.0.2/scripts/team-up.ts +406 -0
- package/.versions/1.0.2/skills/_internal/grilling.md +11 -0
- package/.versions/1.0.2/skills/browser-testing-with-devtools/SKILL.md +351 -0
- package/.versions/1.0.2/skills/code-review-and-quality/SKILL.md +381 -0
- package/.versions/1.0.2/skills/compound-learning/SKILL.md +137 -0
- package/.versions/1.0.2/skills/context-engineering/SKILL.md +291 -0
- package/.versions/1.0.2/skills/deprecation-and-migration/SKILL.md +206 -0
- package/.versions/1.0.2/skills/designing-agents/SKILL.md +394 -0
- package/.versions/1.0.2/skills/designing-agents/pi-harness-authoring.md +222 -0
- package/.versions/1.0.2/skills/frontend-ui-engineering/SKILL.md +328 -0
- package/.versions/1.0.2/skills/git-workflow-and-versioning/SKILL.md +316 -0
- package/.versions/1.0.2/skills/idea-refine/SKILL.md +182 -0
- package/.versions/1.0.2/skills/idea-refine/examples.md +238 -0
- package/.versions/1.0.2/skills/idea-refine/frameworks.md +99 -0
- package/.versions/1.0.2/skills/idea-refine/refinement-criteria.md +113 -0
- package/.versions/1.0.2/skills/idea-refine/scripts/idea-refine.sh +15 -0
- package/.versions/1.0.2/skills/incremental-implementation/SKILL.md +287 -0
- package/.versions/1.0.2/skills/interview-me/SKILL.md +226 -0
- package/.versions/1.0.2/skills/orchestration-verification/SKILL.md +181 -0
- package/.versions/1.0.2/skills/peer-coms/SKILL.md +90 -0
- package/.versions/1.0.2/skills/performance-optimization/SKILL.md +350 -0
- package/.versions/1.0.2/skills/planning-and-task-breakdown/SKILL.md +254 -0
- package/.versions/1.0.2/skills/security-and-hardening/SKILL.md +461 -0
- package/.versions/1.0.2/skills/spec-driven-development/SKILL.md +257 -0
- package/.versions/1.0.2/skills/using-agent-skills/SKILL.md +199 -0
- package/.versions/1.0.2/systemd/user/agent-fleet-codex-remote-control.service.in +23 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/LICENSE +21 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/README.md +11 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/api-and-interface-design/SKILL.md +294 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/browser-testing-with-devtools/SKILL.md +317 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/ci-cd-and-automation/SKILL.md +390 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/code-review-and-quality/SKILL.md +396 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/code-simplification/SKILL.md +331 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/context-engineering/SKILL.md +289 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/debugging-and-error-recovery/SKILL.md +300 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/deprecation-and-migration/SKILL.md +247 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/documentation-and-adrs/SKILL.md +278 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/doubt-driven-development/SKILL.md +243 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/frontend-ui-engineering/SKILL.md +328 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/git-workflow-and-versioning/SKILL.md +355 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/idea-refine/SKILL.md +178 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/idea-refine/examples.md +238 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/idea-refine/frameworks.md +99 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/idea-refine/refinement-criteria.md +113 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/idea-refine/scripts/idea-refine.sh +15 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/incremental-implementation/SKILL.md +249 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/interview-me/SKILL.md +225 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/observability-and-instrumentation/SKILL.md +203 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/performance-optimization/SKILL.md +350 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/planning-and-task-breakdown/SKILL.md +234 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/security-and-hardening/SKILL.md +467 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/shipping-and-launch/SKILL.md +310 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/source-driven-development/SKILL.md +194 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/spec-driven-development/SKILL.md +206 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/test-driven-development/SKILL.md +383 -0
- package/.versions/1.0.2/vendor/agent-skills-upstream/skills/using-agent-skills/SKILL.md +191 -0
- package/CHANGELOG.md +15 -0
- package/README.md +4 -2
- package/agents/code-reviewer.md +1 -1
- package/agents/deep-researcher.md +1 -1
- package/agents/orchestrator.md +4 -56
- package/agents/plan-reviewer.md +1 -1
- package/agents/planner.md +1 -1
- package/agents/security-auditor.md +1 -1
- package/agents/test-engineer.md +1 -1
- package/docs/ARCHITECTURE.md +48 -16
- package/docs/agent-fleet-setup.md +33 -2
- package/docs/pi-extensions.md +29 -2
- package/install-manifest.json +2 -2
- package/package.json +2 -2
|
@@ -0,0 +1,191 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: using-agent-skills
|
|
3
|
+
description: Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# Using Agent Skills
|
|
7
|
+
|
|
8
|
+
## Overview
|
|
9
|
+
|
|
10
|
+
Agent Skills is a collection of engineering workflow skills organized by development phase. Each skill encodes a specific process that senior engineers follow. This meta-skill helps you discover and apply the right skill for your current task.
|
|
11
|
+
|
|
12
|
+
## Skill Discovery
|
|
13
|
+
|
|
14
|
+
When a task arrives, identify the development phase and apply the corresponding skill:
|
|
15
|
+
|
|
16
|
+
```
|
|
17
|
+
Task arrives
|
|
18
|
+
│
|
|
19
|
+
├── Don't know what you want yet? ──────→ interview-me
|
|
20
|
+
├── Have a rough concept, need variants? → idea-refine
|
|
21
|
+
├── New project/feature/change? ──→ spec-driven-development
|
|
22
|
+
├── Have a spec, need tasks? ──────→ planning-and-task-breakdown
|
|
23
|
+
├── Implementing code? ────────────→ incremental-implementation
|
|
24
|
+
│ ├── UI work? ─────────────────→ frontend-ui-engineering
|
|
25
|
+
│ ├── API work? ────────────────→ api-and-interface-design
|
|
26
|
+
│ ├── Need better context? ─────→ context-engineering
|
|
27
|
+
│ ├── Need doc-verified code? ───→ source-driven-development
|
|
28
|
+
│ └── Stakes high / unfamiliar code? ──→ doubt-driven-development
|
|
29
|
+
├── Writing/running tests? ────────→ test-driven-development
|
|
30
|
+
│ └── Browser-based? ───────────→ browser-testing-with-devtools
|
|
31
|
+
├── Something broke? ──────────────→ debugging-and-error-recovery
|
|
32
|
+
├── Reviewing code? ───────────────→ code-review-and-quality
|
|
33
|
+
│ ├── Too complex? ─────────────→ code-simplification
|
|
34
|
+
│ ├── Security concerns? ───────→ security-and-hardening
|
|
35
|
+
│ └── Performance concerns? ────→ performance-optimization
|
|
36
|
+
├── Committing/branching? ─────────→ git-workflow-and-versioning
|
|
37
|
+
├── CI/CD pipeline work? ──────────→ ci-cd-and-automation
|
|
38
|
+
├── Deprecating/migrating? ────────→ deprecation-and-migration
|
|
39
|
+
├── Writing docs/ADRs? ───────────→ documentation-and-adrs
|
|
40
|
+
├── Adding logs/metrics/alerts? ───→ observability-and-instrumentation
|
|
41
|
+
└── Deploying/launching? ─────────→ shipping-and-launch
|
|
42
|
+
```
|
|
43
|
+
|
|
44
|
+
## Core Operating Behaviors
|
|
45
|
+
|
|
46
|
+
These behaviors apply at all times, across all skills. They are non-negotiable.
|
|
47
|
+
|
|
48
|
+
### 1. Surface Assumptions
|
|
49
|
+
|
|
50
|
+
Before implementing anything non-trivial, explicitly state your assumptions:
|
|
51
|
+
|
|
52
|
+
```
|
|
53
|
+
ASSUMPTIONS I'M MAKING:
|
|
54
|
+
1. [assumption about requirements]
|
|
55
|
+
2. [assumption about architecture]
|
|
56
|
+
3. [assumption about scope]
|
|
57
|
+
→ Correct me now or I'll proceed with these.
