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.
npx skills add strikersam/autonomous-ai-agency --skill parallel-agentsgit clone --depth 1 https://github.com/strikersam/autonomous-ai-agencyWrote 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/skills/strikersam/autonomous-ai-agency/parallel-agents)<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/parallel-agents"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/parallel-agents/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/parallel-agents"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/parallel-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.00881 |
| Opus 5 | $0.00000 | $0.00441 |
| Sonnet 5 | $0.00000 | $0.00176 |
| Haiku 4.5 | $0.00000 | $0.00088 |
Grade A, and why
parallel-agents 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: parallel-agents
Purpose
Decompose a large task into N independent subtasks and dispatch them as parallel subagents, then aggregate results. Inspired by the Modal + OpenAI Agents SDK pattern of spawning multiple coding agents simultaneously — each working in its own sandbox — to discover solutions faster through parallelism.
When to Use
- A task has multiple independent sub-problems (e.g. "try 5 different approaches to optimise this function").
- You want competitive parallel exploration (like Parameter Golf — many agents racing to find the best solution).
- Long-running background work that should not block the main conversation.
- Fan-out research: gather information from many sources simultaneously.
Core Concepts (from the Modal/OpenAI Agents SDK pattern)
| Concept | Description |
|---|---|
| Harness | The outer loop that owns the task, spawns subagents, and collects results |
| Subagent | An isolated agent instance working on one subtask with its own tool set |
| Capability | A bound set of tools attached to a specific subagent instance (stateful) |
| Aggregator | Logic that merges/ranks subagent outputs into a final result |
Usage
@parallel-agents
task: <high-level goal>
subtasks:
- <subtask 1>
- <subtask 2>
- <subtask N>
strategy: <first-wins | collect-all | best-of>
Strategies
- first-wins — return as soon as any subagent succeeds (good for speculative execution).
- collect-all — wait for all subagents, return all results.
- best-of — collect all, then score/rank and return the top result.
Example — parallel approach exploration
@parallel-agents
task: Optimise the tokenizer for throughput
subtasks:
- Try a Rust rewrite of the hot path
- Try SIMD intrinsics in C via cffi
- Try batching + async I/O in Python
- Try a pre-computed lookup table approach
strategy: best-of
Example — parallel research
@parallel-agents
task: Summarise competing approaches to RAG chunking
subtasks:
- Fixed-size chunking strategies
- Semantic / sentence-boundary chunking
- Recursive character splitting
- Document-structure-aware chunking
strategy: collect-all
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.
- 11d ago First seen · 110 lines · 0 tokens per session scan A c0ef90e1634c
parallel-agents is a skill published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 881 tokens. 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 2026-08-31.
Other skills, from other repositories
assimilate-popular-workflows
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable…
process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
mcp-app-verification
Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling, host styling, CSP, and legacy pattern detection.
mcp-app-scaffolding
Scaffolds MCP App project structure with correct directory layout, dependencies, entry points, and framework-specific templates. Handles React (useApp hook), Vanilla JS, Vue, Svelte, Preact, and Solid.
mcp-csp-investigation
Comprehensive Content Security Policy audit for MCP Apps in sandboxed iframes. Discovers all network origins, traces them to source, and generates CSP configuration for registerAppResource.
frontmatter-parsing
YAML frontmatter parsing and manipulation for .planning/ documents. Provides read, write, update, query, and validation operations on frontmatter blocks in GSD markdown artifacts.