gauntlex:run

gauntlex:run is a skill for Claude Code from sanjoy1234/gauntlex. It costs 56 tokens per session (509 once invoked), scanned A, original, MIT.

A GAUNTLEX command that tests a specification or GitHub issue with generated adversarial attacks. It produces an Adversarial Resilience Score and a report showing which attacks were mitigated.

In plain words
What is it for?
Use it with a specification file or GitHub issue URL, choosing quick, standard, or thorough testing and an optional OWASP Top 10 policy domain. It saves JSON and Markdown reports in the project.
Why use it?
It provides a repeatable way to look for weaknesses in proposed code or requirements and identify attacks that the system does not handle.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Part of the gauntlex plugin — 7 skills, 1 MCP server shipped together

Good fit Use it with a specification file or GitHub issue URL, choosing quick…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sanjoy1234/gauntlex/run
Install

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.

Any agent
npx skills add sanjoy1234/gauntlex --skill run
Clone the repo
git clone --depth 1 https://github.com/sanjoy1234/gauntlex

Made for: Claude Code.

Or install gauntlex, the plugin that ships this one along with the rest of its 7 skills, 1 MCP server.

Wrote 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.

agentmods badge for gauntlex:run

README.md
[![agentmods](https://agentmods.dev/badge/skills/sanjoy1234/gauntlex/run.svg)](https://agentmods.dev/skills/sanjoy1234/gauntlex/run)
Your own site
<a href="https://agentmods.dev/skills/sanjoy1234/gauntlex/run"><img src="https://agentmods.dev/badge/skills/sanjoy1234/gauntlex/run.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 509 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.00509
Opus 5 $0.00028 $0.00254
Sonnet 5 $0.00011 $0.00102
Haiku 4.5 $0.00006 $0.00051

Measured 6d ago against content hash 674c0b5dd0c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

gauntlex:run 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 6d 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.

.claude/skills/gauntlex/run/SKILL.md · 53 lines

What it actually says

/gauntlex:run

Runs a full Gauntlex session on a specification or GitHub issue.

Usage

/gauntlex:run [--issue <url|file>] [--mode quick|standard|thorough] [--domain owasp_top10]

Execution

This skill invokes the installed gauntlex CLI. Run:

gauntlex run --issue "$ISSUE" --mode "$MODE" --domain "$DOMAIN"

Where:

  • $ISSUE = the spec file path or GitHub issue URL from the user's message
  • $MODE = quick (default, 5 attacks, <90s), standard (20 attacks), thorough (50 attacks)
  • $DOMAIN = policy domain (default owasp_top10)

What It Does

  1. Loads .gauntlex.yml from the current working directory (or defaults if not present)
  2. Runs Builder and Breaker concurrently via asyncio.gather()
  3. Arbiter scores each attack: 1.0 (mitigated) / 0.5 (partial) / 0.0 (miss)
  4. Emits Resilience Report JSON + Markdown to .gauntlex/reports/<run_id>.json
  5. Returns ARS score and a table of attacks

Output to User

After running, report:

  • ARS score (e.g., ARS: 0.87)
  • Number of attacks attempted and how many were mitigated
  • Top 3 unmitigated attacks (if any)
  • Report saved to .gauntlex/reports/<run_id>.json
  • Whether the gate passed or failed (vs minimum_ars in .gauntlex.yml)

Checking prerequisites

Before running, verify:

  1. gauntlex doctor passes (model reachable, ChromaDB writable)
  2. .gauntlex.yml exists or inform user defaults will be used

If gauntlex is not installed: pip install -e <project_root> or pip install gauntlex-ai

Changes

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.

  1. 6d ago First seen · 53 lines · 56 tokens per session scan A 674c0b5dd0c3

Subscribe to this mod's changes

gauntlex:run is a skill published in the GitHub repository sanjoy1234/gauntlex (1 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 509 once invoked, about $0.0003 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

prodcheck-review

Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations and post-launch readiness. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line citations…

FarzamHabibi/pre-production-checklist · 70 tokens

integrate-arcjet-guard-google-adk

Integrate Arcjet security into a Google ADK JS app using @arcjet/guard — put guardPlugin first on Runner({ plugins }) so beforeToolCallback gates tools, and read a caller-owned id from helper options or context. Use when asked to add Arcjet to Google ADK, @google/adk, rate limit its tools, screen inbound messages, or…

arcjet/arcjet-js · 111 tokens

integrate-arcjet-guard-mastra

Integrate Arcjet security into a Mastra agent using @arcjet/guard — wrap createTool execute, screen input/output with a Processor tripwire, and gate unwrapped MCP/workspace tools with hooks. Use when asked to add Arcjet to a Mastra agent, rate limit its tools, screen inbound messages, or block prompt injection / PII.

arcjet/arcjet-js · 82 tokens

integrate-arcjet-guard-claude-managed-agents

Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…

arcjet/arcjet-js · 102 tokens

adr-skill

Create and maintain Architecture Decision Records (ADRs) optimized for agentic coding workflows. Use when you need to propose, write, update, accept/reject, deprecate, or supersede an ADR; bootstrap an adr folder and index; consult existing ADRs before implementing changes; or enforce ADR conventions. This skill uses…

Agent-Threat-Rule/agent-threat-rules · 89 tokens

terraform-skill

Terraform infrastructure as code best practices.

Agent-Threat-Rule/agent-threat-rules · 10 tokens