Megingjord Harness
chf3198/megingjord-harness
Governança unificada para agentes IA: deploy, roteamento e compliance
Ver no GitHubPlataforma de governança para agentes de IA que orquestra Copilot, Claude Code e Codex através de um modelo de baton workflow, roteamento inteligente de LLMs (Ollama/Claude/OpenRouter) e gates de CI automatizados. Funciona como um control plane que deploy skills, hooks, instruções e políticas de forma sincronizada em múltiplos runtimes e projetos.
Instalação
npx convez-ai chf3198/megingjord-harness1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Governança centralizada de múltiplos agentes IA em equipes
- Deploy sincronizado de skills e políticas entre Copilot, Claude Code e Codex
- Implementação de gates de CI/CD e telemetria de uso de agentes
- Reutilização de conhecimento institucional via LLM wiki
- Controle de acesso e auditoria em fleets de agentes
Veredito

Solução madura e bem arquitetada para equipes que precisam governar múltiplos agentes IA em produção. Requer expertise em Node.js e entendimento de workflows de CI/CD, mas oferece controle granular e auditoria robusta — excelente para contextos empresariais com conformidade rigorosa.
README
A tradução para o português deste README ainda está na fila.
Megingjord Harness

Megingjord is a governance-first AI agent harness with skills, hooks, agents, runtime scripts, and a Karpathy-style LLM wiki. It operates as a control plane for AI coding agent runtimes — governing Copilot, Claude Code, and Codex the way Kubernetes governs containers: deploying configuration, enforcing policy, and maintaining desired workflow state across all three simultaneously.
Architecture at a glance
flowchart LR
A[Repo Source] --> B[skills/ instructions/ hooks/ scripts]
B --> C[~/.copilot runtime]
B --> D[~/.codex/devenv-ops runtime]
B --> E[~/.agents/skills runtime]
C --> F[Governed agent execution]
D --> F
E --> F
Why it is robust
- Multi-runtime deployment model with dry-run/apply scripts
- Governance baton model: Manager → Collaborator → Admin → Consultant
- Fleet-aware routing, telemetry, and policy enforcement
- Confidence-aware telemetry separates exact vs estimated Copilot usage with report caveats
- Static dashboard with operations + governance visibility
- LLM wiki integration for reusable institutional knowledge
- Accessibility + UX baseline checks aligned to WCAG 2.2 and Core Web Vitals
How it works — two-tier model
Installing Megingjord in a project seeds two independent layers:
Global layer — lives in your home directory, shared by all projects:
| Runtime | Path | What lives there |
|---|---|---|
| GitHub Copilot Chat | ~/.copilot/ | skills, instructions, hooks, scripts, wiki |
| Claude Code | ~/.claude/ | commands, agents, hooks, settings |
| Codex | ~/.codex/ | AGENTS.md, config, hooks, rules |
One npm run deploy:apply and every project on the machine inherits the full
governance toolkit — skills, routing, telemetry, wiki — for all three runtimes.
Workspace layer — checked into each project repo, workspace-specific:
| Extension | File(s) | Purpose |
|---|---|---|
| Copilot | .github/copilot-instructions.md | workspace override + adapter |
| Claude Code | CLAUDE.md, .claude/settings.json | workspace override + adapter |
| Codex | AGENTS.md, .codex/ | workspace override + adapter |
Workspace files extend or override the global layer. Global governance wins by default; local files add project-specific context and commands.
Multi-project reuse: npm run deploy:apply is idempotent. Multiple projects
share one global skill and governance layer while each keeps its own baton
history, workspace wiki, and local overrides.
Multi-runtime parity: A skill, hook, or governance rule written once deploys to all three runtimes — Copilot, Claude Code, and Codex are equal first-class citizens.
Zero-Cloudflare by default: Cross-agent coordination (mailbox, bundles,
telemetry, async dispatch) uses GitHub-native primitives out of the box — no
Cloudflare account or wrangler deploy required. Set MEGINGJORD_HAMR_ENABLED=1
to opt into the accelerated HAMR Cloudflare Worker for higher-throughput paths.
See docs/howto/github-native-layer2.md.
See docs/howto/installation.md for the full
install walkthrough, including adding a second project.
