organ-lane-telemetry-cockpit
Human-readable cockpit that reads originator-telemetry.jsonl, groups by traceId, and prints a compact per-run timeline with elapsed time, heartbeat count, chars streamed, and status. Use when you need to see what a lane is doing without reading raw JSONL, or when invoking lane-telemetry-cockpit to inspect lane run summaries.
- License 许可
- MIT
- 最近更新
- 2026-10-27
- Stars
- ★ 2
- Forks
- 0
01 前言 Front Matter
- name
- organ-lane-telemetry-cockpit
- scope
- harness
- triggers
- [ "organ-lane-telemetry-cockpit", "how do I use lane-telemetry-cockpit", "lane-telemetry-cockpit usage", "lane-telemetry-cockpit guide", "Lane Telemetry Cockpit (human-readable view over YURI_LANE_TELEMETRY)" ]
- generated
- true
- invocation
- workflow
- description
- Human-readable cockpit that reads originator-telemetry.jsonl, groups by traceId, and prints a compact per-run timeline with elapsed time, heartbeat count, chars streamed, and status. Use when you need to see what a lane is doing without reading raw JSONL, or when invoking lane-telemetry-cockpit to inspect lane run summaries.
- source_file
- _SYSTEM/Scripts/lane-telemetry-cockpit.mjs
- source_node
- lane-telemetry-cockpit
03 SKILL.md 正文
<!-- GENERATED from the canonical graph node "lane-telemetry-cockpit" (mechanism.guide) by _SYSTEM/Scripts/yuri-guide-project.mjs. DO NOT hand-edit — edit _SYSTEM/organ-guides.json, then run: node _SYSTEM/Scripts/yuri-guide-seed.mjs && node _SYSTEM/Scripts/yuri-guide-project.mjs -->
Organ Guide — Lane Telemetry Cockpit (human-readable view over YURI_LANE_TELEMETRY)
Module: _SYSTEM/Scripts/lane-telemetry-cockpit.mjs · Layer: Skills & Orchestration · Invocation: both · CLI: (path) [--json] [--limit N]
Purpose. Human-readable cockpit over the Originator lane-telemetry stream. JSONL is the audit substrate, not the operator experience: this reads originator-telemetry.jsonl, groups by traceId, COLLAPSES the noisy stream/stderr/stdout chunk events into counts, and prints a compact per-run timeline (start → model call → verification → exit) with elapsed, heartbeat count, chars streamed, and status — so the operator sees what a lane is doing without reading raw JSON.
Exports
readTelemetry(file = TELEMETRY, opts = {})- in: optional telemetry file path + opts
- out: parsed telemetry events (malformed lines tolerated)
summarizeByTrace(events)- in: telemetry events
- out: per-traceId summary collapsing chunk events into counts (elapsed, heartbeats, chars, status)
renderCockpit(traces, opts)- in: summarized traces + render opts
- out: the compact human-readable cockpit string
Security boundary
Strictly READ-ONLY — reads the telemetry JSONL and renders it; never mutates telemetry. Input line-count is bounded (limit guard). No protected-path access.
When to use
Inspecting what a dispatched lane run actually did (timeline, model call, verification, exit) without parsing raw originator-telemetry JSON; triaging a slow/failed lane run.
Gotchas
- It collapses stream/stderr/stdout chunk events into COUNTS — individual chunk payloads are not shown (by design, to stay compact).
- Grouping is by traceId; a run without a stable traceId will not group cleanly.
- Read-only over a live-appended file — a snapshot reflects the moment it was read.
Session Notes
2026-06-13
- session: 40m | peak ctx: 0% | compacts: 0
- tools: Bash×824, Read×163, Edit×17, StructuredOutput×16, Write×8, TodoWrite×4, ToolSearch×2, ScheduleWakeup×2, Workflow×1, mcp×1, AskUserQuestion×1
- corrections: none
- errors: none
04 同仓库更多 Skills
zoom-out
Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.
yuri-shura
6-perspective adversarial review for high-stakes turns (architecture decisions, refactor planning, deployment review) — fans out architect, adversary (7-vector attack), maintainer, ops, product, and security perspectives in parallel, then consolidates. Use when user says 'review this decision', '/shura', 'adversarial review', 'what could go wrong', 'architecture review', or 'deployment review'.
yuri-sales-intelligence
Unified sales and outreach skill generating cold outreach openers, social selling sequences, objection rebuttals, and ad creative for any paid platform — multi-persona aware, adapting tone and offer frame to buyer type. Use when user says 'write a cold email', 'outreach sequence', 'objection handling', 'ad copy', or 'sales pitch'.
yuri-code-intelligence
Unified code quality intelligence layer that diagnoses code smells (Long Method, Feature Envy, design pattern issues), prescribes targeted Fowler refactoring techniques, and reviews code for security, performance, and clarity. Use when user says 'review this code', 'refactor this', 'what's wrong with this method', 'code smells', or 'clean this up'.
yuri-adw
Invoke when user asks to run the ADW loop / agentic engineering loop / software factory workflow.
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment