Skills agent-manager-skill
📦

agent-manager-skill

Content revision r2 Safe ⚙️ External commands🌐 Network access

Manage Local CLI Agents with tmux

Coordinating several local CLI agents manually makes task assignment, monitoring, and scheduling difficult. This skill provides tmux-based commands for starting, assigning, and observing agents.

Supports: Claude Codex Code(CC)
🥉 78 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "agent-manager-skill" from https://skillstore.io/skills/sickn33-agent-manager-skill.md and its manifest at https://skillstore.io/api/skills/sickn33-agent-manager-skill/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/sickn33-agent-manager-skill.md Signed manifest GET /api/skills/sickn33-agent-manager-skill/manifest Signed lockfile GET /api/skills/sickn33-agent-manager-skill/lockfile

Test it

Using "agent-manager-skill". Verify that this workstation can run the agent manager.

Expected outcome:

Readiness review complete. Python 3 and tmux are available. Agent configuration was found under the expected directory.

Using "agent-manager-skill". Start the development agent and watch for startup problems.

Expected outcome:

Agent EMP_0001 started in its local session. Monitoring shows normal startup output and no reported errors.

Using "agent-manager-skill". Assign the maintenance workflow to a worker and prepare a daily schedule.

Expected outcome:

The workflow was assigned to EMP_0002. A daily schedule was proposed for review, but no cron entry was created.

Security Audit

Safe
v5 • 7/23/2026 Open versioned report

Six external-command findings are false positives caused by Markdown inline-code and fenced-code syntax; the document contains no shell backtick execution. The GitHub clone instruction is a confirmed low-severity supply-chain risk because it fetches mutable, unverified external content. No prompt injection or data-exfiltration intent was found.

1
Files scanned
48
Lines analyzed
1
Review items
0
False positives ignored
Capability review items (1)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Low
SKILL.md:24
Hardcoded URL
git clone https://github.com/fractalmind-ai/agent-manager-skill.git
The prerequisite clones a mutable external GitHub repository without pinning a commit or verifying integrity. Later documented commands depend on downloaded code, creating low supply-chain exposure.

Risk Factors

⚙️ External commands (6)
SKILL.md:21 SKILL.md:23-25 SKILL.md:25-29 SKILL.md:29-37 SKILL.md:37-41 SKILL.md:41
🌐 Network access (1)
SKILL.md:24
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/sickn33-agent-manager-skill/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/sickn33-agent-manager-skill/security.svg)](https://skillstore.io/skills/sickn33-agent-manager-skill?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/sickn33-agent-manager-skill?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-agent-manager-skill/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/sickn33-agent-manager-skill.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

sickn33. (2026). agent-manager-skill security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-agent-manager-skill/audits/5

BibTeX citation

@techreport{sickn33-sickn33-agent-manager-skill-2026, author = {sickn33}, title = {agent-manager-skill security audit report (audit version 5)}, institution = {Skillstore}, year = {2026}, number = {5}, url = {https://skillstore.io/skills/sickn33-agent-manager-skill/audits/5}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "agent-manager-skill security audit report (audit version 5)" version: "unspecified" type: report authors: - name: "sickn33" date-released: "2026-07-23" url: "https://skillstore.io/skills/sickn33-agent-manager-skill/audits/5" identifiers: - type: other value: "skillstore:sickn33-agent-manager-skill:audit:5" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
87
Content
69
Community
83
Spec Compliance

What You Can Build

Parallel Development Agents

Run independent coding tasks across separate local sessions while keeping each agent output isolated.

Routine Repository Maintenance

Assign recurring maintenance workflows and prepare controlled cron schedules for local repositories.

Agent Fleet Observation

List agents and follow session output during coordinated multi-agent work.

Try These Prompts

Check Prerequisites 
Run the agent-manager doctor check. Report whether tmux, Python, and agent configuration are ready. Do not change anything.
List and Inspect Agents 
List configured agents, summarize their current states, and identify any agent needing attention. Do not start or stop sessions.
Start and Monitor an Agent 
Start agent [AGENT_ID], then monitor its output. Confirm the session started and summarize errors without changing other agents.
Coordinate a Scheduled Workflow 
Review [WORKFLOW_FILE], assign it to [AGENT_ID], and propose a cron schedule. Ask before creating cron entries or modifying agent configuration.

Best Practices

  • Run the doctor check before starting agents or assigning workflows.
  • Use explicit agent identifiers and review current state before every action.
  • Review workflows and obtain approval before cron or consequential operations.

Avoid

  • Do not include credentials or sensitive data in assignments or monitored output.
  • Do not start duplicate sessions without checking the current agent list.
  • Do not treat monitor output as proof that a workflow completed correctly.

Frequently Asked Questions

What does this skill manage?
It guides local CLI agent operations through an external agent manager, with tmux sessions for parallel work.
Which dependencies are required?
The documented workflow requires tmux, Python 3, and the referenced agent-manager repository.
Can it run agents on remote machines?
No remote workflow is documented. The skill describes local sessions only.
Can it schedule recurring work?
It identifies cron-friendly scheduling as a use case. Review schedules and permissions before creating cron entries.
Does it include the management scripts?
No. This package contains SKILL.md guidance and directs users to clone the separate agent-manager repository.
Which AI tools are supported?
The marketplace metadata lists Claude, Codex, and Claude Code as supported tools.

Developer Details

Author

sickn33

License

MIT

Skillstore revision

r2

Version notice

The author did not declare a version.

Repository

https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/agent-manager-skill

Ref

ebdfe608f5de2b66ff37ab4af12af8ac4f5e8006

Maintenance freshness

7/26/2026

Usage

5 downloads · 161 views

File structure

📄 SKILL.md