ai-harness-review

ai-harness-review is a skill for Claude Code, Codex from nirhalfon/cinch-ai-security. It costs 54 tokens per session (1,045 once invoked), scanned A, original, CC-BY-4.0.

A skill for reviewing a project’s security safeguards around its AI harness, the code and controls that connect an AI model to tools and workflows. It checks documentation, constraints, tests, reviews, and AI-specific protections.

In plain words
What is it for?
Use it to review a repository or project and map its findings to NIST AI RMF, OWASP, CUSTODY, and LASM.
Why use it?
It helps identify missing or weak safeguards in the engineering process surrounding an AI system.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

Good fit Use it to review a repository or project and map its findings to NIST AI RMF, OWASP, CUSTODY, and LASM.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nirhalfon/cinch-ai-security/ai-harness-review
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 nirhalfon/cinch-ai-security --skill ai-harness-review
Clone the repo
git clone --depth 1 https://github.com/nirhalfon/cinch-ai-security

Made for: Claude Code, Codex.

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 ai-harness-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/nirhalfon/cinch-ai-security/ai-harness-review/github.svg)](https://agentmods.dev/skills/nirhalfon/cinch-ai-security/ai-harness-review)
Your own site
<a href="https://agentmods.dev/skills/nirhalfon/cinch-ai-security/ai-harness-review"><img src="https://agentmods.dev/badge/skills/nirhalfon/cinch-ai-security/ai-harness-review/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.

agentmods 80×15 button for ai-harness-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/nirhalfon/cinch-ai-security/ai-harness-review"><img src="https://agentmods.dev/badge/skills/nirhalfon/cinch-ai-security/ai-harness-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,045 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 unknown 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 $0.00054 $0.01045
Opus 5 $0.00027 $0.00522
Sonnet 5 $0.00011 $0.00209
Haiku 4.5 $0.00005 $0.00104

Measured 9d ago against content hash 65820306fce4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ai-harness-review 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 9d 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.

skills/ai-harness-review/SKILL.md · 102 lines

The source is not reproduced here

Licensed CC-BY-4.0

The repository is licensed CC-BY-4.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 9d ago First seen · 102 lines · 54 tokens per session scan A 65820306fce4

Subscribe to this mod's changes

ai-harness-review is a skill published in the GitHub repository nirhalfon/cinch-ai-security (0 stars, last pushed 1mo ago), licensed CC-BY-4.0. It adds 54 tokens to every session and 1,045 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

integrate-arcjet-guard-genkit

Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…

arcjet/arcjet-js · 89 tokens

integrate-arcjet-guard-langgraph

Integrate Arcjet security into a LangGraph Graph API agent using @arcjet/guard — wrap tool() / StructuredTool, wrap ToolNode for unwrapped MCP tools, and read threadid for correlation. Use when asked to add Arcjet to a LangGraph StateGraph / ToolNode agent, rate limit its tools, screen inbound messages, or block…

arcjet/arcjet-js · 87 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-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-tanstack-ai

Integrate Arcjet security into a TanStack AI chat() app using @arcjet/guard — put guardMiddleware first on chat({ middleware }) so onBeforeToolCall gates tools, and read a caller-owned id from chat({ context }). Use when asked to add Arcjet to TanStack AI, rate limit its tools, screen inbound messages, or block prompt…

arcjet/arcjet-js · 103 tokens

release-pr-review

Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…

cyanheads/obsidian-mcp-server · 139 tokens