How do I install the Vestige Trace List skill?

Run npx skillmds@latest add conorluddy/vestige-trace-list in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Vestige Trace List safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Vestige Trace List?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Vestige Trace List free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Vestige Trace List?

conorluddy (@conorluddy) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Vestige Trace List by conorluddy — Agent Skill

Name: Vestige Trace List
Author: conorluddy

Vestige Trace List

Use this skill when you want to audit what queries the agent or CLI has run against project memory. Fire when the user says "what queries did the agent run?", "show recent trace events", "did anyone search for X recently?", or "list traces by caller mcp". Every vestige search, recall, expand, and context call writes a query_events row automatically — this skill surfaces them. Use vestige-trace-show to expand a single trace.

conorluddy Updated Sep 17, 2026

File contents

List recent query traces

Every vestige search, vestige recall, vestige expand, and vestige context call writes a row to query_events automatically — no configuration required. This skill lists those rows, filtered by kind, caller, date, or count. Use it to audit what the agent asked and when.

When to fire

Audit trail. Reviewing what recall calls were made in a session before writing a summary or PR.
Debug recall quality. Seeing what mode (lexical / hybrid) was resolved for recent searches.
MCP vs CLI split. Filtering by --caller to separate agent-driven traces from human CLI runs.
Temporal filter. Narrowing to traces since a specific date — e.g. since a refactor started.

How to invoke

vestige trace [--limit N] [--kind <kind>] [--caller <cli|mcp>] [--since <date>] [--json]

--limit <n>: number of traces to return (default: 10).
--kind <kind>: filter by trace kind — search, expand, or context.
--caller <cli|mcp>: filter by surface that issued the query.
--since <date>: only traces at or after this ISO-8601 date/datetime.
--json: structured output.

vestige trace                            # last 10 traces, text
vestige trace --limit 50                 # last 50
vestige trace --kind search              # search traces only
vestige trace --caller mcp               # agent-originated only
vestige trace --since 2026-05-08         # since date
vestige trace --json                     # JSON envelope

After invocation

{
  "traces": [
    {
      "trace_id":    "trace_01JWXXXXXXXXXXXXXXXXXX",
      "kind":        "search",
      "mode":        "hybrid",
      "query":       "ULID migration ordering",
      "result_count": 2,
      "latency_ms":  43,
      "caller":      "mcp",
      "created_at":  "2026-05-08T14:02:11Z"
    },
    {
      "trace_id":    "trace_01JVXXXXXXXXXXXXXXXXXX",
      "kind":        "expand",
      "mode":        null,
      "query":       null,
      "result_count": 1,
      "latency_ms":  3,
      "caller":      "mcp",
      "created_at":  "2026-05-08T14:01:58Z"
    }
  ]
}

Use vestige-trace-show <trace_id> to expand a single trace to its full detail including result IDs and score breakdown.

---name: vestige-trace-listdescription: Use this skill when you want to audit what queries the agent or CLI has run against project memory. Fire when the user says "what queries did the agent run?", "show recent trace events", "did anyone search for X recently?", or "list traces by caller mcp". Every vestige search, recall, expand, and context call writes a query_events row automatically — this skill surfaces them. Use vestige-trace-show to expand a single trace.---# List recent query tracesEvery `vestige search`, `vestige recall`, `vestige expand`, and `vestige context` call writes a row to `query_events` automatically — no configuration required. This skill lists those rows, filtered by kind, caller, date, or count. Use it to audit what the agent asked and when.## When to fire- **Audit trail.** Reviewing what recall calls were made in a session before writing a summary or PR.- **Debug recall quality.** Seeing what mode (lexical / hybrid) was resolved for recent searches.- **MCP vs CLI split.** Filtering by `--caller` to separate agent-driven traces from human CLI runs.- **Temporal filter.** Narrowing to traces since a specific date — e.g. since a refactor started.## How to invoke```bashvestige trace [--limit N] [--kind <kind>] [--caller <cli|mcp>] [--since <date>] [--json]```- **`--limit <n>`**: number of traces to return (default: 10).- **`--kind <kind>`**: filter by trace kind — `search`, `expand`, or `context`.- **`--caller <cli|mcp>`**: filter by surface that issued the query.- **`--since <date>`**: only traces at or after this ISO-8601 date/datetime.- **`--json`**: structured output.```bashvestige trace # last 10 traces, textvestige trace --limit 50 # last 50vestige trace --kind search # search traces onlyvestige trace --caller mcp # agent-originated onlyvestige trace --since 2026-05-08 # since datevestige trace --json # JSON envelope```## After invocation```json{ "traces": [ { "trace_id": "trace_01JWXXXXXXXXXXXXXXXXXX", "kind": "search", "mode": "hybrid", "query": "ULID migration ordering", "result_count": 2, "latency_ms": 43, "caller": "mcp", "created_at": "2026-05-08T14:02:11Z" }, { "trace_id": "trace_01JVXXXXXXXXXXXXXXXXXX", "kind": "expand", "mode": null, "query": null, "result_count": 1, "latency_ms": 3, "caller": "mcp", "created_at": "2026-05-08T14:01:58Z" } ]}```Use `vestige-trace-show <trace_id>` to expand a single trace to its full detail including result IDs and score breakdown.

Frequently asked questions