What is agent-reliability?

A set of Claude skills for checking whether AI agents and machine-learning systems behave reliably in real use. It focuses on differences between testing results and production behavior, confidently wrong answers, and verified root causes.

Use it to examine agent or machine-learning failures, compare evaluation and production behavior, test answer reliability, and investigate causes with measured evidence.

An agent can appear correct in evaluations while failing in real projects. These checks help investigate whether failures come from the system, its tests, or its operating conditions.

agent-reliability — Plugin by ByteStack-Labs

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.

Claude Code

/plugin marketplace add ByteStack-Labs/claude-plugins

agentmods

npx agentmods add plugins/bytestack-labs/claude-plugins/agent-reliability

Clone the repo

git clone --depth 1 https://github.com/ByteStack-Labs/claude-plugins

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

agent-reliability 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.

agent-reliability/.claude-plugin/plugin.json · 13 lines

What it actually says

{
  "name": "agent-reliability",
  "description": "Claude skills for AI agent and ML reliability: reproduce the eval-to-production gap, catch confidently-wrong outputs, and prove root cause with verified numbers. Start with production-autopsy.",
  "version": "0.5.0",
  "author": {
    "name": "Jesse Moses (ByteStack Labs)"
  },
  "homepage": "https://bytestacklabs.com",
  "repository": "https://github.com/ByteStack-Labs/claude-plugins",
  "license": "MIT",
  "keywords": ["agents", "reliability", "evals", "production", "ml", "llm", "calibration", "diagnostics"]
}

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.

yesterday First seen · 13 lines scan A 03caf3b065b7

Subscribe to this mod's changes

agent-reliability is a plugin published in the GitHub repository ByteStack-Labs/claude-plugins (2 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

AI-reliability Data and AI Debugging Testing agent-reliability ai-agents ai-evals anthropic claude-code

agent-reliability

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

skillspec

skillspec

thumbgate-marketplace

thumbgate

codex-bridge

qualixar