Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Track Autonomous Research Agents

ASecurity

CLI tool for managing autonomous research agents with append-only state, instruction queues, and oversight.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgobashsqlgitdatabase

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill track-autonomous-research-agents --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Track Autonomous Research Agents?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Track Autonomous Research Agents
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-track-autonomous-research-agents/badge)](https://www.skillsdirectory.com/skills/rondoflow-track-autonomous-research-agents)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: track-autonomous-research-agents
description: "CLI tool for managing autonomous research agents with append-only state, instruction queues, and oversight."
category: "AI & Agents"
author: community
version: "0.1.0"
icon: bot
---

# Research Tracker

CLI tool for managing autonomous research agents with append-only state, instruction queues, and oversight.

## Prerequisites

```bash
brew tap 1645labs/tap
brew install julians-research-tracker
```

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

## Quick Start

### Start a research project
```bash
research init market-q1 --name "Q1 Market Analysis" --objective "Analyze competitor pricing and positioning"
```

### As the research agent — log progress
```bash
export RESEARCH_SESSION_ID="$SESSION_KEY"  # Track which agent is writing

research log market-q1 STEP_BEGIN --step 1 --payload '{"task":"gather sources"}'
# ... do work ...
research log market-q1 STEP_COMPLETE --step 1
research heartbeat market-q1
```

### Check status (from main session or heartbeat)
```bash
research status market-q1 --json
research context market-q1 --last 5  # Truncated context for prompts
```

### Send instructions to running agent
```bash
research instruct market-q1 "Focus on enterprise segment" --priority URGENT
research stop-signal market-q1  # Request graceful stop
```

### Agent checks for instructions
```bash
research pending market-q1 --json
research ack market-q1 --all  # Acknowledge after processing
research check-stop market-q1  # Exit 0 = stop, Exit 1 = continue
```

## Commands Reference

| Command | Purpose |
|---------|---------|
| `init <id> -o "..."` | Create project with objective |
| `list [--status active\|done\|all]` | List projects (includes `needs_attention` flag) |
| `show <id>` | Project details + recent events |
| `stop <id>` | Stop project, send STOP instruction |
| `archive <id>` | Archive completed project |
| `log <id> <event> [--step N]` | Log event (STEP_BEGIN, CHECKPOINT, BLOCKED, etc.) |
| `heartbeat <id>` | Update alive timestamp |
| `block <id> --reason "..."` | Mark blocked, needs input |
| `complete <id>` | Mark done |
| `status <id> [--json]` | Current state summary |
| `context <id> [--last N]` | Truncated context for agent prompts |
| `instruct <id> "text"` | Send instruction |
| `pending <id>` | List unacked instructions |
| `ack <id> [--all]` | Acknowledge instructions |
| `check-stop <id>` | Exit code: 0=stop, 1=continue |
| `audit <id> --verdict pass\|drift` | Log audit result |

## Event Types

`STARTED`, `STEP_BEGIN`, `STEP_COMPLETE`, `CHECKPOINT`, `BLOCKED`, `UNBLOCKED`, `AUDIT_PASS`, `AUDIT_DRIFT`, `HEARTBEAT`, `DONE`, `STOPPED`, `TIMEOUT`

## Integration Pattern

### Spawning a research agent

```
1. research init <project> --objective "..."
2. sessions_spawn with task including:
   - Project ID and objective
   - Instructions to use research CLI for state
   - Check stop signal before each step
   - Log progress with heartbeat
3. Heartbeat monitors: research list --json | check needs_attention
4. Send instructions via: research instruct <project> "..."
```

### Agent loop (in spawned agent)

```bash
while research check-stop $PROJECT; [ $? -eq 1 ]; do
  research pending $PROJECT --json  # Check instructions
  research log $PROJECT STEP_BEGIN --step $STEP
  # ... do work ...
  research log $PROJECT STEP_COMPLETE --step $STEP
  research heartbeat $PROJECT
  STEP=$((STEP + 1))
done
research complete $PROJECT
```

## Attention Detection

`research list --json` includes `needs_attention: true` when:
- Last event is BLOCKED
- Has unacked URGENT or STOP instructions
- Heartbeat stale (>5 min since last HEARTBEAT event)
- Last audit was AUDIT_DRIFT

## Database

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

Run `research db migrate` after install. Schema auto-migrates on first use.

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →