Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
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
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Agent Swarm

ASecurity

(Industry standard: Parallel Agent) Parallel multi-agent execution pattern for independent sub-tasks running concurrently across isolated worktrees.

7 stars
0 votes
0 copies
0 views
Added 9/2/2026
ai-agentspythonbashbackend

Works with

cli

Security Analysis

A100/100

Pro scans all 12 files and shows the line behind each finding

Scanned 10/3/2026

$npx -y skills add richfrem/agent-plugins-skills --skill agent-swarm --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Agent Swarm?

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

Security grade badge for Agent Swarm
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/richfrem-agent-swarm-agent-plugins-skills/badge)](https://www.skillsdirectory.com/skills/richfrem-agent-swarm-agent-plugins-skills)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: agent-swarm
plugin: agent-orchestration
description: "(Industry standard: Parallel Agent) Parallel multi-agent execution pattern for independent sub-tasks running concurrently across isolated worktrees."
allowed-tools: Bash, Read, Write
---

## Dependencies

Requires Python 3.8+ (standard library only).

---

# Agent Swarm (`agent-swarm`)

Parallel multi-agent execution for batch operations, independent work packages, and mass migrations.

## Contents

- [Dependencies](#dependencies)
- [Constraints](#constraints)
- [Quick start](#quick-start)
- [Workflow](#workflow)
- [Verification](#verification)
- [Engine Optimization](#engine-optimization)
- [References](#references)

## Constraints

- **Independent execution**: Each worker task must be completely independent with zero shared in-memory state.
- **Background stdin**: Append `< /dev/null` to background commands to prevent `SIGTTIN` hangs.
- **Idempotence**: Post-processing commands must be safe to rerun with `--resume`.
- **Concurrency caps**: Limit Copilot CLI to `--workers 2` to prevent throttling; Gemini/Claude supports 5-10.

## Quick start

```bash
# Execute batch job with resume support
python ./scripts/swarm_run.py \
    --engine gemini \
    --job ./resources/jobs/my_job.job.md \
    --files-from checklist.md \
    --resume --workers 5
```

## Workflow

1. **Partition**: Break work into discrete, independent task files with bounded scopes.
2. **Select Engine**: Choose CLI backend (`agy`, `gemini`, `copilot`, `claude`, `llama`).
3. **Dispatch**: Run `swarm_run.py` pointing to the job file and target file list.
4. **Inspect**: Review intermediate logs and resolve failed workers via `--resume`.
5. **Merge**: Run mechanical test suites across all completed worker outputs.

## Verification

```bash
# Validate batch execution completed without orphaned tasks
python ./scripts/swarm_run.py --dry-run --files-from checklist.md
# Run test suite on completed batch outputs
pytest tests/
```

## Engine Optimization

- **Copilot CLI**: Ignores `-p` with stdin; `swarm_run.py` prepends prompt to file content. Concurrency max 2.
- **Gemini / Claude**: Accepts `-p` normally; supports high concurrency (`--workers 5`).
- **Atomic Writes**: If workers write to shared stores, use `fcntl.flock` for atomic file operations.

## References

- [PATTERN_GUIDE.md](references/PATTERN_GUIDE.md) — Comparative loop patterns and architecture.
- [acceptance-criteria.md](references/acceptance-criteria.md) — Verification gates and trigger criteria.
- [fallback-tree.md](references/fallback-tree.md) — Error escalation and checkpoint reconciliation tree.

Attribution

richfremrichfrem
View sourceSee grades on GitHubMore from richfrem →
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

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 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', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 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.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, 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.

741 votes
View all in ai-agents →