Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PramodDutta/qaskillsnpx agentmods add skills/pramoddutta/qaskills/devin-ai-testingWrote 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.
[](https://agentmods.dev/skills/pramoddutta/qaskills/devin-ai-testing)<a href="https://agentmods.dev/skills/pramoddutta/qaskills/devin-ai-testing"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/devin-ai-testing/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.
<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="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 374 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Anti-Refusal · line 532 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
- medium MCP Rug Pull · line 222 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 286 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 349 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 529 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.04555 |
| Opus 5.5 | $0.00017 | $0.01822 |
| Sonnet 5.5 | $0.00009 | $0.00911 |
| Haiku 4.5 | $0.00004 | $0.00456 |
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 1mo 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'; 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
- 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.
- Sandboxed execution -- Never run agent-generated code in production environments. Always execute in isolated sandboxes with limited permissions.
- Multi-layer validation -- Validate agent output at multiple levels: syntax checking, type checking, test execution, security scanning, and human review.
- Task specification clarity -- Autonomous agents are only as good as their task descriptions. Test that the agent correctly interprets ambiguous or incomplete specifications.
- Regression testing for agent behavior -- Track agent performance across versions. When the underlying model changes, verify that task completion quality does not degrade.
- Safety guardrails -- Implement hard limits on what agents can access, modify, and execute. Restrict file system access, network calls, and system commands.
- 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
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.
- 1mo ago First seen · 538 lines · 43 tokens per session scan A 6e08a9eb8670
Autonomous Agent Testing is a skill published in the GitHub repository PramodDutta/qaskills (238 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 4,555 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
gentle-ai-bench
Trigger: bench, journey, journeys, driven mode, gentle-ai-bench, journey corpus, j-numbers, bench axis. Author and verify gentle-ai bench journeys; go test ./bench never proves driven execution.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
write-tests
Write tests that pin real behavior instead of implementation details, config values, or lucky samples. Use when adding tests for new behavior, writing a regression test, fixing a brittle or flaky test, reviewing a test diff, or when a test breaks after a refactor or config change that didn't change behavior.
eval-skills
Eval and improve a skill against golden cases — run the target skill blind in a fresh, context-free subagent on each example input, grade the artifact against the expected outcome, and let the gaps drive the edits. Use when the user wants to test/eval/improve/harden a skill, says "this skill keeps producing X / keeps…
audit-tests
Audit whether tests earn their maintenance cost and which suite owns each contract. Use when pruning redundant tests, investigating implementation coupling or test-only production hooks, reviewing the value of proposed coverage, or auditing an entire subsystem. Use write-tests to implement the resulting test changes.
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.