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 agent-harnessgit 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/agent-harness)<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/agent-harness"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/agent-harness/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/agent-harness"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/agent-harness.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 | $0.00055 | $0.01143 |
| Opus 5.5 | $0.00022 | $0.00457 |
| Sonnet 5.5 | $0.00011 | $0.00229 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
agent-harness 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 7d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: agent-harness
Purpose
Build and run a structured agent harness — an outer loop that gives an LLM a defined set of tools (capabilities) and drives it to task completion. Based on the architecture from the OpenAI Agents SDK blog post: an Agent is a for-loop with an LLM running tools until done.
When to Use
- You need an agent that can take multi-step autonomous action on a complex task.
- You want to define explicit tool capabilities (shell, file I/O, search, etc.) and constrain the agent to them.
- You're building an internal coding agent, research agent, or workflow agent.
Architecture
┌─────────────────────────────────────────────┐
│ HARNESS │
│ │
│ ┌──────────┐ ┌────────────────────────┐ │
│ │ Task │───▶│ Agent Loop │ │
│ │ Input │ │ while not done: │ │
│ └──────────┘ │ action = LLM(state) │ │
│ │ result = tool(action)│ │
│ │ state.update(result) │ │
│ └────────────┬───────────┘ │
│ │ │
│ ┌────────────────────────────▼───────────┐ │
│ │ CAPABILITIES │ │
│ │ shell_exec | file_read | file_write │ │
│ │ web_search | sandboxed_exec | ... │ │
│ └────────────────────────────────────────┘ │
└─────────────────────────────────────────────┘
Key Concepts
| Term | Definition |
|---|---|
| Agent | LLM + tool loop running until a stop condition |
| Harness | The scaffolding around the agent: tools, state, loop control |
| Capability | A stateful, bound set of tools for a specific agent instance |
| Stop condition | Criteria that ends the loop: task_complete, max_steps, error |
| Sandbox | Isolated execution env — use sandboxed-exec skill |
Usage
@agent-harness
task: <what the agent should accomplish>
capabilities: [shell, file_read, file_write, search]
max_steps: <N, default 20>
sandbox: <true|false, default true>
stop_on: <task_complete|max_steps|first_success>
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.
- 7d ago Changed · +4 lines · +55 tokens per session 6c0285897e5c
- 1mo ago First seen · 130 lines · 0 tokens per session scan A dcf1c6e1251f
agent-harness is a skill published in the GitHub repository strikersam/autonomous-ai-agency (11 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 1,143 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
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…
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.
verification-suite
Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.
guardrails-ai-setup
Guardrails AI validation framework setup for LLM applications. Implement input/output validation, safety checks, and structured output enforcement.
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.