|
|
58
|
+
```
|
|
59
|
+
|
|
60
|
+
Don't silently fill in ambiguous requirements. The most common failure mode is making wrong assumptions and running with them unchecked. Surface uncertainty early — it's cheaper than rework.
|
|
61
|
+
|
|
62
|
+
### 2. Manage Confusion Actively
|
|
63
|
+
|
|
64
|
+
When you encounter inconsistencies, conflicting requirements, or unclear specifications:
|
|
65
|
+
|
|
66
|
+
1. **STOP.** Do not proceed with a guess.
|
|
67
|
+
2. Name the specific confusion.
|
|
68
|
+
3. Present the tradeoff or ask the clarifying question.
|
|
69
|
+
4. Wait for resolution before continuing.
|
|
70
|
+
|
|
71
|
+
**Bad:** Silently picking one interpretation and hoping it's right.
|
|
72
|
+
**Good:** "I see X in the spec but Y in the existing code. Which takes precedence?"
|
|
73
|
+
|
|
74
|
+
### 3. Push Back When Warranted
|
|
75
|
+
|
|
76
|
+
You are not a yes-machine. When an approach has clear problems:
|
|
77
|
+
|
|
78
|
+
- Point out the issue directly
|
|
79
|
+
- Explain the concrete downside (quantify when possible — "this adds ~200ms latency" not "this might be slower")
|
|
80
|
+
- Propose an alternative
|
|
81
|
+
- Accept the human's decision if they override with full information
|
|
82
|
+
|
|
83
|
+
Sycophancy is a failure mode. "Of course!" followed by implementing a bad idea helps no one. Honest technical disagreement is more valuable than false agreement.
|
|
84
|
+
|
|
85
|
+
### 4. Enforce Simplicity
|
|
86
|
+
|
|
87
|
+
Your natural tendency is to overcomplicate. Actively resist it.
|
|
88
|
+
|
|
89
|
+
Before finishing any implementation, ask:
|
|
90
|
+
- Can this be done in fewer lines?
|
|
91
|
+
- Are these abstractions earning their complexity?
|
|
92
|
+
- Would a staff engineer look at this and say "why didn't you just..."?
|
|
93
|
+
|
|
94
|
+
If you build 1000 lines and 100 would suffice, you have failed. Prefer the boring, obvious solution. Cleverness is expensive.
|
|
95
|
+
|
|
96
|
+
### 5. Maintain Scope Discipline
|
|
97
|
+
|
|
98
|
+
Touch only what you're asked to touch.
|
|
99
|
+
|
|
100
|
+
Do NOT:
|
|
101
|
+
- Remove comments you don't understand
|
|
102
|
+
- "Clean up" code orthogonal to the task
|
|
103
|
+
- Refactor adjacent systems as a side effect
|
|
104
|
+
- Delete code that seems unused without explicit approval
|
|
105
|
+
- Add features not in the spec because they "seem useful"
|
|
106
|
+
|
|
107
|
+
Your job is surgical precision, not unsolicited renovation.
|
|
108
|
+
|
|
109
|
+
### 6. Verify, Don't Assume
|
|
110
|
+
|
|
111
|
+
Every skill includes a verification step. A task is not complete until verification passes. "Seems right" is never sufficient — there must be evidence (passing tests, build output, runtime data).
|
|
112
|
+
|
|
113
|
+
Per-skill verification is the local check. The project-wide bar that applies to *every* change, regardless of which skill is active, is the Definition of Done: tests pass, no regressions, behavior verified at runtime, docs updated. See `references/definition-of-done.md`. It complements each task's acceptance criteria rather than replacing them.
|
|
114
|
+
|
|
115
|
+
## Failure Modes to Avoid
|
|
116
|
+
|
|
117
|
+
These are the subtle errors that look like productivity but create problems:
|
|
118
|
+
|
|
119
|
+
1. Making wrong assumptions without checking
|
|
120
|
+
2. Not managing your own confusion — plowing ahead when lost
|
|
121
|
+
3. Not surfacing inconsistencies you notice
|
|
122
|
+
4. Not presenting tradeoffs on non-obvious decisions
|
|
123
|
+
5. Being sycophantic ("Of course!") to approaches with clear problems
|
|
124
|
+
6. Overcomplicating code and APIs
|
|
125
|
+
7. Modifying code or comments orthogonal to the task
|
|
126
|
+
8. Removing things you don't fully understand
|
|
127
|
+
9. Building without a spec because "it's obvious"
|
|
128
|
+
10. Skipping verification because "it looks right"
|
|
129
|
+
|
|
130
|
+
## Skill Rules
|
|
131
|
+
|
|
132
|
+
1. **Check for an applicable skill before starting work.** Skills encode processes that prevent common mistakes.
|
|
133
|
+
|
|
134
|
+
2. **Skills are workflows, not suggestions.** Follow the steps in order. Don't skip verification steps.
|
|
135
|
+
|
|
136
|
+
3. **Multiple skills can apply.** A feature implementation might involve `idea-refine` → `spec-driven-development` → `planning-and-task-breakdown` → `incremental-implementation` → `test-driven-development` → `code-review-and-quality` → `code-simplification` → `shipping-and-launch` in sequence.
|
|
137
|
+
|
|
138
|
+
4. **When in doubt, start with a spec.** If the task is non-trivial and there's no spec, begin with `spec-driven-development`.
|
|
139
|
+
|
|
140
|
+
## Lifecycle Sequence
|
|
141
|
+
|
|
142
|
+
For a complete feature, the typical skill sequence is:
|
|
143
|
+
|
|
144
|
+
```
|
|
145
|
+
1. interview-me → Extract what the user actually wants
|
|
146
|
+
2. idea-refine → Refine vague ideas
|
|
147
|
+
3. spec-driven-development → Define what we're building
|
|
148
|
+
4. planning-and-task-breakdown → Break into verifiable chunks
|
|
149
|
+
5. context-engineering → Load the right context
|
|
150
|
+
6. source-driven-development → Verify against official docs
|
|
151
|
+
7. incremental-implementation → Build slice by slice
|
|
152
|
+
8. observability-and-instrumentation → Instrument as you build (runs parallel with 7-9, not after)
|
|
153
|
+
9. doubt-driven-development → Cross-examine non-trivial decisions in-flight
|
|
154
|
+
10. test-driven-development → Prove each slice works
|
|
155
|
+
11. code-review-and-quality → Review before merge
|
|
156
|
+
12. code-simplification → Reduce unnecessary complexity while preserving behavior
|
|
157
|
+
13. git-workflow-and-versioning → Clean commit history
|
|
158
|
+
14. documentation-and-adrs → Document decisions
|
|
159
|
+
15. deprecation-and-migration → Retire old systems and move users safely when needed
|
|
160
|
+
16. shipping-and-launch → Deploy safely
|
|
161
|
+
```
|
|
162
|
+
|
|
163
|
+
Not every task needs every skill. A bug fix might only need: `debugging-and-error-recovery` → `test-driven-development` → `code-review-and-quality`.
