Is the Session Scan skill free?

Yes. The skill itself is free from oliver-kriska/claude-elixir-phoenix. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Session Scan SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Session Scan?

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 Scan 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 Scan

Deterministic friction/fingerprint scoring to triage past Claude Code sessions

by oliver-kriska · oliver-kriska/claude-elixir-phoenix

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 9.2/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · e1ff3c0

Fetched SKILL.md plus both referenced files (compute-metrics.py = HTTP 200 / 67KB, scoring-guide.md = HTTP 200). Security scan of the 1765-line scorer found no network, subprocess, eval, or base64 — stdlib only; it writes only its own result/HTML files. I could not run the full pipeline (ccrider MCP unavailable), so I fabricated a 9-message ccrider-format bug-fix session and ran compute-metrics.py directly: it output friction_score=1.0, fingerprint=bug-fix (conf 0.80), user_corrections=2, retry_loops=1, a tool_profile/bigrams breakdown, and tier2_eligible=true reason "friction > 0.35". Baseline eyeball of the same transcript gave only "bug-fix, moderate-high friction, no scale." Scoring-guide weights matched FRICTION_WEIGHTS in code; verdict is setup because end-to-end use hard-requires the external ccrider MCP.

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 8/10
Docs & honesty 5/5

What Session Scan does

Computes deterministic metrics (friction score, session fingerprint, plugin-opportunity, tool profile) for Claude Code sessions discovered via the ccrider MCP, delegating each session to a haiku subagent and appending results to an append-only metrics ledger. Triggers when you want broad triage of recent sessions — finding which ones had the most struggle, retries, or corrections. It is a manual /session-scan command (disable-model-invocation) and hard-requires the external ccrider MCP server to fetch session messages.

How to install Session Scan

git clone --depth 1 https://github.com/oliver-kriska/claude-elixir-phoenix.git /tmp/session-scan-src
mkdir -p ~/.claude/skills
cp -R /tmp/session-scan-src/.claude/skills/session-scan ~/.claude/skills/session-scan
# REQUIRES the ccrider MCP server (session discovery + message fetch): https://github.com/neilberkman/ccrider
#   Without ccrider the skill cannot discover or fetch sessions and will not run end-to-end.
# Invocation: manual slash command only — /session-scan (SKILL.md sets disable-model-invocation: true)
# Deps: python3 (stdlib only, no pip installs). Scorer: references/compute-metrics.py
# Runtime: spawns one haiku subagent per session (mode=bypassPermissions); writes to <project>/.claude/session-metrics/

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

Commands — how to trigger Session Scan

/session-scan Deterministic friction/fingerprint scoring to triage past Claude Code sessions

It also activates on plain-language prompts like these:

Scan my recent Claude Code sessions for friction
Which sessions had the most wasted effort
Triage sessions by opportunity score

Frequently asked questions

Is the Session Scan skill free?: Yes. The skill itself is free from oliver-kriska/claude-elixir-phoenix. SkillProof publishes the install command and an independent test verdict at no cost.
Does Session Scan work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Works with setup. Fetched SKILL.md plus both referenced files (compute-metrics.py = HTTP 200 / 67KB, scoring-guide.md = HTTP 200). Security scan of the 1765-line scorer found no network, subprocess, eval, or base64 — stdlib only; it writes only its own result/HTML files. I could not run the full pipeline (ccrider MCP unavailable), so I fabricated a 9-message ccrider-format bug-fix session and ran compute-metrics.py directly: it output friction_score=1.0, fingerprint=bug-fix (conf 0.80), user_corrections=2, retry_loops=1, a tool_profile/bigrams breakdown, and tier2_eligible=true reason "friction > 0.35". Baseline eyeball of the same transcript gave only "bug-fix, moderate-high friction, no scale." Scoring-guide weights matched FRICTION_WEIGHTS in code; verdict is setup because end-to-end use hard-requires the external ccrider MCP.
What is the Session Scan SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Session Scan?: 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 Scan 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.