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.
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.
Percentage of realistic task prompts that complete with a verified user-outcome oracle.
Count of reference tasks where TokRepo discovery avoids rebuilding an equivalent local asset from scratch.
Median token reduction from using discovered reusable assets on reference tasks.
Ratio of resolved/reused capabilities to newly harvested private drafts over a release window.
Percentage of installable assets covered by verify, install-plan, policy, evidence bundle, and rollback checks.
Percentage of harvested or handoff candidates whose quality_gate passes without unsafe files or unresolved sensitive findings.
Percentage of recurring or delayed agent tasks with owner, schedule, latest evidence, next action, and rollback or handoff state.
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.
Decide whether the repository README proves plugin-system support.
Before rebuilding a browser automation harness, resolve reusable TokRepo capability and inspect a safe install plan.
After improving a reusable task harness script, package the change as a private draft and produce a handoff plan without publishing.
Gates del ciclo de vida
- 01detect_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 - 02resolve_capability
Call tokrepo_resolve_capability or tokrepo agent-check before rebuilding local tools.
selected_candidate_or_controlled_empty_statenext_mcp_callsfallback_cli_commandslifecycle_contract - 03plan_safe_run
Verify trust and request an install plan before writes, execution, credentials, global config, or recurring work.
policy_decisionpermission_envelopeevidence_bundlerollback_plan - 04execute_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 - 05evaluate_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 - 06record_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 - 07harvest_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 - 08measure_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.
El trabajo largo, recurrente y diferido debe conservar owner, schedule, evidencia, próxima acción y rollback o handoff entre sesiones.
- taskrun_agent_discovery_smoke_dailyhealthyowner: 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
- taskrun_private_harvest_review_weeklyreadyowner: 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
- taskrun_delayed_chrome_mcp_recheckneeds_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
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.
- receipt_20260527_agent_discovery_smokefreshness_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.
- receipt_20260527_private_harvest_reviewfreshness_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.
- receipt_20260527_chrome_mcp_recheckfreshness_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.
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_agent31
- 02Descubrimiento de capacidades en el plan (discover / agent-check)mcp_discover78252% del anterior
- 03Verificar confianza, permisos, policyverify_asset107137% del anterior
- 04Generar plan de instalación tipadoinstall_plan3836% del anterior
- 05Aplicar instalación (después de dry-run + OK del usuario)install_apply197518% del anterior
- 06Traspaso de suministro post-tareahandoff_plan3920% del anterior
- 07Harvest — crear borradores privadosharvest_plan52133% del anterior
- 08Publicar el borrador harvest en el registroharvest_publish00% del anterior
- 09Publicar assets reutilizablespush9
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 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 → 2026-06-07
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.
| Evento | Recuento |
|---|---|
| install_apply | 197 |
| install_dry_run | 179 |
| verify_asset | 107 |
| rollback_plan | 105 |
| capability_resolve | 101 |
| mcp_search | 90 |
| agent_check | 78 |
| harvest_plan | 52 |
| install_plan | 38 |
| agent_handoff | 35 |
| audit_asset | 34 |
| init_agent | 31 |
| mcp_discover | 19 |
| find_for_task | 13 |
| push | 9 |
| handoff_plan | 4 |
| mcp_detail | 3 |
¿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