Ownership Semantics Rollout
Execution role labels represent the active baton holder only. Waiting and terminal states must not carry execution role labels.
See docs/howto/baton-workflow.md for board filters, no-code remediation lane constraints, and the operator rollout checklist.
Quick start
npm run setup
npm start
npm run lint
npm test
npm run deploy:both:apply
No Cloudflare account needed. Cross-agent coordination works immediately via
GitHub-native primitives. To enable the HAMR accelerated path after deploying
the Worker: add MEGINGJORD_HAMR_ENABLED=1 to your .env.
Env-backed credentials
- Copy
.env.exampleto.envfor local resource credentials. - Tavily MCP must keep the secret only in
TAVILY_API_KEY; do not inline Tavily keys in MCP URLs or tracked config. - Verify env-backed Tavily wiring with
npm run governance:credentials-env.
Research-first gate notes
- Research-first Epic detection is label-first:
phase-gate:research-firstontype:epictickets. AC-R*body matching remains a legacy fallback during migration and is slated for removal after #1888 enforcement follow-on completes.- Phase-1 MANAGER_HANDOFF checks use
phase-gate:phase-1by default and can be overridden withPHASE_ONE_LABELfor validation runs.
Scripts
| Script | Command |
|---|---|
adr:build | log4brains build |
adr:new | log4brains adr new |
adr:preview | log4brains preview |
agent:coord:remote | node scripts/global/agent-coord-remote.js |
agent:tier-c | node scripts/global/tier-c-guard.js |
anneal:detect | node scripts/global/workflow-anneal-detect.js |
anneal:goal-sensor | node scripts/global/anneal-goal-sensor.js |
anneal:graph | node scripts/global/anneal-graph.js |
anneal:review | node scripts/global/anneal-review.js |
anneal:rotate | node scripts/global/anneal-log-rotate.js |
anneal:schedule-health | node scripts/global/anneal-schedule-health.js |
auth:audit | node scripts/global/authorization-audit.js |
auth:profile | node scripts/global/authorization-profile.js |
auth:profile:context | node scripts/global/authorization-profile-context.js |
capability:probe | node scripts/global/capability-probe.js |
capability:show | node scripts/global/capability-show.js |
catch-empty | bash scripts/global/catch-empty-lint.sh .github/workflows |
cleanup:branches | node scripts/global/branch-cleanup-plan.js |
collaborator:preflight | node scripts/global/collaborator-preflight.js |
cost-report | node scripts/global/cost-report.js |
cost:baseline | node scripts/global/cost-baseline.js |
cost:token-report | node scripts/global/token-spend-report.js |
deploy | bash scripts/deploy.sh && node scripts/global/xteam-mcp-register.js --target copilot --root . |
deploy:all | bash scripts/deploy.sh --target all && node scripts/global/xteam-mcp-register.js --target all --root . |
deploy:all:apply | bash scripts/deploy.sh --apply --target all && node scripts/global/xteam-mcp-register.js --target all --root . --apply |
deploy:antigravity | bash scripts/deploy.sh --target antigravity && node scripts/global/xteam-mcp-register.js --target antigravity --root . |
deploy:antigravity:apply | bash scripts/deploy.sh --apply --target antigravity && node scripts/global/xteam-mcp-register.js --target antigravity --root . --apply |
deploy:apply | bash scripts/deploy.sh --apply && node scripts/global/xteam-mcp-register.js --target copilot --root . --apply |
deploy:both | bash scripts/deploy.sh --target both && node scripts/global/xteam-mcp-register.js --target copilot --root . && node scripts/global/xteam-mcp-register.js --target codex --root . |
deploy:both:apply | bash scripts/deploy.sh --apply --target both && node scripts/global/xteam-mcp-register.js --target copilot --root . --apply && node scripts/global/xteam-mcp-register.js --target codex --root . --apply |
deploy:claude | bash scripts/deploy.sh --target claude && node scripts/global/xteam-mcp-register.js --target claude --root . |
deploy:claude:apply | bash scripts/deploy.sh --apply --target claude && node scripts/global/xteam-mcp-register.js --target claude --root . --apply |
