Autonomous Agent Testing

Autonomous Agent Testing is a skill for Claude Code, Codex from PramodDutta/qaskills. It costs 43 tokens per session (4,555 once invoked), scanned A, original, MIT.

A testing guide for autonomous AI coding agents, which are systems that can plan and change code with limited supervision. It checks the agent's output, runs it in an isolated sandbox, and adds security, regression, and human-review safeguards.

In plain words
What is it for?
Use it to validate AI-generated code, build agent verification pipelines, test behavior across model changes, and enforce safe execution boundaries.
Why use it?
An agent can produce code that looks plausible but fails requirements or creates security risks. These checks verify the result across syntax, types, tests, security, and task completion.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/pramoddutta/qaskills/devin-ai-testing
Any agent
npx skills add PramodDutta/qaskills --skill devin-ai-testing
Clone the repo
git clone --depth 1 https://github.com/PramodDutta/qaskills

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 Autonomous Agent Testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/pramoddutta/qaskills/devin-ai-testing.svg)](https://agentmods.dev/skills/pramoddutta/qaskills/devin-ai-testing)
Your own site
<a href="https://agentmods.dev/skills/pramoddutta/qaskills/devin-ai-testing"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/devin-ai-testing.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,555 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00043 $0.04555
Opus 5 $0.00022 $0.02278
Sonnet 5 $0.00009 $0.00911
Haiku 4.5 $0.00004 $0.00456

Measured 2d ago against content hash 6e08a9eb8670, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

Autonomous Agent Testing scanned grade A with 1 finding 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 2d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

import { execSync } from 'child_process';
seed-skills/devin-ai-testing/SKILL.md · 538 lines

How it starts

The opening of the file, as written. The whole thing — 538 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autonomous Agent Testing Skill

You are an expert in testing autonomous AI coding agents. When the user asks you to validate autonomous agent output, build verification pipelines for AI-generated code, implement safety guardrails, or test agent task completion, follow these detailed instructions.

Core Principles

  1. Output verification over process observation -- Test what the agent produced (code, tests, configurations), not how it produced it. The output must meet specifications regardless of the generation process.
  2. Sandboxed execution -- Never run agent-generated code in production environments. Always execute in isolated sandboxes with limited permissions.
  3. Multi-layer validation -- Validate agent output at multiple levels: syntax checking, type checking, test execution, security scanning, and human review.
  4. Task specification clarity -- Autonomous agents are only as good as their task descriptions. Test that the agent correctly interprets ambiguous or incomplete specifications.
  5. Regression testing for agent behavior -- Track agent performance across versions. When the underlying model changes, verify that task completion quality does not degrade.
  6. Safety guardrails -- Implement hard limits on what agents can access, modify, and execute. Restrict file system access, network calls, and system commands.
  7. Determinism where possible -- For reproducible testing, pin agent model versions, temperature settings, and random seeds to reduce output variability.

Project Structure

agent-testing/
  tasks/
    definitions/
      simple-function.task.yaml
      api-endpoint.task.yaml
      bug-fix.task.yaml
      refactoring.task.yaml
      test-writing.task.yaml
    expected-outputs/
      simple-function/
        expected-code.ts
        expected-tests.ts
      api-endpoint/
        expected-route.ts
        expected-handler.ts
  validators/
    syntax-validator.ts
    type-validator.ts
    test-runner-validator.ts
    security-scanner.ts
    style-validator.ts
    output-comparator.ts
  sandbox/
    docker-sandbox.ts
    permission-manager.ts
    resource-limiter.ts
    network-policy.ts
  runners/
    task-runner.ts
    batch-runner.ts
    regression-runner.ts
  safety/
    guardrails.ts
    file-access-policy.ts
    command-allowlist.ts
    secret-detector.ts
  metrics/
    task-completion-tracker.ts
    quality-scorer.ts
    cost-tracker.ts
  reports/
    agent-report.ts
    comparison-report.ts
  config/
    agent-config.ts
    sandbox-config.ts

Read the full file on GitHub · 538 lines

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. 2d ago First seen · 538 lines · 43 tokens per session scan A 6e08a9eb8670

Subscribe to this mod's changes

Autonomous Agent Testing is a skill published in the GitHub repository PramodDutta/qaskills (217 stars, last pushed 6d ago), licensed MIT. It adds 43 tokens to every session and 4,555 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.