Caveman Gateway Setup
JuliusBrussee/caveman
Routes every LLM call in a repository through the Caveman Cloud gateway in record mode, so requests and costs are measured without changing behavior.
Inspects LobeHub agent execution snapshots by operation ID: failed tool calls, arguments and results, available tools, LLM calls and the surrounding context.
Install LobeHub Agent Trace Inspector
$ npx skills add lobehub/lobehub --skill agent-tracing -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install lobehub/lobehub agent-tracing --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/lobehub/lobehub.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/agent-tracing .claude/skills/agent-tracing && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "agent-tracing" agent skill from https://github.com/lobehub/lobehub/tree/canary/.agents/skills/agent-tracing into .claude/skills/agent-tracing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-tracing", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/lobehub/lobehub/tree/canary/.agents/skills/agent-tracingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add lobehub/lobehub --skill agent-tracing -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install lobehub/lobehub agent-tracing --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lobehub/lobehub.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/agent-tracing .agents/skills/agent-tracing && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-tracing" agent skill from https://github.com/lobehub/lobehub/tree/canary/.agents/skills/agent-tracing into .agents/skills/agent-tracing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-tracing", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lobehub/lobehub --skill agent-tracing -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install lobehub/lobehub agent-tracing --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lobehub/lobehub.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/agent-tracing .cursor/skills/agent-tracing && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agent-tracing" agent skill from https://github.com/lobehub/lobehub/tree/canary/.agents/skills/agent-tracing into .cursor/skills/agent-tracing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-tracing", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/lobehub/lobehub.git --path .agents/skills/agent-tracing--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add lobehub/lobehub --skill agent-tracing -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install lobehub/lobehub agent-tracing --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lobehub/lobehub.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/agent-tracing .gemini/skills/agent-tracing && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agent-tracing" agent skill from https://github.com/lobehub/lobehub/tree/canary/.agents/skills/agent-tracing into .gemini/skills/agent-tracing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-tracing", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install lobehub/lobehub agent-tracingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add lobehub/lobehub --skill agent-tracing -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/lobehub/lobehub.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/agent-tracing .github/skills/agent-tracing && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agent-tracing" agent skill from https://github.com/lobehub/lobehub/tree/canary/.agents/skills/agent-tracing into .github/skills/agent-tracing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-tracing", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lobehub/lobehub --skill agent-tracing -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install lobehub/lobehub agent-tracing --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lobehub/lobehub.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/agent-tracing .opencode/skills/agent-tracing && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agent-tracing" agent skill from https://github.com/lobehub/lobehub/tree/canary/.agents/skills/agent-tracing into .opencode/skills/agent-tracing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-tracing", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
agent-tracing- GitHub stars
- 83k
- Token cost
- ~5.3k tokens
- SKILL.md length
- 1,777 words
- Files
- 1
- Skills in repo
- 50
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Inspects LobeHub agent execution snapshots by operation ID: failed tool calls, arguments and results, available tools, LLM calls and the surrounding context.
- Works in 3 steps: Context Engine Input — DB messages… → Context Engine Params — systemRole,… → Final LLM Payload — Processed messages…
- Debugging why a specific agent tool call failed in LobeHub
- SKILL.md covers How It Works, Package Location, Data Storage and Remote Traces (Production /…, plus 9 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
The skill documents @lobechat/agent-tracing, a zero-config local tool that records each agent execution step to disk under .agent-tracing/ while running in development mode, finalizing a partial snapshot into a complete ExecutionSnapshot JSON file once the operation finishes. A context-engine side channel carries heavy per-step payloads like agent documents and system role separately from the main events array, so they never enter the state pipeline, while a metadata field carries per-request decisions such as trim stats and cache-warmth gates.