deploy:codex | bash scripts/deploy.sh --target codex && node scripts/global/xteam-mcp-register.js --target codex --root . |
deploy:codex:apply | bash scripts/deploy.sh --apply --target codex && node scripts/global/xteam-mcp-register.js --target codex --root . --apply |
deps:aggregate | node scripts/global/dep-graph-aggregate.js |
deps:augment | node scripts/global/dep-graph-augment.js |
deps:render | node scripts/global/dep-graph-render.js |
deps:review | node scripts/global/dep-proposals-review.js |
doc-graph | node scripts/global/doc-graph-builder.js |
docs:anchors | node scripts/global/docs-anchors.js |
docs:compile | node scripts/docs-compile.js |
docs:exec | node scripts/global/docs-exec.js |
docs:lint | node scripts/docs-lint.js |
epic:sync | node scripts/global/actuator-epic-sync.js |
format | prettier --write .prettierrc.json package.json CONTRIBUTING.md .github/workflows/lint.yml lint-configs/README.md lint-configs/ci-lint.yml lint-configs/eslint.config.devenv.js scripts/lint-readability.js scripts/global/install-readability-toolchain.js |
format:check | prettier --check .prettierrc.json package.json CONTRIBUTING.md .github/workflows/lint.yml lint-configs/README.md lint-configs/ci-lint.yml lint-configs/eslint.config.devenv.js scripts/lint-readability.js scripts/global/install-readability-toolchain.js |
git-state:drift | node scripts/global/git-state-drift-sensor.js |
git:conflict-predict | node scripts/global/git-conflict-predict.js |
git:conflict-predict:test | node --test tests/git-conflict-predict.spec.js |
git:freshness-check | node scripts/global/git-freshness-check.js |
git:freshness-check:test | node --test tests/git-freshness-check.spec.js |
goals:regen | node scripts/global/goals-contract-generate.js |
gov:extract | node scripts/global/rule-card-extractor.js --all > /tmp/rule-cards.json |
gov:parity | node scripts/global/megalint/parity-validator.js |
governance:actuator-transitions:test | node --test tests/actuator-transitions.spec.js |
governance:adapters:emit | node scripts/global/governance-adapter-emit.js |
governance:adapters:test | node scripts/global/governance-adapter-emit.spec.js |
governance:anneal-decision-audit | node scripts/global/anneal-decision-audit.js |
governance:anneal-decision-detector:test | node --test tests/anneal-decision-detector.spec.js |
governance:audit | node scripts/global/governance-audit.js |
governance:baton-latency:test | node --test tests/baton-latency-report.spec.js |
governance:collab-handoff-rebase:test | node --test tests/collab-handoff-rebase-freshness.spec.js |
governance:compatibility:matrix | node scripts/global/governance-compatibility-matrix.js |
governance:coordinator-cleanup | node scripts/global/coordinator-label-cleanup.js |
governance:credentials-env | node scripts/global/credentials-env-guard.js |
governance:cross-team-check | node scripts/global/cross-team-contract-check.js |
governance:cross-team-check:test | node --test tests/cross-team-contract-check.spec.js |
governance:cross-team-lease-dispatch:test | node --test tests/cross-team-lease-dispatch.spec.js |
governance:delegation-lint | node scripts/global/delegation-phrase-lint.js |
governance:dispatcher-set-labels:test | node --test tests/github-dispatcher-set-labels.spec.js |
governance:drift | node scripts/global/governance-drift-classifier.js --json |
governance:duplicate-check | node scripts/global/ticket-duplicate-guard.js --scan |
governance:duplicate-check:test | node --test tests/ticket-duplicate-guard.spec.js |
governance:epic | node scripts/global/epic-evidence.js |
governance:epic-auto-tick:test | node --test tests/epic-task-list-auto-tick.spec.js |
governance:epics | node scripts/global/epic-close-validator.js |
governance:escalation-coverage | node scripts/global/escalation-coverage-gate.js |
governance:escalation-coverage:test | node --test tests/escalation-coverage-gate.spec.js |
governance:generate | node scripts/global/governance-generate.js |
