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 agentmods add skills/jamkris/everything-gemini-code/gan-style-harnessnpx skills add Jamkris/everything-gemini-code --skill gan-style-harnessgit clone --depth 1 https://github.com/Jamkris/everything-gemini-codeWrote 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/jamkris/everything-gemini-code/gan-style-harness)<a href="https://agentmods.dev/skills/jamkris/everything-gemini-code/gan-style-harness"><img src="https://agentmods.dev/badge/skills/jamkris/everything-gemini-code/gan-style-harness.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 | $0.00033 | $0.02843 |
| Opus 5 | $0.00016 | $0.01422 |
| Sonnet 5 | $0.00007 | $0.00569 |
| Haiku 4.5 | $0.00003 | $0.00284 |
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 yesterday.
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
94% identical to gan-style-harness — 41 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
gemini -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.
- yesterday First seen · 279 lines · 33 tokens per session scan A 59625eb8490e
gan-style-harness is a skill published in the GitHub repository Jamkris/everything-gemini-code (87 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 2,843 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to gan-style-harness, differing in 41 lines, and is treated as a copy.
Other skills, from other repositories
looker
These skills are designed for data discovery and business intelligence.
looker-dev
These skills are built for LookML developers, data engineers, and administrators who manage the backbone of Looker.
cloud-sql-postgres-health
Use these skills when you need to audit database health, identify storage bloat, find invalid indexes, analyze table statistics, and manage maintenance configurations like autovacuum.
cloud-sql-postgres-vectorassist
Use these skills to set up and optimize production-ready vector workloads by simply expressing your intent and performance requirements.
cloud-sql-postgres-data
Use these skills when you need to explore the database structure, discover schema objects like views or stored procedures, and execute custom SQL queries to interact with your data.
cloud-sql-postgres-admin
Use these skills when you need to provision new Cloud SQL instances, create databases and users, clone existing environments, and monitor the progress of long-running operations.