Locally, completed snapshots, a latest symlink and in-progress partials each live under their own path inside .agent-tracing/, resolved from the current working directory, so the CLI must run from the repository root. In production or staging, completed snapshots upload to compressed object storage, and the preferred way to inspect them is the lh trace op command, which lists an operation's trace history or inspects one operation by ID using only a LobeHub login, without needing a tracing base URL or bucket domain. The excerpt is cut off partway through the remote trace commands.
When your agent uses it
- Debugging why a specific agent tool call failed in LobeHub
- Reviewing which tools and LLM calls ran during one operation
- Inspecting a production trace by operation ID without direct storage access
Example prompts
- “Inspect operation op_abc123 and show me which tool call failed.”
- “List the traced operations for topic tpc_xyz, newest first.”
- “Show the tool injection details for this operation's trace.”
Requirements
- A LobeHub checkout with NODE_ENV=development for local traces
- A LobeHub login for remote trace inspection
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Context Engine Input — DB messages passed to the engine, with [0], [1], ... indices. Use --msg-input N to view full content.
- Context Engine Params — systemRole, model, provider, knowledge, tools, userMemory, etc.
- Final LLM Payload — Processed messages after context engine (system date injection, user memory, history truncation, etc.), with [0], [1]…
What it can do on your machine
Read from SKILL.md and the folder at commit 6aaeeee. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash, sql and typescript).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
LobeHub Agent Trace Inspector loads about 5.3k tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 1,777 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:66
- or `.agent-tracing/.env` in the repo root with the same `TRACING_BASE_URL=...` line
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,777 words (~5,276 tokens).
“@lobechat/agent-tracing is a zero-config local dev tool that records agent execution snapshots to disk and provides a CLI to inspect them.”
- name
- agent-tracing
- user-invocable
- false
Files
Just SKILL.md in .agents/skills/agent-tracing of lobehub/lobehub.
Open the folder on GitHubat commit 6aaeeee
Compare with similar skills
LobeHub Agent Trace Inspector next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| LobeHub Agent Trace Inspector this skilllobehub/lobehub | 83k | — | ~5.3k | Automated safety check: Notes | Custom licence | |
| Caveman Gateway SetupJuliusBrussee/caveman | 110k | 1 repos | ~2.6k | Automated safety check: Warn | Apache-2.0 | |
| Arize PhoenixArize-ai/phoenix | 12k | 1 repos | ~3.8k | Automated safety check: Pass | MIT | |
| Failproof AI SDK IntegrationFailproofAI/failproofai | 5.3k | — | ~6k | Automated safety check: Pass | Custom licence | |
| Google Agents CLI Observabilitypifferologo/cloud-agents-cli | 129 | 1 repos | ~2.5k | Automated safety check: Pass | Apache-2.0 | |
| Agent Platform Alert Configurationgoogle/skills | 21k | — | ~4.2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Arize Phoenix
Arize-ai/phoenix
Open-source AI observability platform for tracing, evaluating, and improving LLM applications with OpenTelemetry integration
Failproof AI SDK Integration
FailproofAI/failproofai
Helps instrument a custom Python or TypeScript agent to record events for Failproof AI, verify what gets written, and run an evaluator worker that scores the runs.
Google Agents CLI Observability
pifferologo/cloud-agents-cli
This skill should be used when the user wants to "set up tracing", "monitor my ADK agent", "configure logging", "add observability", "debug production traffic", or needs guidance on monitoring…
- Official
Agent Platform Alert Configuration
google/skills
Writes Terraform alerting policies for AI agents that emit OpenTelemetry metrics, covering reliability, cost, safety, security and quality signals on Google Cloud.
- Official
Sentry Elixir SDK
getsentry/sentry-for-ai
Full Sentry SDK setup for Elixir. An agent skill from getsentry/sentry-for-ai.
More from lobehub/lobehub
All 50 skills in this repoLobeHub Interactive Prototype
lobehub/lobehub
Builds single-file interactive HTML prototypes rendered with the real LobeHub UI components and written as production-style React, so they can later be split into files.
