Vrais agents utilisant TokRepo en ce moment
Compteurs agrégés anonymes des 14 derniers jours. Chaque événement est enregistré par l'API funnel agent ; aucun texte de tâche, contenu de fichier, token ou donnée d'asset privé n'est collecté.
Définissez TOKREPO_TELEMETRY=0 pour vous désinscrire. Source : /api/v1/tokenboard/agent/funnel.
Modèle opérationnel pour les tâches agent à forte valeur
C'est la surface produit derrière le contrat machine : les mécanismes d'économie des tâches repris par TokRepo, les gates de cycle de vie appliqués et les KPIs déjà étayés par des preuves d'eval publiques.
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.
Preuve mini harness
Chaque cas enregistre Task, Environment, Tools, Trace et Grader avant que TokRepo ne marque la boucle d'économie des tâches comme réussie.
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 du cycle de vie
- 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
Mécanismes repris
- 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
État des tâches longues
Treat recurring jobs, delayed follow-ups, and automations as first-class high-value task runs with state and evidence.
Le travail long, récurrent et différé doit conserver owner, schedule, preuves, prochaine action et rollback ou handoff entre sessions.
- 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
Chaque tâche longue doit publier un reçu récent avec fraîcheur, commande de vérification, empreinte de preuve, oracle de résultat, verdict et effet utilisateur.
- 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.
Les nombres indiqués comme mesurés viennent de preuves d'eval publiques. Les KPIs contractés restent visibles comme obligations live jusqu'à ce que le ledger d'exécution publie ces mesures.
Le funnel agent
La frontière planification→implémentation est l'endroit où TokRepo prouve sa valeur. Chaque étape ci-dessous regroupe les chemins CLI et MCP en un signal visible unique, quel que soit l'agent que l'utilisateur exécute.
- 01Initialiser la mémoire projet (init-agent)init_agent31
- 02Découverte de capacités au moment du plan (discover / agent-check)mcp_discover78252% du précédent
- 03Vérifier confiance, permissions, policyverify_asset107137% du précédent
- 04Générer un plan d'installation typéinstall_plan3836% du précédent
- 05Appliquer l'installation (après dry-run + accord utilisateur)install_apply200526% du précédent
- 06Transfert de support post-tâchehandoff_plan3920% du précédent
- 07Harvest — créer des brouillons privésharvest_plan52133% du précédent
- 08Publier le brouillon harvest dans le registreharvest_publish00% du précédent
- 09Publier les assets réutilisablespush9
Les compteurs ne sont pas des événements uniques par agent ; une tâche agent déclenche généralement plusieurs événements. Le funnel est une vue de population, pas une vue de session.
Volume d'événements par jour
Total des événements sur toutes les étapes du funnel, par jour UTC. Les pics sont généralement corrélés à l'arrivée de nouvelles surfaces agent.
2026-05-25 → 2026-06-07
Tous les événements enregistrés par le funnel agent
Chaque ligne est un type d'événement du funnel. Le funnel agent est intentionnellement étroit — il n'enregistre que les événements qui filtrent ou attestent une décision.
| Événement | Nombre |
|---|---|
| install_apply | 200 |
| 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 |
Vous voulez voir les événements de votre agent sur cette page ?
Activez-le dans tout projet utilisant Claude Code, Codex, Cursor, Gemini CLI, Copilot, Cline, Windsurf, Roo, OpenHands ou Aider. La commande init-agent écrit un fichier .tokrepo/agent.json lisible par machine plus 11 surfaces d'instructions.
npx tokrepo init-agent --target all