Skip to content
cccskills
FreePublished on GitHub

agent-observability

Add or maintain CodeBuddy hook observability for projects that need local metrics for tool latency, transcript token usage, session cost, and multi-agent trace attribution. Use when wiring hook-based telemetry, debugging missing usage events, and validating AgentLens state.

The English summary is being prepared. Showing the original description.

See how to install

Files included (34)

  • SKILL.md1.8 KB
  • config/pricing.json3.3 KB
  • logs/.gitkeep0 B
  • references/quickstart.md11.2 KB
  • references/schema-v2.md9.5 KB
  • scripts/__init__.py42 B
  • scripts/build_dashboard_data.py29.8 KB
  • scripts/core/__init__.py222 B
  • scripts/core/agent_identity.py22.1 KB
  • scripts/core/agentlens/__init__.py264 B
  • scripts/core/agentlens/bootstrap.py7.4 KB
  • scripts/core/agentlens/normalize.py12.6 KB
  • scripts/core/agentlens/runtime.py36.9 KB
  • scripts/core/agentlens/tracing.py19.8 KB
  • scripts/core/cls_sink.py14.9 KB
  • scripts/core/cls_uploader.mjs2.5 KB
  • scripts/core/collector.py37.4 KB
  • scripts/core/devflow.py11.1 KB
  • scripts/core/emitter.py19.5 KB
  • scripts/core/runtime.py21.5 KB
  • scripts/core/scanner.py18.1 KB
  • scripts/core/state.py42.4 KB
  • scripts/dashboard/index.html61.5 KB
  • scripts/main.py551 B
  • scripts/run_hook.sh522 B
  • templates/settings-hook.json1.5 KB
  • tests/fixtures/transcript.jsonl1.4 KB
  • tests/test_agent_identity.py3.4 KB
  • tests/test_build_dashboard_data.py33.0 KB
  • tests/test_cls_sink.py9.0 KB
  • tests/test_collector.py28.7 KB
  • tests/test_devflow.py19.6 KB
  • tests/test_pricing_overrides.py19.1 KB
  • tests/test_runtime_flow.py3.6 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Workflow

  1. Merge templates/settings-hook.json into the user or project settings.json.
  2. Keep hook entries command-only and keep timeouts around 5 to 10 seconds.
  3. Run a normal CodeBuddy session and inspect logs/metrics.ndjson.
  4. Inspect logs/.state.json when usage replay, offsets, or AgentLens turn state look wrong.
  5. Keep the runtime generic and verify output from metrics.ndjson and .state.json.

Read Next

  • Read references/quickstart.md for setup and smoke-test steps.
  • Read references/schema-v2.md when you need field definitions or sidecar state shape.

Key Files

  • scripts/main.py: hook entrypoint for session-start, user-prompt-submit, pre, post, and stop
  • scripts/run_hook.sh: stable shell wrapper for CodeBuddy hook commands
  • scripts/core/collector.py: transcript parsing, pre/post pairing, and session usage recording
  • scripts/core/agentlens.py: AgentLens trace emission and agent or step grouping
  • scripts/core/state.py: persisted hook state, offsets, and AgentLens sidecar state
  • scripts/core/devflow.py: optional devflow-awareness — detects a multi-agents-devflow-* team, reads workflow-state.json, and emits stage_transition events. No-ops entirely on non-devflow projects.
  • templates/settings-hook.json: hook wiring template

Output Contract

  • Always emit event, sid, and ts.
  • Emit tool for per-call latency and usage for transcript-derived token and cost events.
  • Emit stop for end-of-session flush.
  • Never block the main hook flow; hook exits must stay 0.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

The English summary is being prepared. Showing the original description.

Tencent/LoopForge56Updated Oct 16, 2026

在用户明确要求结构化、可恢复、多阶段的软件交付流程,或要求按 devflow 继续已有任务时使用。覆盖任务分级、需求、设计、计划、实现、设计稿还原、代码审查、测试、固定产物归档、知识沉淀和预览部署;适用于不同 Agent、语言、框架和仓库。普通的一次性小改、单独问答或无需流程编排的代码操作不应仅因属于软件开发而自动触发。

The English summary is being prepared. Showing the original description.

Tencent/LoopForge56Updated Oct 16, 2026

在技术设计前澄清软件交付需求,解决重要产品决策、隐含假设、范围边界、成功标准和未决分支。用于 DevFlow medium/large 的 REQUIREMENT 阶段,或功能请求过于模糊、无法安全设计时。只询问无法从项目证据中回答的问题;不实现、不提交、不写技术方案,也不调用计划类 skill。

The English summary is being prepared. Showing the original description.

Tencent/LoopForge56Updated Oct 16, 2026

在 Codex 中运行 devflow。用户提到 devflow、start/resume/status/abort devflow、多 agent 工作流,或要求“按 Codex devflow 跑”时使用。

The English summary is being prepared. Showing the original description.

Tencent/LoopForge56Updated Oct 16, 2026

通用知识沉淀能力 - 提供从项目交付过程中提炼可复用经验、教训和模式的标准化方法论,包括信息收集、精简提炼、结构化输出。不绑定任何特定工作流或存储方式。当用户说"帮我做知识沉淀"、"总结一下这次需求的经验"、"记录一下踩坑"、"沉淀一下这次的技术决策"、"做个复盘"时使用本技能。

The English summary is being prepared. Showing the original description.

Tencent/LoopForge56Updated Oct 16, 2026

通用知识沉淀能力。用于从 devflow 或其他交付过程的需求、设计、实现、审查、测试产物中提炼可复用经验、技术决策、踩坑记录和流程改进。

The English summary is being prepared. Showing the original description.

Tencent/LoopForge56Updated Oct 16, 2026

See all skills by Tencent

Report a problem with this skill