Telemetría de agente

Agentes reales usando TokRepo ahora mismo

Contadores agregados anónimos de los últimos 14 días. Cada evento es registrado por la API de funnel del agente; no se recopilan textos de tareas, contenido de archivos, tokens ni datos de assets privados.

Define TOKREPO_TELEMETRY=0 para no participar. Fuente: /api/v1/tokenboard/agent/funnel.

43.4%
Tokens ahorrados (mediana)
1,095
Eventos de agente totales
19
Llamadas Discover
197
Instalaciones aplicadas
39
Traspasos
Economía de tareas

Modelo operativo para trabajo de agente de alto valor

Esta es la superficie de producto detrás del contrato de máquina: qué mecanismos de economía de tareas usa TokRepo, qué gates del ciclo de vida se aplican y qué KPIs ya tienen evidencia pública de eval.

100%
Medido
high_value_task_completion_rate

Percentage of realistic task prompts that complete with a verified user-outcome oracle.

/evals/agent-task-receipts.json
20
Medido
duplicate_rebuilds_avoided

Count of reference tasks where TokRepo discovery avoids rebuilding an equivalent local asset from scratch.

/evals/agent-baseline.json
43.4%
Medido
median_tokens_saved_pct

Median token reduction from using discovered reusable assets on reference tasks.

/evals/agent-baseline.json
en seguimiento
Contratado
reuse_to_creation_ratio

Ratio of resolved/reused capabilities to newly harvested private drafts over a release window.

/agent-task-economy.json
100%
Medido
safe_install_gate_coverage_pct

Percentage of installable assets covered by verify, install-plan, policy, evidence bundle, and rollback checks.

/evals/agent-baseline.json
100%
Medido
handoff_quality_pass_rate

Percentage of harvested or handoff candidates whose quality_gate passes without unsafe files or unresolved sensitive findings.

/evals/agent-task-receipts.json
100%
Medido
long_running_task_state_coverage

Percentage of recurring or delayed agent tasks with owner, schedule, latest evidence, next action, and rollback or handoff state.

/evals/agent-task-ledger.json

Evidencia mini harness

Cada caso registra Task, Environment, Tools, Trace y Grader antes de que TokRepo marque el bucle de economía de tareas como aprobado.

3/3
casos aprobados
100%
tasa de aprobación
100%
cobertura de módulos
5
módulos harness
capability_gap_plugin_support

Decide whether the repository README proves plugin-system support.

TaskEnvironmentToolsTraceGrader
2 pasos de tracegrader pass
reuse_before_rebuild_browser_harness

Before rebuilding a browser automation harness, resolve reusable TokRepo capability and inspect a safe install plan.

TaskEnvironmentToolsTraceGrader
3 pasos de tracegrader pass
post_task_private_harvest

After improving a reusable task harness script, package the change as a private draft and produce a handoff plan without publishing.

TaskEnvironmentToolsTraceGrader
3 pasos de tracegrader pass

Gates del ciclo de vida

  1. 01
    detect_high_value_task

    Classify whether the user task is a repeatable high-value task, a one-off local fix, or a post-task reusable artifact opportunity.

    task_value_hypothesisreuse_potentialrisk_profilesuccess_oracle
  2. 02
    resolve_capability

    Call tokrepo_resolve_capability or tokrepo agent-check before rebuilding local tools.

    selected_candidate_or_controlled_empty_statenext_mcp_callsfallback_cli_commandslifecycle_contract
  3. 03
    plan_safe_run

    Verify trust and request an install plan before writes, execution, credentials, global config, or recurring work.

    policy_decisionpermission_envelopeevidence_bundlerollback_plan
  4. 04
    execute_or_stage

    Use dry-run, stage-only, confirmation-required, or direct execution according to policy and user intent.

    changed_files_or_no_writestate_deltapost_verify_commands
  5. 05
    evaluate_task_outcome

    Evaluate the user's real task outcome with a task-specific oracle instead of claiming success from a local command only.

    task_outcome_verdictevidenceopen_risks
  6. 06
    record_memory_and_state

    Record install state, task evidence, audit snapshots, and project memory so future agents inherit the context.