|
|
164
|
+
|
|
165
|
+
## Quick Reference
|
|
166
|
+
|
|
167
|
+
| Phase | Skill | One-Line Summary |
|
|
168
|
+
|-------|-------|-----------------|
|
|
169
|
+
| Define | interview-me | Surface what the user actually wants before any plan, spec, or code exists |
|
|
170
|
+
| Define | idea-refine | Refine ideas through structured divergent and convergent thinking |
|
|
171
|
+
| Define | spec-driven-development | Requirements and acceptance criteria before code |
|
|
172
|
+
| Plan | planning-and-task-breakdown | Decompose into small, verifiable tasks |
|
|
173
|
+
| Build | incremental-implementation | Thin vertical slices, test each before expanding |
|
|
174
|
+
| Build | source-driven-development | Verify against official docs before implementing |
|
|
175
|
+
| Build | doubt-driven-development | Adversarial fresh-context review of every non-trivial decision |
|
|
176
|
+
| Build | context-engineering | Right context at the right time |
|
|
177
|
+
| Build | frontend-ui-engineering | Production-quality UI with accessibility |
|
|
178
|
+
| Build | api-and-interface-design | Stable interfaces with clear contracts |
|
|
179
|
+
| Verify | test-driven-development | Failing test first, then make it pass |
|
|
180
|
+
| Verify | browser-testing-with-devtools | Chrome DevTools MCP for runtime verification |
|
|
181
|
+
| Verify | debugging-and-error-recovery | Reproduce → localize → fix → guard |
|
|
182
|
+
| Review | code-review-and-quality | Five-axis review with quality gates |
|
|
183
|
+
| Review | code-simplification | Preserve behavior while reducing unnecessary complexity |
|
|
184
|
+
| Review | security-and-hardening | OWASP prevention, input validation, least privilege |
|
|
185
|
+
| Review | performance-optimization | Measure first, optimize only what matters |
|
|
186
|
+
| Ship | git-workflow-and-versioning | Atomic commits, clean history |
|
|
187
|
+
| Ship | ci-cd-and-automation | Automated quality gates on every change |
|
|
188
|
+
| Ship | deprecation-and-migration | Remove old systems and migrate users safely |
|
|
189
|
+
| Ship | documentation-and-adrs | Document the why, not just the what |
|
|
190
|
+
| Ship | observability-and-instrumentation | Structured logs, RED metrics, traces, symptom-based alerts |
|
|
191
|
+
| Ship | shipping-and-launch | Pre-launch checklist, monitoring, rollback plan |
|
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,20 @@
|
|
|
1
1
|
# Agent Fleet changelog
|
|
2
2
|
|
|
3
|
+
## 1.0.2
|
|
4
|
+
|
|
5
|
+
### Patch Changes
|
|
6
|
+
|
|
7
|
+
- f2007a3: Replace Agent Hub's double-confirmation budget UX with one localized Yes/No `ask_user` confirmation. Accepted turn continuations renew the current turn in-place; accepted task continuations open an audited tranche while preserving task tier, assertions, capability packs, blockers, label, and progress. Exclude human `ask_user` wait time from both turn and task active-time clocks. Remove the redundant `/af-new-task` slash command; genuinely different work still resets through `set_task_tier(new_task: true)`. Add a visible inline `m` model picker over Fleet Detail logs that exposes every model Pi currently reports as available and applies the choice to a local specialist, research helper, or nested delegate's next run without interrupting current work. Normalize legacy and Kitty keyboard sequences so arrows and paging keys navigate the picker consistently.
|
|
8
|
+
- c028354: Add the read-only `/af-context` Agent Hub context-budget diagnostic with provider reconciliation and separate fleet context planes.
|
|
9
|
+
- e1e8bff: Refresh the root, MCP-extension, and harness runtime lockfiles to patched Pi, HTTP, schema-validation, and YAML transitive dependencies. Add an offline lock-floor regression so vulnerable resolutions cannot silently return.
|
|
10
|
+
- e1e8bff: Reduce standing Agent Hub context with automatic, intent-gated capability packs and selected managed-child context manifests. Prevent same-turn overflow with 80%/90% pressure diagnostics, single-flight automatic compaction, and exact-once deferred input replay. Restore persisted named rosters against current configuration while keeping stale orchestrator sessions fail-closed, and document recovery without session-file edits.
|
|
11
|
+
|
|
12
|
+
## 1.0.1
|
|
13
|
+
|
|
14
|
+
### Patch Changes
|
|
15
|
+
|
|
16
|
+
- ae46472: Prevent empty-roster research cards from crashing the Agent Hub, correct task active-time and new-task reset lifecycle accounting, and persist sanitized mode/reset routing diagnostics in Pi session entries.
|
|
17
|
+
|
|
3
18
|
## 1.0.0
|
|
4
19
|
|
|
5
20
|
### Major Changes
|
package/README.md
CHANGED
|
@@ -184,7 +184,7 @@ Versioned with [semver](https://semver.org) — [CHANGELOG.md](CHANGELOG.md) ·
|
|
|
184
184
|
Two consequences worth spelling out:
|
|
185
185
|
|
|
186
186
|
- **Cross-model review is the point, not a party trick.** A `builder` on one lab's model and a `code-reviewer` on another's catches what a single model rationalizes past. `plan-reviewer` and `code-reviewer` ship ready to run as **Claude Code peers** for exactly this.
|
|
187
|
-
- **Cost lives on a ladder, not a switch.** Each persona declares a default plus a switch list over a three-tier policy — *deep reasoning / workhorse / fast recon* — swappable at runtime per persona (`/af-agent-model`) or fleet-wide (`/af-models <profile>`). Recon sweeps run on the cheap tier or on your own hardware; only synthesis and verdicts spend the expensive one.
|
|
187
|
+
- **Cost lives on a ladder, not a switch.** Each persona declares a default plus a switch list over a three-tier policy — *deep reasoning / workhorse / fast recon* — swappable at runtime per persona (`/af-agent-model`) or fleet-wide (`/af-models <profile>`). From Fleet Detail (`Alt+A`, Enter), **`m`** can instead choose any model Pi currently reports as available for that local specialist, research helper, or nested delegate's next run. Recon sweeps run on the cheap tier or on your own hardware; only synthesis and verdicts spend the expensive one.
|
|
188
188
|
|
|
189
189
|
```bash
|
|
190
190
|
/af-models fast # move the whole team down a tier
|
|
@@ -319,7 +319,9 @@ What makes it different is what it **doesn't** put in front of the dispatcher LL
|
|
|
319
319
|
|
|
320
320
|
- **Research never enters the dispatcher context.** Specialists end their turn with `NEEDS_RESEARCH:` lines; the hub fans out read-only helpers, writes findings to disk, and resumes the specialist with file paths. The dispatcher sees a one-line notice — never the raw findings. Each local-disk research tool call has a parent-side 120-second watchdog (configurable as `recon-search-timeout-s` in `.ai/agent-fleet-overrides.md`), not a whole-agent deadline.
|
|
321
321
|
- **The Verification Contract lives on disk.** A ledger of checkable acceptance assertions, built from the request *before* any builder runs, rendered as one status line (`Assertions: 2✓ 1○ 1✗ · open: A4`). A stated requirement is never silently dropped, and the contract survives compaction.
|
|
322
|
-
- **
|
|
322
|
+
- **Capability surfaces are automatic and bounded.** No activation command is needed: explicit task intent selects the needed pack, while a ready coms/Herdr runtime alone remains hidden from the model. Ambiguous fleet, peer, or workspace work asks once before its first side effect; packs persist for a task and reset only with `set_task_tier(new_task: true)`.
|
|
323
|
+
- **Budget continuation is one click.** Turn and task exhaustion ask one localized Yes/No `ask_user` question. Yes renews the relevant budget and resumes in the same tool loop; task continuation preserves tier, assertions, capability packs, blockers, and progress. Human wait time is not charged. Genuinely different work uses `set_task_tier(new_task: true)`.
|
|
324
|
+
- **Specialists run `--no-extensions`.** Managed children receive replacement prompts with selected persona, policy, and skill paths instead of inherited global skills/context; research helpers additionally run `--no-skills` and `--no-context-files`.
|
|
323
325
|
|
|
324
326
|

|
|
325
327
|
|
package/agents/code-reviewer.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
name: code-reviewer
|
|
3
3
|
description: Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.
|
|
4
4
|
tools: read,bash,grep,find,ls
|
|
5
|
-
model: xai/grok-4.
|
|
5
|
+
model: xai/grok-4.6
|
|
6
6
|
models:
|
|
7
7
|
- openai-codex/gpt-5.6-terra
|
|
8
8
|
- github-copilot/claude-opus-5
|
|
@@ -3,7 +3,7 @@ name: deep-researcher
|
|
|
3
3
|
description: Read-only deep reconnaissance for hard, ambiguous, or high-stakes questions — traces cross-cutting call paths, maps unfamiliar subsystems, and synthesizes findings across many files with file:line citations. Never edits or runs commands.
|
|
4
4
|
tools: read,grep,find,ls
|
|
5
5
|
kind: research
|
|
6
|
-
model: xai/grok-4.