Acceptance Evidence for Deliveries
lobehub/lobehub
Verifies a delivery end to end by driving the real product on a CLI, web, desktop or iOS Simulator surface, capturing evidence and publishing a round with the lh CLI.
Git Worktree Cleanup
lobehub/lobehub
Audits stale Git worktrees and branches with a bundled script, classifies each one, and deletes only after you approve the exact candidates.
LobeHub Alint Rule Set Maintenance
lobehub/lobehub
Maintains LobeHub's model-backed alint rule set: writing rules, removing false positives against real code, deciding warn versus error and tracking token cost.
LobeHub Builtin Tool Authoring
lobehub/lobehub
Guides building LobeHub builtin agent tools, from the manifest and execution runtime to executors, chat UI renders and registry wiring.
LobeHub Data Fetching Layers
lobehub/lobehub
Explains how LobeHub client code fetches data through services, SWR store hooks and cache keys, and when to avoid useEffect fetching or duplicated state.
Related
Categories
Questions about LobeHub Agent Trace Inspector
What does LobeHub Agent Trace Inspector do?
Inspects LobeHub agent execution snapshots by operation ID: failed tool calls, arguments and results, available tools, LLM calls and the surrounding context. agent-tracing/ while running in development mode, finalizing a partial snapshot into a complete ExecutionSnapshot JSON file once the operation finishes. A context-engine side channel carries heavy per-step payloads like agent documents and system role separately from the main events array, so they never enter the state pipeline, while a metadata field carries per-request decisions such as trim stats and cache-warmth gates.
When should I use LobeHub Agent Trace Inspector?
LobeHub Agent Trace Inspector fits situations like: debugging why a specific agent tool call failed in LobeHub; reviewing which tools and LLM calls ran during one operation; inspecting a production trace by operation ID without direct storage access.
How do I install LobeHub Agent Trace Inspector in Claude Code?
Run `npx skills add lobehub/lobehub --skill agent-tracing -a claude-code`. Or copy the skill folder (.agents/skills/agent-tracing in lobehub/lobehub) into .claude/skills/agent-tracing in your project. Claude Code loads it when a task matches its description.
How do I install LobeHub Agent Trace Inspector in Codex?
Run `npx skills add lobehub/lobehub --skill agent-tracing -a codex`. Or copy the skill folder (.agents/skills/agent-tracing in lobehub/lobehub) into .agents/skills/agent-tracing in your project. Codex loads it when a task matches its description.
Can I use LobeHub Agent Trace Inspector in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lobehub/lobehub --skill agent-tracing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-tracing, .gemini/skills/agent-tracing, .github/skills/agent-tracing and .opencode/skills/agent-tracing in your project.
What does LobeHub Agent Trace Inspector need to run?
SKILL.md names no scripts, command-line tools or credentials: LobeHub Agent Trace Inspector is instructions for the agent only. Our summary lists: A LobeHub checkout with NODE_ENV=development for local traces; A LobeHub login for remote trace inspection.
Does LobeHub Agent Trace Inspector access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is LobeHub Agent Trace Inspector safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does LobeHub Agent Trace Inspector use?
LobeHub Agent Trace Inspector has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does LobeHub Agent Trace Inspector use?
About 5.3k tokens (SKILL.md is roughly 21k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to LobeHub Agent Trace Inspector?
Skills that share tags, products or a category with LobeHub Agent Trace Inspector: Caveman Gateway Setup (JuliusBrussee/caveman, 110k stars), Arize Phoenix (Arize-ai/phoenix, 12k stars), Failproof AI SDK Integration (FailproofAI/failproofai, 5.3k stars) and Google Agents CLI Observability (pifferologo/cloud-agents-cli, 129 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains LobeHub Agent Trace Inspector?
lobehub (a GitHub organization) maintains it in lobehub/lobehub, which has 83,044 GitHub stars. The repository holds 50 skills in this directory. The repository was last updated on October 8, 2026.
Source: lobehub/lobehub on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.