Research Tracker

PassAudited by ClawScan on May 10, 2026.

Overview

The skill is coherent for local research-agent tracking, but users should knowingly install the external CLI and supervise any long-running sub-agents and stored context.

Before installing, verify that you trust the external research CLI source, keep research-agent tasks narrowly scoped, monitor heartbeats and stop signals, and avoid storing secrets or highly sensitive material in the tracker database.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

Installing the skill's companion CLI means trusting code from the referenced external repository or Homebrew tap.

Why it was flagged

The skill is instruction-only in registry metadata, but its documented setup depends on installing an external CLI, including an unpinned @latest Go install target.

Skill content
brew tap 1645labs/tap
brew install julians-research-tracker

Or: `go install github.com/1645labs/julians-research-tracker/cmd/research@latest`
Recommendation

Install only if you trust the source; prefer a pinned version or reviewed release before using it for important research workflows.

What this means

A broadly scoped research task could continue consuming time or resources unless the user sets clear limits and monitors it.

Why it was flagged

The skill explicitly supports long-running sub-agent coordination and background research monitoring. This is purpose-aligned and disclosed, but it is a sensitive operating mode.

Skill content
Use when spawning long-running research sub-agents, tracking multi-step investigations, coordinating agent handoffs, or monitoring background work.
Recommendation

Use explicit project objectives, time/resource limits, and the documented stop-signal and heartbeat mechanisms when spawning research agents.

What this means

Past logs, queued instructions, or inaccurate project context may affect future research-agent prompts.

Why it was flagged

The tracker stores persistent research events and can reinsert recent context into future prompts, so stale or incorrect logged instructions could influence later agent behavior.

Skill content
SQLite at `~/.config/research-tracker/research.db` (WAL mode, append-only events).

`context <id> [--last N]` | Truncated context for agent prompts
Recommendation

Review project context before reusing it, avoid logging secrets or sensitive private data, and archive or clean up projects when they are no longer needed.