governance:ghs-feedback-loop:test | node --test tests/ghs-feedback-loop.spec.js |
governance:goal-tier-resolver:test | python3 -m unittest tests.hooks.test_goal_tier_resolver |
governance:hamr-bypass-workflow:test | node --test tests/hamr-bypass-lint-workflow.spec.js |
governance:hook-parity | node scripts/global/hook-parity-check.js |
governance:hook-parity:test | node --test tests/hook-parity-check.spec.js |
governance:hooks:test | python3 -m unittest discover -s tests/hooks -p 'test_*.py' |
governance:instructional-coverage | node scripts/global/instructional-coverage-audit.js |
governance:instructional-coverage:test | node --test tests/instructional-coverage-audit.spec.js |
governance:issue-transition-dispatch:test | node --test tests/issue-transition-dispatch.spec.js |
governance:lease-heartbeat | node scripts/global/worktree-lease-heartbeat.js |
governance:lease-heartbeat:test | node --test tests/worktree-lease-heartbeat.spec.js |
governance:list-tickets | node scripts/global/ticket-presenter.js |
governance:list-tickets:test | node --test tests/ticket-presenter.spec.js |
governance:load-local-env:test | npx playwright test tests/load-local-env.spec.js |
governance:manifest:test | node scripts/global/governance-manifest-validate.spec.js |
governance:manifest:validate | node scripts/global/governance-manifest-validate.js |
governance:model-diversity-replay | node scripts/global/model-diversity-replay-eval.js |
governance:model-diversity-replay:test | node --test tests/model-diversity-replay-eval.spec.js |
governance:no-sync-http | node scripts/global/no-sync-http-handlers.js |
governance:operator-ownership:eval | node scripts/global/operator-ownership-eval.js |
governance:operator-ownership:test | node --test tests/operator-ownership-rules.spec.js tests/delegation-phrase-lint.spec.js tests/operator-ownership-eval.spec.js tests/runtime-side-effect-guard.spec.js |
governance:orchestrator-parity | node scripts/global/orchestrator-governance-parity.js --json |
governance:orchestrator-parity:test | node --test tests/orchestrator-governance-parity.spec.js |
governance:parity:test | node scripts/global/governance-parity.spec.js |
governance:pre-commit-docs-check | node scripts/global/pre-commit-docs-check.js |
governance:pre-commit-docs-check:test | node --test tests/pre-commit-docs-check.spec.js |
governance:pre-pr-gate | node scripts/global/pre-pr-gate.js |
governance:pre-pr-gate:test | node --test tests/pre-pr-gate.spec.js |
governance:price-cap | node scripts/global/provider-price-cap-gate.js |
governance:price-cap:test | node --test tests/provider-price-cap-gate.spec.js |
governance:reconcile | node scripts/global/ticket-reconcile.js --json |
governance:review-promotion-eval | node scripts/global/model-diversity-replay-eval.js && node scripts/global/second-opinion-replay-eval.js |
governance:review-score | node scripts/global/review-score-classifier.js |
governance:review-score:test | node --test tests/review-score-classifier.spec.js |
governance:role-baton-audit | node scripts/global/role-baton-audit.js |
governance:role-baton-linter | node scripts/global/role-baton-linter.js |
governance:role-baton-linter:test | node --test tests/role-baton-linter.spec.js |
governance:rule-parity | node scripts/global/governance-rule-parity.js |
governance:rule-parity:test | node --test tests/governance-rule-parity.spec.js |
governance:runtime-guard:test | node --test tests/runtime-side-effect-guard.spec.js |
governance:second-opinion-replay | node scripts/global/second-opinion-replay-eval.js |
governance:second-opinion-replay:test | node --test tests/second-opinion-replay-eval.spec.js |
governance:second-opinion-runner | node scripts/global/second-opinion-runner.js |
governance:second-opinion-runner:test | node --test tests/second-opinion-runner.spec.js |
governance:second-opinion-tier3:test | node --test tests/second-opinion-tier3-trigger.spec.js |
governance:soak-language | node scripts/global/megalint/soak-language-guard.js |
