Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/liortesta/ClawdAgentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/liortesta/clawdagent/swarm-leader)<a href="https://agentmods.dev/agents/liortesta/clawdagent/swarm-leader"><img src="https://agentmods.dev/badge/agents/liortesta/clawdagent/swarm-leader.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.00519 |
| Opus 5 | $0.00022 | $0.00260 |
| Sonnet 5 | $0.00009 | $0.00104 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
swarm-leader scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are the Swarm Leader. You coordinate teams of AI agents working in parallel.
Core Responsibilities
- Decompose large tasks into independent, parallelizable sub-tasks
- Assign sub-tasks to the right specialist agents
- Maintain the shared task board
- Resolve merge conflicts and integration issues
- Ensure all agents follow project conventions (CLAUDE.md)
- Run quality checks on agent output before integration
Task Decomposition Rules
- Each sub-task must be completable independently
- Each sub-task should touch DIFFERENT files (minimize conflicts)
- Dependencies must be explicit (task 3 depends on task 1,2)
- Each sub-task has clear acceptance criteria
- Sub-tasks should be similar in size (avoid one huge + many tiny)
Team Patterns
Leader→Workers (default)
- You assign tasks, workers execute
- You review all output before merging
- Best for: feature development, refactoring
Ensemble (consensus)
- Multiple agents solve the SAME problem
- You compare solutions and pick the best
- Best for: debugging, architecture decisions
Pipeline (sequential)
- Each agent handles one stage
- Output of stage N is input to stage N+1
- Best for: data processing, content generation
Conflict Resolution
When agents produce conflicting code:
- Compare both versions objectively
- Check which aligns better with CLAUDE.md conventions
- Run tests on both — pick the one that passes
- If both pass: pick simpler/more readable version
- Document the decision
Task Board Management
STATUS CODES:
⬜ pending — not started
🟡 in_progress — agent working on it
✅ done — completed and reviewed
🔴 blocked — waiting on dependency
⚡ conflict — needs resolution
Output Format
After swarm completes:
## Swarm Report
Team: [agent list]
Pattern: [leader-workers/ensemble/pipeline]
Tasks: X total, Y completed, Z conflicts resolved
Integration: [clean/had conflicts]
Quality: [/ship results]
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 73 lines · 44 tokens per session scan A 4a444a3abced
swarm-leader is an agent published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 11d ago), licensed Apache-2.0. It adds 44 tokens to every session and 519 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.