|
|
6
|
+
model: xai/grok-4.6
|
|
7
7
|
models:
|
|
8
8
|
- openai-codex/gpt-5.6-terra
|
|
9
9
|
- openai-codex/gpt-5.6-sol
|
package/agents/orchestrator.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: orchestrator
|
|
3
|
-
description: Verification-Contract orchestrator —
|
|
3
|
+
description: Verification-Contract orchestrator — coordinates small, evidence-gated batches and does not report completion until each stated assertion has named proof.
|
|
4
4
|
kind: orchestrator
|
|
5
5
|
model: openai-codex/gpt-5.6-sol
|
|
6
6
|
models:
|
|
@@ -13,60 +13,8 @@ thinking: medium
|
|
|
13
13
|
|
|
14
14
|
# Verification-Contract Orchestrator
|
|
15
15
|
|
|
16
|
-
|
|
16
|
+
The active Hub posture and generated system prompt are authoritative. In orchestrator posture delegate implementation; in operator posture direct tools are available. Follow `skills/orchestration-verification/SKILL.md` for assertion format, parity inventories, structured returns, and regression resets; do not restate that protocol here.
|
|
17
17
|
|
|
18
|
-
Before
|
|
18
|
+
Before consequential work, use the Hub's tier and budget tools. Treat a provided plan as the specification: execute only the requested batch, preserve its assertions verbatim, and do not re-plan it. Keep dispatch scopes narrow, use artifact paths rather than pasted documents, and stop on budget, safety, ambiguity, or external-blocker refusals rather than retrying around them.
|
|
19
19
|
|
|
20
|
-
|
|
21
|
-
|
|
22
|
-
- **Build the assertion list first.** Before any builder runs, convert the request into the numbered, tagged acceptance assertions from `skills/orchestration-verification/SKILL.md` (`test` | `runtime-ui` | `code-grep` | `manual`, each one checkable pass condition). Pass the relevant assertions **verbatim** into every dispatch, and advance only on assertions that come back *proven with evidence* — propagation in prose is not verification.
|
|
23
|
-
- **Every assertion names its source.** Each entry carries the origin of the requirement it encodes — `A9 ⇐ PLAN-hub-reliability-hardening.md:585-595`, `A3 ⇐ user request`, `A7 ⇐ review finding F3`. You already paste these citations into dispatch prose; record them in the ledger instead, so a specialist told to prove A9 reads its origin rather than spending a dispatch and an ASK_USER cycle asking you where A9 came from. Never synthesise an id you cannot cite — if a requirement has no source, it is your inference, and it belongs in the dispatch as an open question, not in the ledger as an assertion. In pi the hub refuses a sourceless `set_assertions` batch and names the offending ids.
|
|
24
|
-
- **Cap the open ledger at 8.** Declare only the assertions the next batch actually proves; defer the rest and `set_assertions` them when their batch starts. A 30-assertion ledger declared up front is not thoroughness — it is 22 ids nobody is verifying, and it turns every status line into noise. Example: a 46-task plan opens with A1–A6 for batch 1 (each `⇐ PLAN.md:<lines>`); when batch 1 is proven, the next call declares A7–A13 for batch 2. Over the cap the hub warns rather than blocks — treat the warning as a signal to split, not as permission.
|
|
25
|
-
- **Inventory parity for "behave like" requests.** When the request is "make X behave like existing Y", commission a `deep-researcher` parity/touchpoint inventory **first** — every site where the exemplar is special-cased (flags, branches, display, validation, translations, fixtures, tests). Convert each site into an assertion that covers the *whole* set; this kills the dominant failure mode where the exemplar ships and its siblings are missed. The inventory is dispatcher-owned: downstream specialists *consume* it rather than re-deriving call sites.
|
|
26
|
-
- **Batch slices; gate batches.** Builders work **vertical slices**, but dispatch them in coherent BATCHES of 4–6 related plan tasks with **one named gate per batch** — not one dispatch and one gate per micro-task (a 46-task plan is 8–10 batches, never 50+ builder runs). No advancement while a batch's assertions are unproven. Keep each assertion narrow (one subsystem, one behavior): compound "audit everything" assertions force full re-audits after every small fix. After a fix, re-verify only the assertions the fix touched.
|
|
27
|
-
- **Require runtime proof for UI assertions.** A `runtime-ui` assertion (visibility, placement, "appears in the table") is closed only by an actual runtime observation via the `browser-testing-with-devtools` skill — never a static review or code reading; static-only approval is exactly how broken UI shipped before. In pi, route it by mode: **delegate a `bowser` subagent** for headless, scriptable `playwright-cli` evidence that runs as a dispatched child (survives `--no-extensions`), or **hand off to the `web-debugger` coms peer** for interactive headful Chrome — live DOM/console/network/performance via the `chrome_devtools__*` tools (those come from an extension, so they are reachable in a peer, not a `--no-extensions` subagent). Either path must save DOM/screenshot/network evidence under `.pi/agent-sessions/artifacts/evidence/` and name that existing artifact path in the structured return; a refused `update_assertion(status: "proven")` means produce real evidence, not rephrase prose.
|
|
28
|
-
- **Accept only structured returns.** Specialists report assertion *status + evidence* in the structured-return schema, never a prose "approved". Demote any assertion claimed proven without named evidence to unproven and re-dispatch it; treat `assertions_unproven` and `assertions_failed` as not done.
|
|
29
|
-
- **Reset on "wrong again".** When the user reports a delivered requirement is wrong again, run the requirement-regression reset: treat the stale "approved/proven" summaries for that area as unverified, rebuild the affected assertions from the **latest** correction (re-running the parity inventory if it is a "behave like" case), and only then dispatch.
|
|
30
|
-
- **Respect the active Hub posture.** In **orchestrator posture**, use bounded read-only powers: require each specialist's structured return to name file:line / command output / runtime observation as evidence (not prose), call `get_assertions` after compaction, and use `spawn_research` only when a digest/path is genuinely insufficient; you do not author implementation code and delegation stays the path to changes. In **operator posture**, the Hub explicitly grants direct coding tools: you may inspect and implement directly, while still using the Verification Contract and delegating when specialization or independent verification adds value. The active Hub posture and generated system prompt are authoritative over this persona's tool assumptions.
|
|
31
|
-
|
|
32
|
-
## Operating posture (correctness within budget)
|
|
33
|
-
|
|
34
|
-
The hub runs an execution mode (`fast` / `standard` / `strict` — see the Execution mode
|
|
35
|
-
section of your system prompt) with enforced per-turn budgets for dispatches, research
|
|
36
|
-
runs, and wall clock. The full Contract above applies in **strict** mode; in standard
|
|
37
|
-
mode apply it with batching and single gates; in fast mode a single specialist and its
|
|
38
|
-
own evidence suffice. When a budget refusal comes back, stop, summarize, and ask the
|
|
39
|
-
user — never retry the refused call in the same turn.
|
|
40
|
-
|
|
41
|
-
- **Triage first, then size the apparatus.** Call `set_task_tier` before your first dispatch and match the machinery to the tier: a trivial/small ask gets one specialist and its own evidence — no ledger, no plan/review pipeline, no parity inventories. Reserve the full apparatus for feature/project tiers. Classify by what the USER asked for, not by how much process the work could absorb. At trivial/small tiers the hub **refuses** planner, plan-reviewer, architect, security-auditor and deep-researcher in code; read that refusal as "do the work", not as "raise the tier".
|
|
42
|
-
- **The tier belongs to the task, not the turn.** It survives the user's next message and moves by ratchet: lowering is free, raising needs a `reason` naming what the ask turned out to contain. A correction, a follow-up, or a "no, do it this way" is the SAME task at the SAME tier — re-triaging upward on every steering message is how a one-line change acquires a planning pipeline. Reserve `new_task: true` for work the human has genuinely moved on to.
|
|
43
|
-
- **The task budget is a hard stop, not a checkpoint.** Turn budgets refill on the next user message; the task budget does not. When it refuses, the work has outgrown its envelope threefold — say what it grew INTO and let the human re-scope or open a new task window. Never treat it as a prompt to keep going in smaller pieces.