governance:soak-language:test | node --test tests/soak-language-guard.spec.js |
governance:status-cardinality | node scripts/global/label-lint-status-cardinality.js |
governance:status-cardinality:test | node --test tests/label-lint-status-cardinality.spec.js |
governance:sync-check | node scripts/global/governance-sync-check.js |
governance:ticket-redundancy:test | node --test tests/validate-ticket-redundancy.spec.js |
governance:tokens | node scripts/global/governance-token-lint.js |
governance:validate-config-schemas-workflow:test | node --test tests/validate-config-schemas-workflow.spec.js |
governance:verify | node scripts/global/governance-verify.js --json |
governance:weekly | node scripts/global/governance-weekly-report.js |
governance:wiki-catalog:test | node --test tests/validate-wiki-catalog.spec.js |
governance:wiki-metrics:test | node --test tests/wiki-metrics.spec.js |
governance:worktree-intercept:test | node --test tests/worktree-write-intercept.spec.js |
governance:worktree-inventory | node scripts/global/worktree-inventory.js |
governance:worktree-lock:test | node --test tests/worktree-active-session-lock.spec.js |
governance:worktrees | node scripts/global/worktree-governance-audit.js --json |
hamr:activate | bash scripts/global/hamr-activate.sh |
hamr:batch-route:test | node --test tests/batch-route-async.spec.js |
hamr:batch-router | node scripts/global/anthropic-batch-router.js |
hamr:batch-validate | node scripts/global/batch-validator.js |
hamr:cache-emit | node scripts/global/cache-stats-emit.js |
hamr:cache-gate | node scripts/global/cache-hit-gate.js |
hamr:cache-gate:test | node --test tests/cache-hit-gate-eligibility.spec.js |
hamr:cache-push | node scripts/global/cache-stats-push.js |
hamr:compress | node scripts/global/constitution-compressor.js |
hamr:deploy | bash scripts/global/hamr-deploy.sh |
hamr:doctor | node scripts/global/hamr-doctor.js |
hamr:fleet-cascade-gate | node scripts/global/fleet-cascade-gate.js |
hamr:fleet-cascade-gate:test | node --test tests/fleet-cascade-gate.spec.js |
hamr:governance-bundle-push | node scripts/global/governance-bundle-push.js |
hamr:health | node scripts/global/substrate-health.js |
hamr:health-push | node scripts/global/substrate-health-push.js |
hamr:install-cron | bash scripts/global/install-cron.sh |
hamr:log-rotate | node scripts/global/log-rotate.js |
hamr:multi-judge:test | node --test tests/multi-judge-prompts.spec.js tests/multi-judge-variance.spec.js tests/multi-judge-orchestrator.spec.js |
hamr:policy-overrides | node scripts/global/cascade-policy-overrides.js |
hamr:premium-budget:test | node --test tests/premium-budget-governor.spec.js |
hamr:rule-gate | node scripts/global/rule-coverage-gate.js |
hamr:skill-views | node scripts/global/skill-views-derive.js |
hamr:spillover | node scripts/global/header-spillover.js |
hamr:sticky-route | node scripts/global/sticky-route.js |
hamr:sync-verify | node scripts/global/hamr-sync-verify.js |
hamr:teardown | bash scripts/global/hamr-teardown.sh |
harness:self-test | node scripts/global/harness-self-test.js |
harness:self-test:capability | node scripts/global/harness-self-test.js --capability |
harness:self-test:regression | node scripts/global/harness-self-test.js --regression |
harness:self-test:test | node --test tests/harness-self-test-runner.spec.js tests/harness-self-test-reporters.spec.js tests/harness-self-test-telemetry.spec.js tests/harness-self-test.spec.js |
health | node scripts/health-check.js |
help:topic | node scripts/help-topic.js |
hooks:install | bash scripts/global/install-hooks.sh |
hooks:pre-push | node scripts/global/pre-push-gates.js |
issue:transition | node scripts/global/issue-transition.js |
it-ops:usage-report | node scripts/global/it-bypass-usage-report.js |
label:provision | node scripts/global/label-provision.js |
lint | node scripts/lint.js |
lint:all | npm run lint:js && npm run lint:py && npm run lint:sh && npm run lint:md && npm run lint:decisions |
