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/gongyijie85/dsh-eccnpx agentmods add skills/gongyijie85/dsh-ecc/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/gongyijie85/dsh-ecc/gan-style-harness)<a href="https://agentmods.dev/skills/gongyijie85/dsh-ecc/gan-style-harness"><img src="https://agentmods.dev/badge/skills/gongyijie85/dsh-ecc/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/gongyijie85/dsh-ecc/gan-style-harness"><img src="https://agentmods.dev/badge/skills/gongyijie85/dsh-ecc/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 | $0.00054 | $0.02890 |
| Opus 5 | $0.00027 | $0.01445 |
| Sonnet 5 | $0.00011 | $0.00578 |
| Haiku 4.5 | $0.00005 | $0.00289 |
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 8d 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
81% identical to gan-style-harness — 54 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 — 280 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 │
│ (Sonnet) │
└──────┬──────┘
│ Product Spec
│ (features, sprints, design direction)
▼
┌────────────────────────┐
│ │
│ GENERATOR-EVALUATOR │
│ FEEDBACK LOOP │
│ │
│ ┌──────────┐ │
│ │GENERATOR │--build-->│──┐
│ │ (Sonnet) │ │ │
│ └────▲─────┘ │ │
│ │ │ │ live app
│ feedback │ │
│ │ │ │
│ ┌────┴─────┐ │ │
│ │EVALUATOR │<-test----│──┘
│ │ (Sonnet) │ │
│ │+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.
- 8d ago First seen · 280 lines · 54 tokens per session scan A d91da8ca4a77
gan-style-harness is a skill published in the GitHub repository gongyijie85/dsh-ecc (7 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 2,890 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 81% identical to gan-style-harness, differing in 54 lines, and is treated as a copy.
Other skills, from other repositories
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…
dsh-plugin-guide
Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by…
investor-distiller
An analysis tool for studying investment bloggers on WeChat, a Chinese messaging and publishing platform. It collects their articles and builds a structured profile of their trading methods, market views, writing style, topics and audience interaction.
playlet-douyin-feed
A tool that tracks popular short dramas on Douyin, a Chinese short-video platform, and creates a daily HTML report with covers, engagement data, links, topic groups, and writing observations.
playlet-xhs-feed
A daily tracker for popular short-drama posts on Xiaohongshu, a Chinese social-media platform. It groups posts by story themes and creates an HTML report with covers, interaction data, links, and writing insights.
bilibili-search-download
A tool for searching Bilibili, a Chinese video-sharing site, by keyword and collecting download links for matching videos. It can sort and filter results and return video, audio and cover-image resources.