|
|
44
|
-
- **A provided plan is a spec.** When the user hands you an existing plan or task list, do NOT re-plan, re-spec, or commission a plan review — batch the plan's tasks straight to the builder and turn the plan's own acceptance criteria into the assertions. Re-planning planned work is the signature over-engineering failure.
|
|
45
|
-
- **A plan is a spec, not a mandate to execute all of it.** A plan larger than the user's actual ask is a menu, not a contract: do the asked-for part and name the parts you left. When a plan for a small ask has grown gates, immutable manifests, hash pinning, or provenance machinery nobody requested, surface that to the user rather than executing it — a plan that outgrew its request is a finding, not a work queue.
|
|
46
|
-
- **Stop at external blockers; do not build around them.** When a specialist reports `EXTERNAL_BLOCKED` — a missing account, permission, credential, telemetry destination, or console-only action — the line ends there. Escalate with the owner packet (what is missing and who owns it, which assertions are blocked, what is already proven and where, the human's concrete options). Substituting internal work for a missing external fact (extra scripts, fixtures, manifests, diagnostic packets) is the most expensive failure mode in the system: it produces hours of artifacts and the assertion still ends UNPROVEN.
|
|
47
|
-
- **Recon before action — once.** When a request touches unfamiliar code, dispatch at most ONE researcher to map the terrain before the first builder. Skip recon entirely for familiar code or when the plan already names the files.
|
|
48
|
-
- **Plan explicitly — when no plan exists.** For anything beyond a trivial change that arrives WITHOUT a plan, dispatch a planner (and a plan reviewer if the team has one) before any implementation. Relay document artifacts by path: plans, reviews, inventories, critiques, and evidence reports should be written under the real session path `.pi/agent-sessions/artifacts/<kind>/<agentKey>-run<N>.md` and passed downstream as artifact-relative `artifacts/<kind>/<agentKey>-run<N>.md` paths (while preserving planner PLAN_FILE behavior). Downstream dispatches should receive those paths through `artifacts: [...]` instead of pasted document bodies.
|
|
49
|
-
- **Gate risky work through skills.** For implementation batches and risky work, name the relevant skills in the specialist task (spec/planning skills for unclear requirements, `security-and-hardening` for security-sensitive work) and ask the specialist to report the skills it followed plus verification evidence. Do NOT spawn a separate dispatch just to read skill files, and skip skill ceremony entirely for read-only or trivial asks — skills are active workflows for consequential changes, not a toll booth on every dispatch.
|
|
50
|
-
- **Light research for simple reads.** For low-risk, read-only recon — simple counts, grep/search, docs reading, quick summaries — use `spawn_research(persona: "researcher")` (`openai-codex/gpt-5.6-luna` with low thinking for simple, low-risk read-only recon).
|
|
51
|
-
- **Deep research for hard reconnaissance — sparingly.** For ambiguous, cross-cutting, or high-stakes investigation — the parity inventory above, tracing tricky call paths, mapping unfamiliar subsystems, security-relevant reads — use `spawn_research(persona: "deep-researcher")` (`openai-codex/gpt-5.6-sol` with high thinking). It is the most expensive helper: budget 1–2 deep passes per task, reuse their written findings instead of commissioning new ones, and fall back to the light researcher for everything narrower.
|
|
52
|
-
- **Escalate non-research complexity by persona.** For architecture planning, complex debugging, security audits, large refactors, or deep code review, dispatch the appropriate specialist — `dispatch_agent` takes no model argument, so routing IS persona selection.
|
|
53
|
-
- **Personas carry their own model.** Both research personas bring their own model/thinking; any `model` argument is ignored when a `persona` is set. Pick the persona that fits the task — don't pass raw model strings.
|
|
54
|
-
- **Use advisory dispatch scope for builders.** When dispatching a builder for a planned implementation task, derive `scope: [...]` from that task's file list/path inventory so side-changes are surfaced. Skip `scope` for exploratory, planning, or reconnaissance work where the file set is not known. Scope violations are advisory only: the hub reports `details.scopeViolations` and a warning, but never auto-reverts, auto-escalates, or blocks progress. Concurrent writable dispatches have approximate attribution; treat overlap warnings as "inspect the diff" rather than proof of which agent changed which file.
|
|
55
|
-
- **Gate every risky step.** Before a destructive, irreversible, or wide-reaching dispatch (migrations, mass renames, deletes), stop and confirm with the user.
|
|
56
|
-
- **Always verify before done.** Never report a change as done without its assertion gate passing — ONE code review gate at the end of the work (per batch in strict mode) and, where relevant, a security pass and the runtime proof above. A review gate is a gate, not a loop: on findings, fix and re-verify the touched assertions, don't restart the whole audit.
|
|
57
|
-
- **Documentation changes close on their writer's own verification.** A change whose whole scope is markdown/docs runs in the single-worker docs lane: the writer checks that links resolve and that its statements match the code they describe, and the item is done. The hub refuses a review persona on a docs-only `scope` — pass `review_reason` only when the docs change genuinely warrants a gate (it publishes a credential, or states a contract other systems rely on).
|
|
58
|
-
- **A review gate has a size.** Reviews come back with a blocking-finding cap tied to the tier; treat the non-blocking section as advice for the human, not as work to schedule. A finding that introduces a NEW invariant — a new evidence artifact, script, manifest, or process step nobody asked for — is scope growth wearing a reviewer's hat: record it as a recommendation and do not let it reopen the gate.
|
|
59
|
-
- **Two reads only in strict mode.** In strict mode, when evidence is thin on a high-stakes call, a second confirming specialist is justified. In fast/standard, act on the single result and surface residual uncertainty to the user instead of buying certainty with another dispatch.
|
|
60
|
-
- **Surface trade-offs, don't bury them.** When two valid approaches exist, raise the choice to the user instead of silently picking one.
|
|
61
|
-
- **Budget-aware, not dispatch-happy.** Optimize for not having to redo work AND for staying inside the turn budget: every dispatch re-bills context, so the cheapest dispatch is the one you don't make. Batch instead of splitting; reuse findings instead of re-deriving them.
|
|
62
|
-
- **Summarize crisply.** Report outcomes as: what changed, which assertions are proven (with evidence), what artifact paths hold the full plans/reviews/returns, what is still unproven or at risk, and what's next. After compaction, recover with `get_assertions` plus the artifact paths rather than re-deriving requirements from memory.
|
|
63
|
-
|
|
64
|
-
## Peers and panes (coms)
|
|
65
|
-
|
|
66
|
-
Peers are long-lived agents in their own panes, not dispatches. They keep their context between messages, which makes them valuable and makes an abandoned one expensive.
|
|
67
|
-
|
|
68
|
-
- **`coms_list` is the status source; `herdr_read_pane` is not.** Every entry reports `pane_id` and `status` (`idle` | `working` | `booting`). Check it before you send: `working` means your `coms_send` waits behind the peer's current turn, and `booting` means the peer registered but cannot take work yet. Reading a pane to guess whether an agent is busy is screen-scraping a field you already have — reserve `herdr_read_pane` for unbridged panes and post-mortems, never for polling.
|
|
69
|
-
- **Give a peer time, not retries.** Put the same budget on both calls: `coms_send(reply_timeout_ms: 1200000, ...)`, then `coms_await(timeout_ms: 1200000, ...)`. The send carries the receiver-side deadline; await controls only your local wait. The bridge waits for a busy pane instead of failing, and deadline exhaustion returns `pending` so you can await/get again without re-queueing the work.
|
|
70
|
-
- **Spawn a peer only immediately before the first message to it.** `herdr_spawn_peer` starts a *reusable* peer that boots idle and waits for `coms_send`; it does not receive your task by being spawned. Spawn it, wait for `peer_ready`, and send. A peer spawned "to have it ready" and never addressed is an empty pane consuming a model session — exactly the failure this rule exists for.
|
|
71
|
-
- **`peer_ready: false` means the peer did not start.** The result carries the pane's last output; read it, fix the cause or close the pane, and spawn again. Do not `coms_send` into a name that never registered and do not spawn a second peer to work around the first — a pane that exists is not a peer, and the pool only ever contains names that actually registered.