lint:coverage-metric | node scripts/global/lint-coverage-metric.js |
lint:decisions | node scripts/global/decisions-md-validator.js |
lint:js | eslint -c lint-configs/eslint.config.devenv.js --max-warnings 9999 dashboard/js scripts/global scripts/wiki |
lint:md | markdownlint-cli2 '**/*.md' '!node_modules/**' '!scripts/xteam-mcp/node_modules/**' '!.claude/**' '!research/**' '!wiki/wisdom/global/sources/**' '!wiki/wisdom/global/syntheses/**' '!raw/**' '!.dashboard/**' '!CHANGELOG-archive.md' '!tickets/**' '!planning/**' '!generated/**' '!tests/fixtures/governance/golden/**' '!tests/fixtures/changelog-fragments-invalid/**' |
lint:py | ruff check --config lint-configs/ruff.devenv.toml hooks/scripts/ |
lint:readability | node scripts/lint-readability.js |
lint:readability:ci | node scripts/lint-readability.js --max-warnings=475 |
lint:router | node scripts/lint-router.js |
lint:sh | find scripts -name '*.sh' -exec shellcheck --severity=warning {} + |
mailbox:flush | node scripts/global/mailbox-outbox.js flush |
mailbox:poll | node scripts/global/mailbox-client.js poll |
mailbox:send | node scripts/global/mailbox-client.js send |
mcp:project-state | node scripts/global/mcp-project-state.js |
mcp:register | node scripts/global/xteam-mcp-register.js --target all --root . --apply |
merge-evidence:snapshot | node scripts/global/merge-evidence-snapshot.js |
prepare | bash scripts/install-git-hooks.sh |
quality:parity | node scripts/global/quality-parity-report.js --json |
rag:search | node scripts/global/rag-search.js |
readability:snapshot | bash scripts/readability-snapshot.sh |
repo:scope | node scripts/global/repo-scope.js |
rotation:check | node scripts/global/hamr-rotation-check.js |
router:cascade | node scripts/global/cascade-dispatch.js |
router:dispatch | node scripts/global/task-router-dispatch.js |
router:free | node scripts/global/free-router.js |
router:smoke | node scripts/global/task-router-smoke.js |
router:weekly | node scripts/global/model-routing-weekly-report.js |
routing:baseline | node scripts/global/routing-baseline-report.js |
routing:calibrate | node scripts/global/cascade-calibrate.js |
routing:fallback-report | node scripts/global/routing-fallback-report.js |
routing:fleet-cost-report | node scripts/global/fleet-dev-cost-report.js |
routing:free-cloud-report | node scripts/global/free-cloud-usage-report.js |
routing:freshness | node scripts/global/matrix-freshness.js |
routing:reconcile | node scripts/global/token-telemetry-reconcile.js --json |
routing:refresh | node scripts/global/routing-refresh.js --update-matrix |
routing:report | node scripts/global/routing-baseline-report.js --days 7 |
routing:telemetry | node scripts/global/token-telemetry-report.js --json |
setup | npm install && echo '✅ megingjord ready — run: npm start' |
signing:bootstrap | node scripts/global/crypto-signing-bootstrap.js |
start | node scripts/dashboard-server.js |
state:offload | node scripts/global/state-offload-client.js |
stress | MEGINGJORD_STRESS_TIER=A node scripts/global/stress-orchestrator.js |
stress:anneal | node --test tests/stress-anneal-decision.spec.js |
stress:bounded | MEGINGJORD_STRESS_TIER=C node scripts/global/stress-orchestrator.js |
stress:evidence-check | node scripts/global/stress-evidence-check.js |
stress:evidence-check:test | node --test tests/stress-evidence-check.spec.js |
stress:full | MEGINGJORD_STRESS_TIER=D node scripts/global/stress-orchestrator.js |
stress:load-local-env | node --test tests/stress-load-local-env.spec.js |
stress:post-merge-sweep | node --test tests/stress-post-merge-sweep.spec.js |
stress:realism | MEGINGJORD_STRESS_TIER=B node scripts/global/stress-orchestrator.js |
stress:rebase | node --test tests/stress-rebase-discipline.spec.js |
stress:role-baton | node --test tests/stress-role-baton-linter.spec.js |
stress:surface-audit | node scripts/global/stress-surface-audit.js |
stress:surface-audit:test | node --test tests/stress-surface-audit.spec.js |
stress:test | node scripts/global/stress-runner.js |