    TokRepo.lock_or_state_referenceaudit_referenceproject_memory_reference
  7. 07
    harvest_reusable_work

    Run tokrepo_harvest or tokrepo harvest --changed --json when the task creates reusable instructions, scripts, configs, or evals.

    private_package_draftsquality_gatesensitive_findingsdedupe_discovery
  8. 08
    measure_task_economics

    Update aggregate evidence for task completion, duplicated rebuilds avoided, token/time saved, safe install coverage, and handoff quality.

    task_completion_rateduplicate_rebuilds_avoidedmedian_tokens_saved_pctsafe_install_gate_coverage_pcthandoff_quality_pass_rate

Mecanismos prestados

  • mini_agent_harness

    TokRepo now publishes a deterministic mini task harness eval where each case records the task, fixture environment, tool calls with arguments/results, answer, and grader checks.

    https://tokrepo.com/evals/agent-task-harness.json
  • high_value_task_economics

    Every agent-facing surface should answer which high-value task it helps complete, what duplicate rebuild it avoids, and how the task result is verified.

    https://tokrepo.com/evals/agent-baseline.json
  • production_harness

    TokRepo's harness is the MCP/CLI/install-plan/evidence bundle lifecycle: resolve, discover, verify, plan, dry-run, install or stage, audit, rollback, and handoff.

    https://tokrepo.com/.well-known/tokrepo.json
  • skill_supply_chain

    Treat skills, prompts, scripts, MCP configs, workflows, project rules, and evals as typed supply with private-by-default harvest and human-confirmed publishing.

    https://tokrepo.com/agent-ecosystem.json#supply_handoff
  • long_running_clock

    Represent recurring and delayed work as task runs with schedule, status, state, evidence, next action, and rollback or handoff plan rather than as disconnected one-shot commands.

    https://tokrepo.com/evals/agent-task-ledger.json
  • outcome_oracle_receipts

    TokRepo now publishes deterministic task receipts so long-running work can be audited for freshness and outcome, not only remembered as a scheduled state row.

    https://tokrepo.com/evals/agent-task-receipts.json
  • memory_and_persona_context

    Project memory from tokrepo init-agent, .tokrepo/agent.json, installed-state files, and audit records must carry the user's operating rules into future agent sessions.

    https://tokrepo.com/schemas/agent-memory.schema.json
  • multi_agent_reliability

    Acceptance gates must include cross-agent project memory, local and hosted MCP parity, npx latest packages, install safety, handoff quality, and production live checks.

    https://tokrepo.com/evals/multi-agent-compatibility.json
  • task_to_supply_flywheel

    After a task is verified, agents should run tokrepo_harvest or tokrepo harvest --changed --json, inspect quality_gate, keep drafts private, and only push explicit reviewed files after human confirmation.

    https://tokrepo.com/evals/handoff-quality.json

Estado de tareas largas

Treat recurring jobs, delayed follow-ups, and automations as first-class high-value task runs with state and evidence.

Superficies actuales
TokRepo.lock.tokrepo/state.json.tokrepo/agent.jsontokrepo installed --project --jsonhttps://tokrepo.com/evals/agent-task-ledger.jsonhttps://tokrepo.com/evals/agent-task-receipts.json
Superficies previstas
schedule/heartbeat connector metadataIM or notification connector metadata
Ledger de ejecuciones

El trabajo largo, recurrente y diferido debe conservar owner, schedule, evidencia, próxima acción y rollback o handoff entre sesiones.

agent-task-ledger.json
3/3
runs con estado
100%
cobertura de estado
100%
evidencia adjunta
0
stale o bloqueado
  1. taskrun_agent_discovery_smoke_daily
    healthyowner: tokrepo-release-agentdailypass_with_warning
    schedule
    2026-05-28T00:20:00Z
    latest_evidence
    https://tokrepo.com/.well-known/tokrepo.json
    next_action
    Rerun after the external MCP Registry catches up to live manifest 2.16.1.
    rollback_or_handoff
    handoff · machine-readable endpoint regression or external registry lag persists past the next release window
  2. taskrun_private_harvest_review_weekly
    readyowner: tokrepo-harvest-agentweeklypass
    schedule
    2026-06-01T03:00:00Z
    latest_evidence
    https://tokrepo.com/evals/agent-task-harness.json
    next_action
    Run tokrepo_harvest on changed reusable scripts, keep drafts private, and require quality_gate.status=pass before handoff.
    rollback_or_handoff
    rollback · quality gate fails or sensitive_findings is nonzero
  3. taskrun_delayed_chrome_mcp_recheck
    needs_recheckowner: tokrepo-browser-ops-agentdelayedpass_proxy_connected
    schedule
    2026-05-27T03:30:00Z
    latest_evidence
    local:chrome-mcp-proxy-status
    next_action
    If MCP stdio transport is closed in the current agent session, reconnect the MCP server or start a fresh Codex session before browser-dependent validation.
    rollback_or_handoff
    handoff · mcp__chrome__ list_pages reports Transport closed after proxy health is green
Recibos de tareas

Cada tarea de larga duración debe publicar un recibo reciente con frescura, comando de verificación, digest de evidencia, oráculo de resultado, veredicto y efecto para el usuario.

