Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/aiappsgbb/awesome-gbbnpx agentmods add skills/aiappsgbb/awesome-gbb/agent-framework-harnessWrote 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/aiappsgbb/awesome-gbb/agent-framework-harness)<a href="https://agentmods.dev/skills/aiappsgbb/awesome-gbb/agent-framework-harness"><img src="https://agentmods.dev/badge/skills/aiappsgbb/awesome-gbb/agent-framework-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/aiappsgbb/awesome-gbb/agent-framework-harness"><img src="https://agentmods.dev/badge/skills/aiappsgbb/awesome-gbb/agent-framework-harness.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00201 | $0.05169 |
| Opus 5.5 | $0.00080 | $0.02068 |
| Sonnet 5.5 | $0.00040 | $0.01034 |
| Haiku 4.5 | $0.00020 | $0.00517 |
Grade A, and why
agent-framework-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 1mo 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quick decision table
| Need | Owner |
|---|---|
Compose a Microsoft Agent Framework Agent with Harness providers, middleware, modes, todos, compaction, recovery, approval UX, or opt-in executors |
agent-framework-harness |
| Deploy, authorize, containerize, roll out, or operate a hosted agent | foundry-hosted-agents |
| Enforce deterministic authorization, policy, audit, or governance | foundry-agt |
| Publish or consume centrally distributed skills through Foundry Skills REST | foundry-skill-catalog |
| Design evaluations or scoring | foundry-evals |
Agent Harness is runtime scaffolding, not hosting. Native approval provides interactive UX and session-backed standing-rule convenience; it is not non-bypassable policy. ResponsesHostServer adapts an existing Agent and does not create the Harness composition.
This skill excludes deployment, RBAC, identity grants, containers, registries, azure.yaml, rollout, service lifecycle, deterministic governance, audit ownership, sandbox ownership, Foundry Skills REST distribution, and general evaluation design.
Architecture and internal factory pipeline
create_harness_agent returns a normal Agent Framework Agent around any compatible chat client. Preserve this exact context-provider order:
- history;
- optional after-call
CompactionProvider; - todo;
AgentModeProvider;FileMemoryProvider;- optional
FileAccessProvider; - optional
SkillsProvider; - optional
BackgroundAgentsProvider; - optional shell provider;
- caller context providers.
Before-call compaction is not a context provider: it is attached to agent.compaction_strategy. When both token budgets create the shared strategy, the factory assembles the before-call strategy and after-call CompactionProvider phases together.
Preserve this tool order:
- conditional web-search tool when the client implements
SupportsWebSearchTooland web search is not disabled; - optional shell tool when
shell_executoris supplied and the client implementsSupportsShellTool; - caller-supplied tools.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/python/hosted_harness.py 1.8 KB runs code
- references/python/local_harness.py 1.4 KB runs code
- references/python/plan_execute.py 3.6 KB runs code
- references/python/session_recovery.py 676 B runs code
- references/python/test_harness_contract.py 15 KB runs code
- references/upstream-pin.md 7.8 KB
- test-fixture/consumer_prompt.md 2.3 KB
- test-fixture/live_smoke.py 8.6 KB runs code
- test-fixture/requirements.txt 247 B
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.
- 1mo ago First seen · 242 lines · 201 tokens per session scan A f8415e9adead
agent-framework-harness is a skill published in the GitHub repository aiappsgbb/awesome-gbb (8 stars, last pushed yesterday), licensed MIT. It adds 201 tokens to every session and 5,169 once invoked, about $0.0008 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 2026-09-15.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…