Real agents using TokRepo right now
Anonymous aggregate counters from the last 14 days. Every event is recorded by the agent funnel API; no task text, file contents, tokens, or private asset data are collected.
Set TOKREPO_TELEMETRY=0 to opt out. Source: /api/v1/tokenboard/agent/funnel.
Operating model for high-value agent work
This is the product surface behind the machine contract: which task-economy mechanisms TokRepo borrowed, which lifecycle gates are enforced, and which KPIs are already backed by public eval evidence.
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.
Mini harness evidence
Each case records Task, Environment, Tools, Trace, and Grader output before TokRepo treats the task-economy loop as passing.
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.
Lifecycle gates
- 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
Borrowed mechanisms
- 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
Long-running task state
Treat recurring jobs, delayed follow-ups, and automations as first-class high-value task runs with state and evidence.
Long-running, recurring, and delayed work must carry owner, schedule, evidence, next action, and rollback or handoff state across 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
Every long-running task run needs a recent receipt with freshness, verification command, evidence digest, outcome oracle, verdict, and user effect.
- 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.
Numbers shown as measured come from public eval evidence. Contracted KPIs are exposed as live obligations and stay visible until the runtime ledger starts publishing those measurements.
The agent funnel
The plan-to-implementation boundary is where TokRepo earns its keep. Each step below collapses CLI and MCP paths into a single visible signal so you can read the funnel regardless of which agent the user runs.
- 01Bootstrap project memory (init-agent)init_agent31
- 02Plan capability discovery (discover / agent-check)mcp_discover78252% of previous
- 03Verify trust, permissions, policyverify_asset107137% of previous
- 04Generate typed install planinstall_plan3836% of previous
- 05Apply install (after dry-run + user OK)install_apply199524% of previous
- 06Post-task supply handoffhandoff_plan3920% of previous
- 07Harvest — package private draftsharvest_plan52133% of previous
- 08Publish harvested draft to registryharvest_publish00% of previous
- 09Publish reusable assetspush9
Counts are not per-agent unique events; one agent task usually fires multiple events. The funnel is a population view, not a session view.
Event volume per day
Total events across all funnel stages, by UTC day. Bumps usually correlate with new agent surfaces shipping.
2026-05-25 → 2026-06-07
Every event the agent funnel records
Each row is one funnel event type. The agent funnel is intentionally narrow — recording only the events that gate or evidence a decision.
| Event | Count |
|---|---|
| install_apply | 199 |
| 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 |
Want your agent's events on this page?
Drop into any project that uses Claude Code, Codex, Cursor, Gemini CLI, Copilot, Cline, Windsurf, Roo, OpenHands, or Aider. The init-agent command writes a machine-readable .tokrepo/agent.json plus 11 instruction surfaces.
npx tokrepo init-agent --target all