# Session Scan

> Compute metrics for Claude Code sessions. Discovers via ccrider, filters trivial, computes friction/opportunity/fingerprint scores. Use for broad session triage.

- **Type:** Skill
- **Install:** `agentstack add skill-oliver-kriska-claude-elixir-phoenix-session-scan`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [oliver-kriska](https://agentstack.voostack.com/s/oliver-kriska)
- **Installs:** 0
- **Category:** [Data & Analytics](https://agentstack.voostack.com/c/data-and-analytics)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [oliver-kriska](https://github.com/oliver-kriska)
- **Source:** https://github.com/oliver-kriska/claude-elixir-phoenix/tree/main/.claude/skills/session-scan
- **Website:** https://phxagents.dev

## Install

```sh
agentstack add skill-oliver-kriska-claude-elixir-phoenix-session-scan
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Session Scan (Tier 1)

Compute deterministic metrics for sessions discovered via ccrider MCP.

## STOP — Read Before Executing

**NEVER call `mcp__ccrider__get_session_messages` in main context.**
Each response is 5-50KB of JSON. Fetching N sessions directly = context crash.

**You MUST delegate all scoring to subagents.** The main context only does:
discovery, deduplication, subagent spawning, and result collection.

## Requirements

Requires **ccrider MCP**. If not available:

> ccrider MCP is required. See: 

## Usage

```
/session-scan                         # Last 7 days, up to 50 sessions
/session-scan --since 2026-02-01      # Since specific date
/session-scan --project enaia         # Filter by project name
/session-scan --limit 20              # Cap session count
/session-scan --list                  # Discovery only, no scoring
/session-scan --rescan                # Recompute already-scanned sessions
```

## What Main Context Does

### 1. Parse Arguments

Extract from `$ARGUMENTS`:

- **`--since DATE`**: ISO date filter (default: 7 days ago)
- **`--project NAME`**: Filter by project path substring
- **`--limit N`**: Max sessions to process (default: 50)
- **`--list`**: Discovery only — show table, skip scoring
- **`--rescan`**: Recompute metrics for already-scanned sessions

### 2. Discover Sessions (safe — response is ~1KB)

```
mcp__ccrider__list_recent_sessions(limit: N, project: PROJECT, after_date: SINCE)
```

Filter out sessions with  {PROJECT_ROOT}/.claude/session-metrics/_result_{SHORT_ID}.json && rm {PROJECT_ROOT}/.claude/session-metrics/_tmp_{SHORT_ID}.json

4. Report back: "Scored {SHORT_ID}: friction=X.XX fingerprint=Y"

If ccrider fails, report the error and exit.
""")
```

**Spawn ALL subagents in parallel.** Wait for all to complete.

### 6. Collect Results

```bash
for f in .claude/session-metrics/_result_*.json; do
  cat "$f" >> .claude/session-metrics/metrics.jsonl
  rm "$f"
done
```

### 7. Display Results

Show summary table sorted by friction (descending):

```
| ID       | Project | Date       | Type        | Friction | Opportunity | Tier2? |
|----------|---------|------------|-------------|----------|-------------|--------|
| ffa155ee | enaia   | 2026-02-18 | bug-fix     | 0.42     | 0.65        | Yes    |
| 90a74843 | wedding | 2026-02-17 | feature     | 0.15     | 0.20        | No     |
```

If Tier 2 eligible: suggest `/session-deep-dive --from-scan`.

### 8. Update Scan Metadata

Write `.claude/session-metrics/latest-scan.json`:

```json
{
  "scanned_at": "2026-02-20T14:30:00Z",
  "sessions_discovered": 25,
  "sessions_scanned": 18,
  "sessions_skipped": 7,
  "tier2_eligible": 5
}
```

## Scoring Reference

See `references/scoring-guide.md` for full algorithm documentation.

- **Friction Score** (0-1): Weighted signals, sigmoid-normalized
- **Fingerprint**: Rule-based classifier (6 types)
- **Plugin Opportunity** (0-1): Missed `/phx:` commands
- **Tier 2 Eligible**: friction > 0.35 OR opportunity > 0.5 OR plugin used OR msgs > 50

## Iron Laws

1. **NEVER call `get_session_messages` in main context** — WILL crash context
2. **ONE subagent per session** — each fetches exactly ONE session
3. **`mode="bypassPermissions"` on every Task** — subagents need Write+Bash
4. **Absolute paths in subagent prompts** — subagents don't inherit context
5. **Result files, not direct append** — avoid jsonl race conditions
6. **NEVER modify existing metrics.jsonl entries** — append-only ledger
7. **ALWAYS delete temp and result files** after processing

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [oliver-kriska](https://github.com/oliver-kriska)
- **Source:** [oliver-kriska/claude-elixir-phoenix](https://github.com/oliver-kriska/claude-elixir-phoenix)
- **License:** MIT
- **Homepage:** https://phxagents.dev

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-oliver-kriska-claude-elixir-phoenix-session-scan
- Seller: https://agentstack.voostack.com/s/oliver-kriska
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.