agent-task-receipts.json
3/3
recibos frescos
100%
frescura
100%
cobertura del oráculo
100%
resultados aceptados
  1. receipt_20260527_agent_discovery_smoke
    freshness_status: freshpass_with_warning
    last_run_at
    2026-05-27T04:36:00Z
    next_due_at
    2026-05-28T04:36:00Z
    outcome_oracle
    machine_readable_surface_contract · All TokRepo agent discovery surfaces return HTTP 200, include the task-economy eval set, and hosted MCP JSON-RPC tools answer without schema regressions.
    evidence_digest
    sha256:443da96fc8c6287ea881348554b3211c8b44fa36dce2cb3dee08d789815a84ef
    user_effect
    Planning agents can discover the live TokRepo MCP, CLI, manifest, harness, ledger, and task-economy surfaces without GUI browsing; the only warning is external registry version lag outside the production site.
  2. receipt_20260527_private_harvest_review
    freshness_status: freshpass
    last_run_at
    2026-05-27T04:38:00Z
    next_due_at
    2026-06-03T04:38:00Z
    outcome_oracle
    quality_gate_receipt · The private harvest case includes tokrepo_harvest and tokrepo_handoff_plan traces, keeps draft supply private by default, and passes the Grader checks.
    evidence_digest
    sha256:d27a4f80a242278fdd1115bc985fe762895fd742500d6b8b9ebbb92daeb1f389
    user_effect
    Reusable work created during agent sessions can be reviewed as private package drafts with quality gates before any public push.
  3. receipt_20260527_chrome_mcp_recheck
    freshness_status: freshpass_with_handoff
    last_run_at
    2026-05-27T04:44:00Z
    next_due_at
    2026-05-27T05:14:00Z
    outcome_oracle
    browser_validation_fallback · Proxy status remains chromeConnected=true and the production browser validation matrix passes with System Chrome when the current MCP stdio transport is closed.
    evidence_digest
    sha256:e6d852212930cd1bf3d70c6dcc35400c70c50bba8513e14d71607510081f0cb1
    user_effect
    Browser-dependent TokRepo production validation remains executable even when the current Codex Chrome MCP stdio transport needs a session-level reconnect.

Los números marcados como medidos vienen de evidencia pública de eval. Los KPIs contratados permanecen visibles como obligaciones live hasta que el ledger de ejecución publique esas mediciones.

Discover → Verify → Install → Handoff → Harvest → Publish

El funnel del agente

El límite plan→implementación es donde TokRepo demuestra su valor. Cada paso a continuación colapsa las rutas CLI y MCP en una sola señal visible, sin importar qué agente ejecute el usuario.

  • 01Inicializar memoria del proyecto (init-agent)init_agent
    31
  • 02Descubrimiento de capacidades en el plan (discover / agent-check)mcp_discover
    78
    252% del anterior
  • 03Verificar confianza, permisos, policyverify_asset
    107
    137% del anterior
  • 04Generar plan de instalación tipadoinstall_plan
    38
    36% del anterior
  • 05Aplicar instalación (después de dry-run + OK del usuario)install_apply
    197
    518% del anterior
  • 06Traspaso de suministro post-tareahandoff_plan
    39
    20% del anterior
  • 07Harvest — crear borradores privadosharvest_plan
    52
    133% del anterior
  • 08Publicar el borrador harvest en el registroharvest_publish
    0
    0% del anterior
  • 09Publicar assets reutilizablespush
    9

Los contadores no son eventos únicos por agente; una tarea de agente normalmente dispara múltiples eventos. El funnel es una vista poblacional, no de sesión.

Volumen diario

Volumen de eventos por día

Total de eventos en todas las etapas del funnel, por día UTC. Los picos suelen correlacionarse con nuevas superficies de agente desplegándose.

2026-05-25 — 1012026-05-26 — 1592026-05-27 — 552026-05-28 — 842026-05-29 — 6082026-05-30 — 22026-05-31 — 92026-06-01 — 32026-06-02 — 62026-06-03 — 92026-06-04 — 242026-06-05 — 62026-06-06 — 142026-06-07 — 15

2026-05-25 → 2026-06-07

Totales por evento

Cada evento que registra el funnel del agente

Cada fila es un tipo de evento del funnel. El funnel del agente es intencionalmente estrecho — solo registra los eventos que filtran o evidencian una decisión.

EventoRecuento
install_apply197
install_dry_run179
verify_asset107
rollback_plan105
capability_resolve101
mcp_search90
agent_check78
harvest_plan52
install_plan38
agent_handoff35
audit_asset34
init_agent31
mcp_discover19
find_for_task13
push9
handoff_plan4
mcp_detail3
Ejecuta esto para tu agente

¿Quieres que los eventos de tu agente aparezcan en esta página?

Lánzalo en cualquier proyecto que use Claude Code, Codex, Cursor, Gemini CLI, Copilot, Cline, Windsurf, Roo, OpenHands o Aider. El comando init-agent escribe un archivo .tokrepo/agent.json legible por máquina más 11 superficies de instrucciones.

npx tokrepo init-agent --target all