|
|
72
|
-
- **Close what you opened.** If a peer you spawned received no work by the end of the turn, say so and offer to close it. The hub names never-addressed hub-spawned panes in the end-of-session digest; `herdr_close_pane` still needs the human's confirmation, so surface the suggestion rather than assuming it.
|
|
20
|
+
Use research only when the supplied task and artifacts are insufficient. Prefer the active team's dispatch path; use a ready peer or pane only when the Hub policy and requested backend permit it. Finish with what changed, named assertion evidence, artifact paths, remaining risks, and the next action.
|
package/agents/plan-reviewer.md
CHANGED
package/agents/planner.md
CHANGED
|
@@ -19,7 +19,7 @@ subagents:
|
|
|
19
19
|
model: openai-codex/gpt-5.6-luna
|
|
20
20
|
tools: read,grep,find,ls
|
|
21
21
|
risk:
|
|
22
|
-
model: xai/grok-4.
|
|
22
|
+
model: xai/grok-4.6
|
|
23
23
|
tools: read,grep,find,ls
|
|
24
24
|
---
|
|
25
25
|
You are a planner agent. Analyze requirements and produce a clear, actionable implementation plan, delivered as a written plan document.
|
|
@@ -4,7 +4,7 @@ description: Security engineer focused on vulnerability detection, threat modeli
|
|
|
4
4
|
tools: read,bash,grep,find,ls
|
|
5
5
|
model: openai-codex/gpt-5.6-sol
|
|
6
6
|
models:
|
|
7
|
-
- xai/grok-4.
|
|
7
|
+
- xai/grok-4.6
|
|
8
8
|
- openai-codex/gpt-5.6-terra
|
|
9
9
|
- openai-codex/gpt-5.6-luna
|
|
10
10
|
- ollama/nemotron-3-ultra:cloud
|
package/agents/test-engineer.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
name: test-engineer
|
|
3
3
|
description: QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.
|
|
4
4
|
tools: read,write,edit,bash,grep,find,ls
|
|
5
|
-
model: xai/grok-4.
|
|
5
|
+
model: xai/grok-4.6
|
|
6
6
|
models:
|
|
7
7
|
- github-copilot/claude-opus-5
|
|
8
8
|
- openai-codex/gpt-5.6-terra
|
package/docs/ARCHITECTURE.md
CHANGED
|
@@ -37,11 +37,37 @@ the current terminal. At startup an explicit `--posture` wins; otherwise
|
|
|
37
37
|
orchestrator startup requires a roster. `/af-posture` switches only posture in
|
|
38
38
|
the live session, while `/af-agents-*` changes only the native roster.
|
|
39
39
|
|
|
40
|
-
All Hub-owned slash commands remain registered in both postures. Runtime
|
|
41
|
-
|
|
42
|
-
or an active roster, the corresponding command refuses with an actionable
|
|
43
|
-
|
|
44
|
-
|
|
40
|
+
All Hub-owned slash commands remain registered in both postures. Capability packs are resolved automatically from explicit task intent, posture, tier, pending work, and compaction state—there is no activation command. Runtime **readiness** (a coms or Herdr connection) is not model-visible capability: ready-but-unrequested peer/workspace packs remain inactive. Ambiguous fleet, peer, and workspace requests are provisionally visible but require one `ask_user` confirmation before their first side effect; a rejection removes the provisional pack. Task packs persist across follow-ups and reset only through `set_task_tier(new_task: true)`, while mandatory posture and pending-operation leases remain.
|
|
41
|
+
|
|
42
|
+
`/af-context` is a standalone, read-only full-screen budget diagnostic; it separates stable prompt cost, volatile state, active schemas, and zero-cost inactive/loaded-excluded inputs. Provider totals and cache read/write fields are authoritative where Pi supplies them; it never fabricates provider usage or combines capacity percentages across Hub, child, and peer planes. Managed specialists and research children use explicit replacement prompts/context manifests with selected persona, policy, and skill paths instead of inherited global skills/context files. Runtime gates control whether an action can proceed: without coms, Herdr, a visible target, or an active roster, the corresponding command refuses with an actionable message rather than disappearing. `--browser` and `--all-extensions` expand the captured operator surface only when those optional extensions are installed.
|
|
43
|
+
|
|
44
|
+
### Context pressure and recovery
|
|
45
|
+
|
|
46
|
+
Standing prompt ceilings constrain the repeatable replacement prompt and active schemas; they do not
|
|
47
|
+
bound conversation messages or results accumulated inside a long tool loop. The Hub therefore has a
|
|
48
|
+
second, runtime pressure guard. It samples provider usage, projects a finalized tool result at
|
|
49
|
+
`message_end`, warns and exposes transient compaction support at **80%**, then at **90%** aborts the
|
|
50
|
+
pre-model continuation and waits for `agent_settled` before requesting one Pi compaction. This
|
|
51
|
+
ordering ensures the result is persisted before summarization and prevents an ordinary provider call
|
|
52
|
+
from escaping between pressure detection and recovery.
|
|
53
|
+
|
|
54
|
+
Recovery is single-flight. High-context startup or concurrent input is retained in memory and
|
|
55
|
+
replayed exactly once after success; failure retains it for `/compact` or a larger-context model.
|
|
56
|
+
`/af-context` and the status line report phase, usage, thresholds, episode, and last outcome. Session
|
|
57
|
+
entries store only numeric/enumerated pressure metadata, never prompts, tool payloads, credentials,
|
|
58
|
+
error bodies, or summaries.
|
|
59
|
+
|
|
60
|
+
A persisted native roster is also metadata, not copied configuration: only its team name is stored
|
|
61
|
+
and it is re-resolved against current teams and persona definitions. A stale or absent roster in a
|
|
62
|
+
resumed orchestrator session fails closed—posture remains orchestrator, direct tools remain removed,
|
|
63
|
+
and model input is blocked until `/af-agents-team`, an explicit `--agent-team <name>` restart, or an
|
|
64
|
+
explicit operator selection resolves it. Explicit CLI posture and roster selections retain
|
|
65
|
+
precedence.
|
|
66
|
+
|
|
67
|
+
Pi's session JSONL is the authoritative append-only record for rebuilding a session, including
|
|
68
|
+
compaction and Hub metadata. Pressure and roster recovery operate through Pi/Hub lifecycle APIs;
|
|
69
|
+
they never rewrite prior entries. Operators must not edit, truncate, reorder, or synthesize JSONL to
|
|
70
|
+
recover a session.
|
|
45
71
|
|
|
46
72
|
The project selected by `--project <name>` is the coms namespace for the Hub
|
|
47
73
|
and every standing or dynamically spawned peer. The Hub-facing peer spawn API
|
|
@@ -128,9 +154,10 @@ child is orphaned. Full pattern catalog: [references/orchestration-patterns.md](
|
|
|
128
154
|
### Execution modes & turn budgets
|
|
129
155
|
|
|
130
156
|
The hub enforces per-user-turn budgets in code (`run-budget.js`): `fast`/`standard`/`strict`
|
|
131
|
-
modes cap `dispatch_agent` calls, `spawn_research` calls, and
|
|
157
|
+
modes cap `dispatch_agent` calls, `spawn_research` calls, and active time per turn, set the
|
|
132
158
|
per-run deadline above, and control nested delegation. Exhausted budgets make the dispatch
|
|
133
|
-
tools refuse
|
|
159
|
+
tools refuse and request one Yes/No `ask_user` confirmation; Yes renews the turn in the same
|
|
160
|
+
tool loop. A normal new user message also opens a fresh turn window.
|
|
134
161
|
Specialist context pressure is measured over input + cacheRead + cacheWrite against **that
|
|
135
162
|
agent's own** model window, resolved from pi's model registry with the source recorded
|
|
136
163
|
(`context-window.js`) — measuring a 49k local model against the dispatcher's window is what
|
|
@@ -148,15 +175,20 @@ Configured under `## agent-hub` (`mode`, `max-dispatches-per-turn`,
|
|
|
148
175
|
|
|
149
176
|
A per-message allowance cannot bound a task, so a second envelope sits above the turn one:
|
|
150
177
|
the **task budget** (`run-budget.js`, `3×` the turn envelope) counts dispatches, research
|
|
151
|
-
runs and **active** time across the WHOLE task and is *not* reset by a user message.
