Improve Prompt
AgentX-ai/AgentX-Trace-Eval
Propose an improved version of a prompt registered in a self-hosted AgentX (AgentX-trace-eval) instance, using real low-rated evaluation results as evidence, then publish it as a new version once…
Inspect and debug live streaming agent sessions to understand what the agent did.
Install Inspect
$ npx skills add agentevals-dev/agentevals --skill inspect -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install agentevals-dev/agentevals inspect --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/agentevals-dev/agentevals.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/inspect .claude/skills/inspect && 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 "inspect" agent skill from https://github.com/agentevals-dev/agentevals/tree/main/.claude/skills/inspect into .claude/skills/inspect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "inspect", 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/agentevals-dev/agentevals/tree/main/.claude/skills/inspectType 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 agentevals-dev/agentevals --skill inspect -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install agentevals-dev/agentevals inspect --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentevals-dev/agentevals.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/inspect .agents/skills/inspect && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "inspect" agent skill from https://github.com/agentevals-dev/agentevals/tree/main/.claude/skills/inspect into .agents/skills/inspect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "inspect", 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 agentevals-dev/agentevals --skill inspect -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install agentevals-dev/agentevals inspect --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentevals-dev/agentevals.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/inspect .cursor/skills/inspect && 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 "inspect" agent skill from https://github.com/agentevals-dev/agentevals/tree/main/.claude/skills/inspect into .cursor/skills/inspect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "inspect", 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/agentevals-dev/agentevals.git --path .claude/skills/inspect--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 agentevals-dev/agentevals --skill inspect -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install agentevals-dev/agentevals inspect --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentevals-dev/agentevals.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/inspect .gemini/skills/inspect && 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 "inspect" agent skill from https://github.com/agentevals-dev/agentevals/tree/main/.claude/skills/inspect into .gemini/skills/inspect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "inspect", 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 agentevals-dev/agentevals inspectInstalls 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 agentevals-dev/agentevals --skill inspect -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/agentevals-dev/agentevals.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/inspect .github/skills/inspect && 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 "inspect" agent skill from https://github.com/agentevals-dev/agentevals/tree/main/.claude/skills/inspect into .github/skills/inspect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "inspect", 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 agentevals-dev/agentevals --skill inspect -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install agentevals-dev/agentevals inspect --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentevals-dev/agentevals.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/inspect .opencode/skills/inspect && 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 "inspect" agent skill from https://github.com/agentevals-dev/agentevals/tree/main/.claude/skills/inspect into .opencode/skills/inspect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "inspect", 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
inspect- GitHub stars
- 162
- Token cost
- ~534 tokens
- SKILL.md length
- 192 words
- Files
- 2
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Inspect and debug live streaming agent sessions to understand what the agent did.
- Works in 5 steps: List sessions with list_sessions. Show… → Summarize with summarize_session. This… → Present as a readable narrative. For… → …
- The user wants to see what happened in a recent agent run
- Calls uv
- Trace through the tool calls step by step
What it does
Inspect is an agent skill from agentevals-dev/agentevals. Inspect and debug live streaming agent sessions to understand what the agent did. Use this skill when the user wants to see what happened in a recent agent run, trace through the tool calls step by step, debug unexpected agent behavior, or get a readable narrative of a session. Trigger on phrases like "show me what my agent did", "inspect session", "what happened in that run", "debug my agent", "trace through session", "walk me through the last run", "what tools did it call". Requires agentevals serve --dev to be…
Its SKILL.md is about 530 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `evals/evals.json`).
It sits in DevOps & Cloud, covering LLM evaluation and Observability. It works with OpenTelemetry. The repository describes itself as: agentevals is a framework-agnostic evaluations solution based on OpenTelemetry traces. The licence is Apache-2.0.
When your agent uses it
- The user wants to see what happened in a recent agent run
- Trace through the tool calls step by step
- Debug unexpected agent behavior
- Get a readable narrative of a session
Example prompts
- “show me what my agent did”
- “inspect session”
- “what happened in that run”
- “/inspect”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- List sessions with list_sessions. Show session ID, completion status,
- Summarize with summarize_session. This converts raw OTLP spans into
- Present as a readable narrative. For each turn
- Flag anything worth investigating
- Offer next steps. If the user wants to score the session against a golden
What it can do on your machine
Read from SKILL.md and the folder at commit 94785bb. 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
Shell commands in SKILL.md call:
uv
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.
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
Inspect loads about 534 tokens when it runs. Until then it costs about 148 tokens; SKILL.md has 192 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 passed
The automated check found no risky patterns in SKILL.md.
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
The full file from agentevals-dev/agentevals at commit 94785bb, republished under its Apache-2.0 licence (© agentevals-dev). 192 words, ~534 tokens.
Download SKILL.mdSave it as
.claude/skills/inspect/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- inspect
- description
- Inspect and debug live streaming agent sessions to understand what the agent did. Use this skill when the user wants to see what happened in a recent agent run, trace through the tool calls step by step, debug unexpected agent behavior, or get a readable narrative of a session. Trigger on phrases like "show me what my agent did", "inspect session", "what happened in that run", "debug my agent", "trace through session", "walk me through the last run", "what tools did it call". Requires `agentevals serve --dev` to be running. For scoring/pass-fail evaluation, use /eval instead.
