Is the Session Investigator skill free?

Yes. The skill itself is free from evalstate/fast-agent. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Session Investigator SkillProof Score?

8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 4/5.

How do I install Session Investigator?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Session Investigator with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Session Investigator

Investigates fast-agent session and history files to diagnose why a run failed.

by evalstate · evalstate/fast-agent

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.0/10
Tested: Jul 13, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 2066a6a

Tested verbatim install (clean clone+copy, self-contained SKILL.md, strict-YAML frontmatter) plus a fabricated fast-agent history_dev.json seeded with a dangling tool call. Both skill and base arms correctly identified the Unanswered Tool Call pattern at message index 5 and the same 0-4 truncation point; the skill arm edged ahead only by naming the canonical failure pattern and flagging that its own jq truncation recipe anchors too conservatively, so the A/B gain was marginal. Note the skill's commands silently assume jq is installed (absent on the test machine and never listed as a prerequisite).

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 6/10
Docs & honesty 4/5

What Session Investigator does

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.

How to install Session Investigator

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

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Session Investigator

/session-investigator Investigates fast-agent session and history files to diagnose why a run failed.

It also activates on plain-language prompts like these:

Why did this fast-agent session end unexpectedly
Correlate this sub-agent trace with the main session
Debug this tool loop using the session history

Frequently asked questions

Is the Session Investigator skill free?: Yes. The skill itself is free from evalstate/fast-agent. SkillProof publishes the install command and an independent test verdict at no cost.
Does Session Investigator work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Tested · Works. Tested verbatim install (clean clone+copy, self-contained SKILL.md, strict-YAML frontmatter) plus a fabricated fast-agent history_dev.json seeded with a dangling tool call. Both skill and base arms correctly identified the Unanswered Tool Call pattern at message index 5 and the same 0-4 truncation point; the skill arm edged ahead only by naming the canonical failure pattern and flagging that its own jq truncation recipe anchors too conservatively, so the A/B gain was marginal. Note the skill's commands silently assume jq is installed (absent on the test machine and never listed as a prerequisite).
What is the Session Investigator SkillProof Score?: 8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 4/5.
How do I install Session Investigator?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Session Investigator with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.