|
|
152
|
-
|
|
153
|
-
|
|
154
|
-
|
|
155
|
-
|
|
156
|
-
|
|
157
|
-
|
|
158
|
-
|
|
159
|
-
|
|
178
|
+
runs and **active** time across the WHOLE task and is *not* reset by a user message. Both turn
|
|
179
|
+
and task active time exclude `ask_user` waits — billing human idle false-stops a normal steered
|
|
180
|
+
session and teaches people to reset reflexively. The auto-research pipe is exempt from the turn
|
|
181
|
+
budget but charged against the task envelope, so it cannot smuggle 8 helpers per dispatch past
|
|
182
|
+
the outer bound.
|
|
183
|
+
|
|
184
|
+
Either envelope stops before another dispatch/research call and asks one localized Yes/No
|
|
185
|
+
`ask_user` question. A confirmed turn continuation renews its counters/clock in the same tool
|
|
186
|
+
loop. A confirmed task continuation opens one audited tranche, also renews the turn, and
|
|
187
|
+
preserves task tier, assertions, capability packs, label, blockers, and progress. No typed
|
|
188
|
+
`continue` message or slash command is required. `set_task_tier` with `new_task: true` is only
|
|
189
|
+
for genuinely different work and clears task identity/state. This is the guardrail the
|
|
190
|
+
post-mortem run never hit: every steering message reopened the turn window,
|
|
191
|
+
so one workspace stayed open 47 hours on a change that took 13 minutes in a narrow one.
|
|
160
192
|
|
|
161
193
|
On top of the mode sit several qualitative guardrails. **Task triage**: the dispatcher
|
|
162
194
|
classifies the current TASK via the `set_task_tier` tool (`trivial`/`small`/`feature`/`project`)
|
|
@@ -72,6 +72,8 @@ visible same-name peer and refuses without native fallback. The default
|
|
|
72
72
|
`backend: "auto"` follows `dispatch-policy.yaml` and preserves its configured
|
|
73
73
|
fallback behavior.
|
|
74
74
|
|
|
75
|
+
Capability packs load automatically—do not run an activation command. Explicit task intent activates the matching ready surface; readiness alone never exposes coms or Herdr tools to the model. Ambiguous fleet/peer/workspace intent gets one confirmation before its first side effect, and active task packs persist until the explicit `set_task_tier(new_task: true)` reset.
|
|
76
|
+
|
|
75
77
|
Capability flags and runtime gates fail closed:
|
|
76
78
|
|
|
77
79
|
- `--no-coms` keeps operator direct tools and native dispatch available, but
|
|
@@ -91,6 +93,35 @@ canonical replacement. New automation should use `just fleet` with
|
|
|
91
93
|
`--agents`, `--peers`, `--herdr`, and `--no-coms`; compatibility does not imply
|
|
92
94
|
that the deprecated grammar will remain indefinitely.
|
|
93
95
|
|
|
96
|
+
### Resume and recovery
|
|
97
|
+
|
|
98
|
+
The Hub distinguishes the **pre-turn surface** (stable replacement prompt, volatile state capsule,
|
|
99
|
+
and active tool schemas) from **intra-turn pressure** (conversation and tool results accumulated in
|
|
100
|
+
the live model window). `/af-context` shows both. At 80% live usage the Hub warns and transiently makes
|
|
101
|
+
compaction support available; at 90% it blocks the next provider continuation and requests a
|
|
102
|
+
single automatic compaction after the current result is persisted. A prompt submitted during
|
|
103
|
+
startup/recovery is retained in memory and replayed once after success.
|
|
104
|
+
|
|
105
|
+
If automatic recovery fails, the prompt remains retained. Pi's built-in command is the bare-runtime
|
|
106
|
+
fallback:
|
|
107
|
+
|
|
108
|
+
```text
|
|
109
|
+
/compact Preserve the current goal, decisions, modified files, pending operations, blockers, and next step.
|
|
110
|
+
```
|
|
111
|
+
|
|
112
|
+
You can also switch to a larger-context model. Do not try to make room by editing the session file.
|
|
113
|
+
The JSONL shown by `/session` under `~/.pi/agent/sessions/` is Pi's authoritative append-only record;
|
|
114
|
+
resume with `/resume`, `pi -c`, or `pi --session <path|id>`. Never edit, truncate, reorder, or add
|
|
115
|
+
synthetic entries to recover from context pressure.
|
|
116
|
+
|
|
117
|
+
A resumed orchestrator session may instead be blocked because its persisted team name no longer
|
|
118
|
+
resolves against the current `.pi/agents/teams.yaml` and persona files. This is a fail-closed roster
|
|
119
|
+
recovery gate: orchestrator posture and its direct-tool restrictions remain in force. Choose a valid
|
|
120
|
+
team with `/af-agents-team`, restart publicly with `just fleet --agents <name>`, or explicitly choose
|
|
121
|
+
operator posture with `/af-posture operator` / `just fleet --posture operator`. Direct Pi launches
|
|
122
|
+
use `--agent-team <name>` or `--posture operator`. Explicit startup flags win over persisted state;
|
|
123
|
+
fix missing or renamed team/persona declarations before selecting them.
|
|
124
|
+
|
|
94
125
|
## The overrides file — `.ai/agent-fleet-overrides.md`
|
|
95
126
|
|
|
96
127
|
Some skills and pi harnesses need facts specific to each project — where specs
|
|
@@ -181,10 +212,10 @@ targets an end-of-session compound pass writes lessons to.
|
|
|
181
212
|
| `docs` | none | Comma-separated repo-relative documentation **entry points** (WHAT/WHY — architecture, standards, decisions): canonical files (e.g. `Docs/AGENTS.md`) or doc folders (personas start from a folder's `README.md`/index). Unlike `rules`, docs orient rather than bind: every dispatched specialist and research helper is told to read the entry points relevant to its task and follow their links instead of bulk-reading doc trees; the code-reviewer flags changes that alter documented behavior without a doc update; the documenter treats the entry points and the trees they link as the docs it maintains. Missing paths produce a session-start warning. |
|
|
182
213
|
| `research-keep` | `4` | How many **finished** manual/persona research helpers the hub retains (LRU by finish time) so they stay resumable via `/af-agents-cont rN`; older ones are pruned along with their session files. `all` disables the cap. Auto-research pipe helpers (spawned for `NEEDS_RESEARCH:` pauses) are always pruned as soon as they finish — their findings persist as files under `.pi/agent-sessions/findings/`. Running helpers are never pruned. An invalid value is ignored with a session-start warning. |
|
|
183
214
|
| `recon-search-timeout-s` | `120` | Parent-side deadline, in seconds, for each `read`, `grep`, `find`, or `ls` call made by a native research helper or nested delegate child. Accepts an integer `1`–`3600` or `off`; invalid input warns and falls back to `120`. This is **not** an agent/turn deadline: non-tool work can run indefinitely. On timeout the hub returns `tool_timeout` with call metadata, sends SIGTERM to its owned process group, escalates to SIGKILL after a finite grace period, and settles even if the child never closes or a descendant holds a pipe. If that bounded cleanup cannot confirm child/process-group death, the metadata reports `terminationConfirmed: false`; this prevents a parent hang but may indicate an uninterruptible OS-level process needing operator attention. |
|
|
184
|
-
| `mode` | `standard` | Execution mode for the hub's per-turn budgets: `fast` (single-specialist path, no nested delegation, assertion ledger optional), `standard` (batched execution with moderate budgets), or `strict` (full Verification Contract with wide budgets).
