Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Find Claude Code sessions tracked by the Agent Monitor by project (cwd), model, status, or date, then rank the matches by cost or recency. Pulls the session list and the distinct cwd / facet values so filters use real values rather than guesses. Use when locating a session — "find my EstateWise sessions", "which Opus runs errored this week", "most expensive sessions in /repo".
.claude/skills/hoangsonww-session-search/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-12 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-08 | ✓→✗ | ▼ Worse | -14% | 0% |
| case-15 | ✓→✗ | ▼ Worse | -22% | 0% |
| case-16 | ✓→✗ | ▼ Worse | -44% | 0% |
| case-22 | ✓→✗ | ▼ Worse | 300% | 0% |
Locate Claude Code sessions in the Agent Monitor by project, model, status, or date.
The user provides: $ARGUMENTS
A free-form query naming any combination of:
EstateWise, /Users/.../repo)opus, sonnet, haiku, or a full model id substringactive, working, completed, errortoday, this week, or an ISO date / range matched against started_atby cost (default when cost is mentioned) or recent (default otherwise)If the query is empty, return the most recent sessions ranked by recency.
| Endpoint | Returns | |----------|---------| | GET /api/sessions?limit=N | session list: id, status, model, cwd, started_at, ended_at, cost, metadata (thinking_blocks, turn_count, total_turn_duration_ms, usage_extras) | | GET /api/run/cwds | the distinct working directories that have sessions — use to resolve a fuzzy project name to exact cwd values | | GET /api/events/facets | distinct facet values (event types, tool names, models, statuses) for validating filters |
Fetch /api/run/cwds and /api/events/facets to map the user's loose terms to real values: pick the cwd(s) whose path contains the project term, confirm the model substring exists, and validate the status against known statuses. State which concrete filters you settled on.
GET /api/sessions?limit=200 (raise the limit if the date window is wide). Filter in-memory by cwd, model (substring, case-insensitive), status, and started_at date window.
Sort by cost descending when the user asked "by cost"; otherwise by started_at descending (most recent first). Keep the top 20 unless the user asked for more.
One row per session.
Count of matches, summed cost across matches, and the model / status distribution.
Markdown table: # | id (short) | status | model | cwd (basename) | started_at | cost. Currency as USD to 4 decimal places; token / count fields with thousands separators. If a filter resolved to zero rows, say so and show the closest available values (e.g. the cwds that do exist) rather than fabricating results. If the dashboard is unreachable, tell the user to start it with npm start from the repo root.
Other measured skills in the registry, with their headline benchmark lift.