adversarial-gate SKILL.md skillA

adversarial-gate from jpantsjoha/ai-native-developer-experience is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add jpantsjoha/ai-native-developer-experience/adversarial-gate@git:20260807.c64e31f

Pins git:20260807.c64e31f in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
jpantsjoha/ai-native-developer-experience
Path
skills/adversarial-gate/SKILL.md
Versions recorded
1
Latest version
git:20260807.c64e31f, committed Aug 7, 2026
Size
3,750 bytes
Repository stars
13
License
Apache-2.0

JP's signature red-team pass — "how would I break this?" Argue against your own approach before proceeding. Trigger on any high-stakes decision, architecture choice, or before marking work complete.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Adversarial Gate

> **Coined by Jaroslav Pantsjoha (#HarnessEngineering).** The Adversarial Gate is the practice of forcing an agent — or a human — to argue against their own design before proceeding. It pre-empts bad reasoning before bad output exists.

The gate has one question: **"How would I break this?"**

Answer it honestly. If you cannot name at least two plausible failure modes, you do not understand the system well enough to ship it.

## When to use

- Before finalising any architecture or design decision
- Before a deployment or release
- When an agent is about to take an irreversible action
- When a design looks clean and elegant (danger signal — simple-looking systems hide the hard failure modes)
- When the team is under time pressure and "just shipping it" feels compelling

## Procedure

1. **State the proposal clearly** — in one or two sentences, what is the approach being validated?
2. **Run the adversarial pass** — argue against it. Ask:
   - What is the single most likely way this fails in production?
   - What happens under load / at scale / with bad input?
   - What is the blast radius if this fails? Is it recoverable?
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jpantsjoha/ai-native-developer-experience/adversarial-gate@sha256:609c9fb6431dd934

The line at the top of this page pins the label git:20260807.c64e31f, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_dhailavaghiqvuav.svg)](https://markdownregistry.com/a/art_dhailavaghiqvuav)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Aug 7, 2026.

versioncommittedcommitsizeaudit
git:20260807.c64e31f latest2026-08-07 c64e31f 3,750 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3750 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

jpantsjoha/ai-native-developer-experience · 13 stars · license Apache-2.0 · pushed 2026-10-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_dhailavaghiqvuav
GET https://markdownregistry.com/api/v1/resolve?ref=jpantsjoha/ai-native-developer-experience/adversarial-gate
GET https://markdownregistry.com/api/v1/blob/609c9fb6431dd93402671975fccf9e7e1bc0875c031166078bd71afb05ab7201

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from jpantsjoha/ai-native-developer-experience

AGENTS.md AGENTS.md file
jpantsjoha/ai-native-developer-experience · AGENTS.md
git:20261016.e93069b · audit A · 13 stars
CLAUDE.md CLAUDE.md file
jpantsjoha/ai-native-developer-experience · CLAUDE.md
git:20261016.e93069b · audit A · 13 stars
adk-expert SKILL.md skill
jpantsjoha/ai-native-developer-experience · skills/adk-expert/SKILL.md · Google ADK (Agent Development Kit) orchestration patterns — boundaries, agent composition, and tool seams. Trigger when…
git:20260807.c64e31f · audit A · 13 stars
cloud-checkup SKILL.md skill
jpantsjoha/ai-native-developer-experience · skills/cloud-checkup/SKILL.md · Read-only SRE checkup of any GCP project: deterministic probes of the edge, Cloud Run services, 7-day error logs, Cloud…
git:20260914.1704508 · audit A · 13 stars
cloud-expert SKILL.md skill
jpantsjoha/ai-native-developer-experience · skills/cloud-expert/SKILL.md · Cloud guardrails for any vendor workload — Google Cloud (GCP, Vertex AI, GKE), AWS (IAM, EKS, Bedrock), Azure (Entra…
git:20260914.d9753e2 · audit A · 13 stars
cost-guardrail SKILL.md skill
jpantsjoha/ai-native-developer-experience · skills/cost-guardrail/SKILL.md · LLM and cloud cost awareness — model tiering, token budgets, right-sizing, and when a cheaper model suffices. Trigger…
git:20261016.9a80630 · audit A · 13 stars
cxo-oversight SKILL.md skill
jpantsjoha/ai-native-developer-experience · skills/cxo-oversight/SKILL.md · Challenge vision alignment, value, cost, risk and operating ownership at material scope or release decisions.
git:20261016.e93069b · audit A · 13 stars
delivery-orchestrator SKILL.md skill
jpantsjoha/ai-native-developer-experience · skills/delivery-orchestrator/SKILL.md · Decompose an epic into atomic parallelizable tasks, route each to the right skill, and keep the four delivery records…
git:20261016.e93069b · audit A · 13 stars
domain-validator SKILL.md skill
jpantsjoha/ai-native-developer-experience · skills/domain-validator/SKILL.md · Validate agent output against declared domain rules and ground truth before trusting it downstream. Trigger after any…
git:20260807.c64e31f · audit A · 13 stars
frontend-performance-audit SKILL.md skill
jpantsjoha/ai-native-developer-experience · skills/frontend-performance-audit/SKILL.md · Measure real frontend performance — Core Web Vitals (LCP, CLS, INP), page-load traces, CPU and network throttling…
git:20260914.0883cff · audit B · 13 stars
get-it-done SKILL.md skill
jpantsjoha/ai-native-developer-experience · skills/get-it-done/SKILL.md · Pursue an agreed goal to a working outcome without waiting: decompose it, re-prioritise as evidence arrives, branch…
git:20261016.e93069b · audit A · 13 stars
github-manager SKILL.md skill
jpantsjoha/ai-native-developer-experience · skills/github-manager/SKILL.md · Use when configuring or optimising GitHub repositories for cost-effective, consistent operations — CI triggers, Actions…
git:20261002.c547def · audit A · 13 stars

Every file in jpantsjoha/ai-native-developer-experience

Browse by kind, by grade A, or by owner.