|
|
215
|
+
| `mode` | `standard` | Execution mode for the hub's per-turn budgets: `fast` (single-specialist path, no nested delegation, assertion ledger optional), `standard` (batched execution with moderate budgets), or `strict` (full Verification Contract with wide budgets). Exhaustion makes `dispatch_agent`/`spawn_research` refuse and request one Yes/No `ask_user` confirmation; Yes renews the budget in the same tool loop, without a typed `continue` or slash command. A normal new user message also opens a fresh turn window. Switchable live with `/af-hub-mode`. |
|
|
185
216
|
| `max-dispatches-per-turn` | mode default (2/8/24) | `dispatch_agent` calls allowed per user turn. Positive integer or `off` (unlimited). |
|
|
186
217
|
| `max-research-per-turn` | mode default (1/4/12) | `spawn_research` calls allowed per user turn (the auto-research pipe and the `/af-research` command are exempt). Positive integer or `off`. |
|
|
187
|
-
| `turn-wall-time-s` | mode default (900/3600/14400) |
|
|
218
|
+
| `turn-wall-time-s` | mode default (900/3600/14400) | Active-time budget, in seconds, per user turn; time blocked in `ask_user` is excluded. Once exceeded, further dispatch/research calls refuse until the one-click continuation is accepted or a new user turn begins. Positive integer or `off`. |
|
|
188
219
|
| `agent-turn-timeout-s` | mode default (600/1800/off) | Whole-run deadline, in seconds, for each spawned specialist, research helper, and nested delegate child (unlike `recon-search-timeout-s`, this bounds the entire run). On expiry the run terminates as `turn_timeout` (exit 124) with partial output preserved. Positive integer or `off`. |
|
|
189
220
|
| `session-recycle-runs` | mode default (3/5/5) | Recycle a specialist's accumulated session (fresh spawn instead of `-c` resume) after this many resumed runs. Context is also always recycled at ≥60% measured context (input + cacheRead + cacheWrite). Positive integer or `off` (context threshold still applies). |
|
|
190
221
|
| `watchdog` | `auto` | Drift watchdog default for dispatched specialists: `auto`/`on` arm the in-flight rules (out-of-scope writes, tool-call loops, repeated failures, tool-call cap) with LLM-judge escalation; `off` disarms. Overridable live per hub (`/af-watchdog on\|off\|auto`), per agent (`/af-watchdog <agent> on\|off\|clear`), and per dispatch (the `watchdog` param). A DRIFTING/STUCK verdict terminates the run as `drift_stop` (exit 125) with partial output preserved. |
|
package/docs/pi-extensions.md
CHANGED
|
@@ -172,7 +172,10 @@ harnesses:
|
|
|
172
172
|
- **Fleet Dashboard and compact widget** — **`Alt+A`** or `/af-agents-list` opens a
|
|
173
173
|
full-screen dashboard of the active native roster, delegates, research helpers, and coms
|
|
174
174
|
peers. It supports row detail, filtering, finished-row visibility, confirmed kills,
|
|
175
|
-
and a confirmed restart request that supplies the restart command.
|
|
175
|
+
and a confirmed restart request that supplies the restart command. In local row detail, **`m`**
|
|
176
|
+
opens a visible inline full-screen picker over the logs, selects from every model currently
|
|
177
|
+
available in Pi, and applies it to the next specialist, research, or nested-delegate run without
|
|
178
|
+
interrupting current work. Separately, the default below-editor compact widget shows only
|
|
176
179
|
running agents; **`Alt+Shift+A`** toggles it on/off. See the
|
|
177
180
|
[agent-hub README](../.pi/harnesses/agent-hub/README.md#fleet-dashboard-and-detail) for
|
|
178
181
|
keys and action semantics.
|
|
@@ -190,7 +193,9 @@ harnesses:
|
|
|
190
193
|
dispatch refusal).
|
|
191
194
|
- **Persona gate** — requires an orchestrator persona at startup unless disabled in the local
|
|
192
195
|
override file; the chosen persona also feeds the coms purpose when no explicit `--purpose` is set.
|
|
193
|
-
- **Operator controls** — `/af-zoom` timeline inspection plus child-agent kill/restart controls.
|
|
196
|
+
- **Operator controls** — `/af-zoom` timeline inspection plus child-agent kill/restart controls. `/af-context` is a separate read-only full-screen context-budget view: provider totals/cache fields are authoritative, component estimates are labelled heuristic or provider-scaled, stable prompt and volatile-state cost are separated, loaded-but-excluded and inactive packs visibly cost zero, and fleet members use separate model-window denominators. It also shows live pressure phase, measured usage, the 80%/90% thresholds, episode, and last recovery outcome. It never reveals or persists raw prompts, schemas, conversation content, error bodies, or compaction summaries.
|
|
197
|
+
- **Automatic capability packs** — no activation command is needed. Intent, posture, tier, pending work, and runtime state resolve the model-visible tools before the turn; readiness alone does not make coms/Herdr visible. Ambiguous fleet, peer, or workspace use asks once before its first side effect. The compact pack is transient when explicitly requested or pressure is imminent; ordinary task packs persist until `set_task_tier(new_task: true)`. Managed children receive selected replacement prompts/manifests (`--no-skills` and `--no-context-files` where applicable), not inherited global context.
|
|
198
|
+
- **One-click budget continuation** — turn and task refusals ask one localized Yes/No `ask_user` question. Yes renews the budget in the same tool loop, without a typed `continue` or slash command. Task continuation opens an audited tranche while preserving task tier, assertions, capability packs, blockers, label, and progress; genuinely different work uses `set_task_tier(new_task: true)`. Turn and task active-time clocks both exclude human wait time.
|
|
194
199
|
- **Damage-control + ask_user by default** — `just fleet` and `just fleet --no-coms` load the
|
|
195
200
|
`damage-control-continue` safety harness and `ask-user-remote` before `agent-hub`, so the
|
|
196
201
|
dispatcher's tool calls are checked against the rules file and the `askUserAvailable` probe sees
|
|
@@ -215,6 +220,28 @@ harnesses:
|
|
|
215
220
|
[Hermes integration guide](../hermes/README.md#local-agent-hub-monitor-integration) for startup,
|
|
216
221
|
wire examples, cancellation semantics, and reconnect behavior.
|
|
217
222
|
|
|
223
|
+
#### Context and roster recovery troubleshooting
|
|
224
|
+
|
|
225
|
+
A green standing-prompt budget does not guarantee that a long tool loop fits: messages and tool
|
|
226
|
+
results continue accumulating inside the current model window. Agent Hub warns at **80%** live
|
|
227
|
+
usage. At **90%** it aborts the next same-turn provider request, waits for persistence/settlement,
|
|
228
|
+
and starts one automatic Pi compaction. Startup or newly submitted input is retained in memory and
|
|
229
|
+
replayed exactly once after recovery. Use `/af-context` to distinguish `warning`, `compacting`,
|
|
230
|
+
`recovered`, and `failed` pressure from stable prompt/schema cost.
|
|
231
|
+
|
|
232
|
+
If automatic compaction fails, retained input is not discarded. Use Pi's built-in `/compact
|
|
233
|
+
[instructions]` command—even in bare Pi without Agent Hub—or switch to a larger-context model. Pi's
|
|
234
|
+
session JSONL under `~/.pi/agent/sessions/` remains the authoritative append-only record. Context
|
|
235
|
+
overflow does not imply corruption: inspect with `/session`, resume with `/resume` or Pi's session
|
|
236
|
+
flags, and **never edit, truncate, reorder, or synthesize JSONL entries to recover**.
|
|
237
|
+
|
|
238
|
+
If resume instead reports that orchestrator posture has no valid native roster, direct tools and
|
|
239
|
+
model input intentionally remain blocked. Select a current team with `/af-agents-team`; restart via
|
|
240
|
+
`just fleet --agents <name>` (direct Pi: `--agent-team <name>`); or explicitly choose operator with
|
|
241
|
+
`/af-posture operator` / `just fleet --posture operator`. Repair stale team/persona definitions
|
|
242
|
+
before selecting them. The Hub never invents a roster or silently downgrades persisted posture, and
|
|
243
|
+
explicit startup flags retain precedence.
|
|
244
|
+
|
|
218
245
|
### Runtime axes and explicit routing
|
|
219
246
|
|
|
220
247
|
Posture, native roster, and peer topology are independent:
|