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/majiang213/OpenClaw-MASnpx agentmods add skills/majiang213/openclaw-mas/gan-style-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/majiang213/openclaw-mas/gan-style-harness)<a href="https://agentmods.dev/skills/majiang213/openclaw-mas/gan-style-harness"><img src="https://agentmods.dev/badge/skills/majiang213/openclaw-mas/gan-style-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/majiang213/openclaw-mas/gan-style-harness"><img src="https://agentmods.dev/badge/skills/majiang213/openclaw-mas/gan-style-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 | $0.00033 | $0.02847 |
| Opus 5 | $0.00016 | $0.01424 |
| Sonnet 5 | $0.00007 | $0.00569 |
| Haiku 4.5 | $0.00003 | $0.00285 |
Grade A, and why
gan-style-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.
This is a copy
92% identical to gan-style-harness — 27 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GAN-Style Harness Skill
Inspired by Anthropic's Harness Design for Long-Running Application Development (March 24, 2026)
A multi-agent harness that separates generation from evaluation, creating an adversarial feedback loop that drives quality far beyond what a single agent can achieve.
Core Insight
When asked to evaluate their own work, agents are pathological optimists — they praise mediocre output and talk themselves out of legitimate issues. But engineering a separate evaluator to be ruthlessly strict is far more tractable than teaching a generator to self-critique.
This is the same dynamic as GANs (Generative Adversarial Networks): the Generator produces, the Evaluator critiques, and that feedback drives the next iteration.
When to Use
- Building complete applications from a one-line prompt
- Frontend design tasks requiring high visual quality
- Full-stack projects that need working features, not just code
- Any task where "AI slop" aesthetics are unacceptable
- Projects where you want to invest $50-200 for production-quality output
When NOT to Use
- Quick single-file fixes (use standard
claude -p) - Tasks with tight budget constraints (<$10)
- Simple refactoring (use de-sloppify pattern instead)
- Tasks that are already well-specified with tests (use TDD workflow)
Architecture
┌─────────────┐
│ PLANNER │
│ (Opus 4.6) │
└──────┬──────┘
│ Product Spec
│ (features, sprints, design direction)
▼
┌────────────────────────┐
│ │
│ GENERATOR-EVALUATOR │
│ FEEDBACK LOOP │
│ │
│ ┌──────────┐ │
│ │GENERATOR │--build-->│──┐
│ │(Opus 4.6)│ │ │
│ └────▲─────┘ │ │
│ │ │ │ live app
│ feedback │ │
│ │ │ │
│ ┌────┴─────┐ │ │
│ │EVALUATOR │<-test----│──┘
│ │(Opus 4.6)│ │
│ │+Playwright│ │
│ └──────────┘ │
│ │
│ 5-15 iterations │
└────────────────────────┘
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 First seen · 279 lines · 33 tokens per session scan A 2ce1e3d2579e
gan-style-harness is a skill published in the GitHub repository majiang213/OpenClaw-MAS (5 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 2,847 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to gan-style-harness, differing in 27 lines, and is treated as a copy.
Other skills, from other repositories
sequence-diagram
Show interactions and flows over time. Illustrate request paths, asynchronous patterns, error handling. Use when documenting complex flows or onboarding on system behavior.
architecture-anti-patterns
Identify and avoid common architectural mistakes. Recognize patterns of failure. Use when reviewing designs or learning from mistakes.
architecture-patterns-catalog
Reference catalog of proven architecture patterns. Know when to apply each pattern, tradeoffs, and examples. Use as reference when designing systems.
system-audit
Conduct comprehensive system architecture evaluation. Assess design quality, technical debt, operational readiness, scalability. Use when auditing existing systems.
storage-selection
Choose the right database technology for specific workloads. Evaluate relational, NoSQL, data warehouses, and search engines. Use when selecting storage systems for new features or optimizing existing ones.
architecture-review-facilitation
Lead effective architecture reviews. Manage discussions, surface disagreements, build consensus, document decisions. Use when conducting reviews or running architecture forums.