Help the user understand what happened in a live streaming agent session.
If list_sessions or summarize_session fail with a connection error, the server
is not running. Tell the user:
uv run agentevals serve --devThe --dev flag is required — plain serve does not enable the WebSocket endpoint
that sessions stream to. Also note: sessions are in-memory only with a 2-hour TTL.
If the server was restarted or the session is older than 2 hours, it is gone.
List sessions with
list_sessions. Show session ID, completion status, span count, and start time. Default to the most recent completed session unless the user specifies one.Summarize with
summarize_session. This converts raw OTLP spans into structured invocations with user messages, tool calls, and agent responses.Present as a readable narrative. For each turn:
Turn 1: User: [what the user asked] Tools: tool_name(arg=val, ...) → [one-line description of what this achieves] Response: [response text, truncated if long]Flag anything worth investigating:
- Turns with no tool calls when tools would be expected
- Empty or very short response after a long tool chain
- Same tool called repeatedly in one turn (possible loop)
- Abrupt stop mid-conversation
Offer next steps. If the user wants to score the session against a golden reference (pass/fail), suggest
/evalwith the session ID or a comparison run.
© agentevals-dev, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .claude/skills/inspect of agentevals-dev/agentevals.
- SKILL.md
- evals/evals.json
Open the folder on GitHubat commit 94785bb
Compare with similar skills
Inspect 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 |
|---|---|---|---|---|---|---|
| Inspect this skillagentevals-dev/agentevals | 162 | — | ~534 | Automated safety check: Pass | Apache-2.0 | |
| Improve PromptAgentX-ai/AgentX-Trace-Eval | 106 | — | ~2k | Automated safety check: Pass | Custom licence | |
| Dt Obs GenaiDynatrace/dynatrace-for-ai | 161 | — | ~4.5k | Automated safety check: Pass | Apache-2.0 | |
| Agent Kill Switchvivekchand/clawmetry | 424 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Sls Dashboard Builderalibaba/loongsuite-pilot | 198 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Agent Platform Alert Configurationgoogle/skills | 21k | — | ~4.2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Dt Obs Genai
Dynatrace/dynatrace-for-ai
Analyze & debug GenAI/LLM apps: token cost & caching by prompt, model & provider; latency/errors; agent & tool loops/failures; conversations; guardrails; evaluations; OpenTelemetry/dt-evals setup.
Agent Kill Switch
vivekchand/clawmetry
Give the human an off switch and a cost meter for the coding agents on this machine, using ClawMetry.
Sls Dashboard Builder
alibaba/loongsuite-pilot
当任务需要创建、修改、扩展或重组阿里云 SLS 的 dashboard JSON 或可导入的大盘配置时使用；尤其适用于线上大盘、强对比的分析看板、已校验的查询包，或需要专业中文标签与指标定义的运维向大盘。
- 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.
Clawmetry Selfcheck
vivekchand/clawmetry
Read your own agent telemetry from ClawMetry (waste, progress, cost) and act on it before finishing a task.
More from agentevals-dev/agentevals
Eval
agentevals-dev/agentevals
Evaluate and score agent behavior against a golden reference.
Related
Works with
Categories
Questions about Inspect
What does Inspect do?
Inspect and debug live streaming agent sessions to understand what the agent did. Inspect is an agent skill from agentevals-dev/agentevals. Inspect and debug live streaming agent sessions to understand what the agent did.
When should I use Inspect?
Inspect fits situations like: the user wants to see what happened in a recent agent run; trace through the tool calls step by step; debug unexpected agent behavior; get a readable narrative of a session.
How do I install Inspect in Claude Code?
Run `npx skills add agentevals-dev/agentevals --skill inspect -a claude-code`. Or copy the skill folder (.claude/skills/inspect in agentevals-dev/agentevals) into .claude/skills/inspect in your project. Claude Code loads it when a task matches its description.
How do I install Inspect in Codex?
Run `npx skills add agentevals-dev/agentevals --skill inspect -a codex`. Or copy the skill folder (.claude/skills/inspect in agentevals-dev/agentevals) into .agents/skills/inspect in your project. Codex loads it when a task matches its description.
Can I use Inspect 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 agentevals-dev/agentevals --skill inspect -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/inspect, .gemini/skills/inspect, .github/skills/inspect and .opencode/skills/inspect in your project.
What does Inspect need to run?
Going by SKILL.md and its folder, Inspect needs the command-line tools its instructions call (uv).
Does Inspect access the network?
SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Inspect safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Inspect use?
Inspect is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Inspect use?
About 534 tokens (SKILL.md is roughly 2.1k 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 Inspect?
Skills that share tags, products or a category with Inspect: Improve Prompt (AgentX-ai/AgentX-Trace-Eval, 106 stars), Dt Obs Genai (Dynatrace/dynatrace-for-ai, 161 stars), Agent Kill Switch (vivekchand/clawmetry, 424 stars) and Sls Dashboard Builder (alibaba/loongsuite-pilot, 198 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Inspect?
agentevals-dev (a GitHub organization) maintains it in agentevals-dev/agentevals, which has 162 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 6, 2026.
Source: agentevals-dev/agentevals on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.