Skip to content
mcp/skillhub

Agent Skill

Session Investigator skill

session-investigatorevalstate/fast-agentexamples/hf-toad-cards/skills/session-investigator/SKILL.md

Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool call/result correlation, and common failure patterns.

3.9kApache-2.0

always on

68 tokname + description

once used

2,217 tokSKILL.md body

bundled files

0

repo stars

3.9kGitHub

Install the Session Investigator skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/evalstate/fast-agent --skill session-investigator

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/evalstate/fast-agent.git /tmp/fast-agent
mkdir -p ~/.claude/skills
cp -R /tmp/fast-agent/examples/hf-toad-cards/skills/session-investigator ~/.claude/skills/session-investigator

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description68 tok
When the agent uses itThe SKILL.md instructions2,217 tok
Only if openedNo bundled files—

Until it is used, session-investigator costs about 20× less than the median MCP server we measured (1,363 tokens on every turn). Installing all 3 skills from evalstate/fast-agent would load 184 tokens of descriptions. Skills vs MCP study

Checks

Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • Session Investigator
  • Session Directory Structure
  • Key Files
  • session.json
  • history\<agent>.json
  • Investigation Commands
  • Basic inspection
  • Tool call correlation
  • Find specific tool calls
  • Session Statistics
  • LLM Call Stats
  • Tool Execution Stats
  • Session Timeline
  • Sub-agent Stats
  • Common Failure Patterns
  • Unanswered Tool Call
  • Duplicate User Messages
  • Sub-agent Trace Correlation
  • Log File

More skills from evalstate/fast-agent

All skills in this repo
  1. fast-agent-designevalstate/fast-agent

    Use this skill to generate well-branded interfaces and assets for fast-agent, either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for protoyping.

    3.9k2252 tok idle · 117 in use
  2. pr-writing-reviewevalstate/fast-agent

    Extract and analyze writing improvements from GitHub PR review comments. Use when asked to show review feedback, style changes, or editorial improvements from a GitHub pull request URL. Handles both explicit suggestions and plain text feedback. Produces structured output comparing original phrasing with reviewer suggestions to help refine future writing.

    3.9k164 tok idle · 1,530 in use