stress:wiki-metrics:test | node --test tests/stress-wiki-metrics.spec.js |
stress:worktree | node --test tests/stress-worktree-isolation.spec.js |
sync | bash scripts/sync.sh |
sync:all | bash scripts/sync.sh --target all |
sync:all:dry | bash scripts/sync.sh --dry-run --target all |
sync:both | bash scripts/sync.sh --target both |
sync:both:dry | bash scripts/sync.sh --dry-run --target both |
sync:claude | bash scripts/sync.sh --target claude |
sync:claude:dry | bash scripts/sync.sh --dry-run --target claude |
sync:codex | bash scripts/sync.sh --target codex |
sync:codex:dry | bash scripts/sync.sh --dry-run --target codex |
sync:dry | bash scripts/sync.sh --dry-run |
synthesis:init | node scripts/global/synthesis-init.js |
synthesis:snapshot | node scripts/global/synthesis-snapshot.js |
synthesis:status | node scripts/global/broker-synthesis-status.js |
test | npx playwright test |
test:collaborator-input-shape | node --test tests/collaborator-handoff-input-shape.spec.js |
test:compatibility | node --test tests/orchestrator-compatibility.spec.js |
test:headed | npx playwright test --headed |
test:post-merge-sweep | node --test tests/post-merge-sweep.spec.js |
test:quality | npx playwright test tests/google-quality.spec.js |
test:sse-load | node scripts/tools/sse-load-test.js |
ticket:create | node scripts/global/ticket-create.js |
toolchain:readability:install | node scripts/global/install-readability-toolchain.js |
validate:compat | node scripts/validate-plugin-compat.js |
validate:triage | node scripts/validate-plugin-triage.js |
wiki:anneal | node scripts/wiki/anneal.js |
wiki:auto-update | node scripts/wiki/auto-update-pipeline.js |
wiki:drift | node scripts/wiki/drift-detector.js |
wiki:ingest | node scripts/wiki/ingest.js |
wiki:ingest:code | node scripts/wiki/ingest-code.js |
wiki:lint | node scripts/wiki/lint.js |
wiki:reindex | node scripts/wiki/reindex.js |
wiki:replay-eval | node scripts/wiki/replay-eval-harness.js |
wiki:search | node scripts/wiki/search.js |
worktree:bootstrap | bash scripts/worktree-bootstrap-node-modules.sh |
worktree:start | bash scripts/worktree-session-start.sh |
Token telemetry reconciliation configuration
- Run
npm run routing:reconcileto generatelogs/token-telemetry-reconcile.json. - Default thresholds:
drift_pct=0.15,drift_pct_fail=0.35,min_samples=3. - OpenRouter aggregate usage is auto-probed when
OPENROUTER_API_KEYis set. - Anthropic/LiteLLM aggregate usage can be enabled with
ANTHROPIC_USAGE_URLandLITELLM_USAGE_URL(plus keys). - OpenAI-compatible providers should be logged generically unless a narrower adapter is known.
- Codex VS Code sessions are first-class routing consumers, but do not assume they expose per-request token totals; reconcile route metadata with aggregate OpenAI usage or configured Codex OpenTelemetry exports.
Public trust surfaces
Runtime mapping
| Source | Runtime target |
|---|---|
| skills/ | ~/.copilot/skills + ~/.agents/skills |
| instructions/ | ~/.copilot/instructions |
| hooks/ | ~/.copilot/hooks + ~/.codex/devenv-ops/hooks |
| scripts/global/ | ~/.copilot/scripts + ~/.codex/devenv-ops/scripts |
| .codex/ | ~/.codex/AGENTS.md + config.toml + hooks.json + rules/ |
| wiki/ | ~/.copilot/wiki + ~/.codex/devenv-ops/wiki |
Issue flows
Formerly DevEnv Ops. Codex name rejected due product conflict; Aegis rejected due broad name reuse.
/xteam — cross-runtime synthesis slash command
Kick off cross-team R&D synthesis across all 4 AI runtimes with a single slash command. After installing the MCP server per runtime, type /xteam <epic-N> or /xteam-create <description> in any team's chat.
See docs/howto/cross-team-rd-synthesis.md for the full workflow.
Cross-team R&D synthesis
For Epics that benefit from multi-team independent perspectives, see How-to: Run a cross-team R&D synthesis. One-line kickoff: npm run synthesis:init -- --epic <N>. Canonical protocol at instructions/cross-team-rd-synthesis.instructions.md. Tier-1 by default; HAMR R2 mailbox is the Tier-2 optimization.