What is stelow-workflow-testing-ai-code?

A testing plan for software built with AI assistance. It uses a product specification to decide how broadly to test behavior, including cases that ordinary code checks may miss.

Use it during technical planning for software or hybrid products when an approved spec-product.md file defines the scope.

It helps catch unreliable AI-generated code, missing edge cases, security problems, and tests that only check isolated pieces. It also makes the expected testing scope explicit.

stelow-workflow-testing-ai-code — Skill for Claude Code and Codex by c

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 calionauta/stelow --skill stelow-workflow-testing-ai-code

Clone the repo

git clone --depth 1 https://github.com/calionauta/stelow

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/calionauta/stelow/stelow-workflow-testing-ai-code.svg)](https://agentmods.dev/skills/calionauta/stelow/stelow-workflow-testing-ai-code)

Your own site

<a href="https://agentmods.dev/skills/calionauta/stelow/stelow-workflow-testing-ai-code"><img src="https://agentmods.dev/badge/skills/calionauta/stelow/stelow-workflow-testing-ai-code.svg" alt="Measured on agentmods" height="20"></a>

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,760 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.

Model	Per session	Once invoked
Fable 5.1	$0.00104	$0.05760
Opus 5	$0.00052	$0.02880
Sonnet 5	$0.00021	$0.01152
Haiku 4.5	$0.00010	$0.00576

Measured 7d ago against content hash 40396392eb2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

stelow-workflow-testing-ai-code 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 7d 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/stelow-workflow-testing-ai-code/SKILL.md · 632 lines

How it starts

The opening of the file, as written. The whole thing — 632 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI-Aware Testing Strategy

Based on empirical research:

AgentAssay (2026): Non-deterministic agent testing framework

MSR 2026: Over-mocking anti-patterns in AI-generated tests

Veracode 2025: 45% of AI code contains vulnerabilities

CodeRabbit 2025: AI code has 1.7x more bugs than human code

CoderEval (2023): 43.1% of AI code is less robust

Standalone awareness: when inside stelow, triggered automatically by product_type in spec-product.md frontmatter. When standalone, invoke directly with a spec-product.md path. Appetite defaults to Core if not found — documented in output. All test-breadth tables and quality baselines work identically in both modes.

Activation

Trigger: product_type: software or product_type: hybrid in spec-product.md frontmatter
Phase: Phase 11 (Tech Planning)
Prerequisite: approved spec-product.md with scope defined

Step 2: Read Appetite and Product Context

Read appetite from spec-product.md before generating test scopes. When running standalone, appetite defaults to Core if not found in frontmatter — the skill documents this assumption in the output.

Appetite controls test breadth, not quality baseline.

Appetite	Test breadth
`Lean`	Behavior/E2E (1 happy path) + smoke tests + critical-path unit tests. Add integration only when an external seam is in scope.
`Core`	Behavior/E2E (happy path + variations) + unit tests for main logic + integration tests for DB/API/external seams.
`Complete`	Behavior/E2E (full coverage + edge cases) + unit + integration + security tests/scans.

Quality baseline applies to every appetite: build/test/lint/typecheck always run when available, and a11y checks run whenever UI files exist. Appetite changes exploration breadth, not whether quality gates exist.

Then determine the product context:

Before generating testing strategy, determine the product context:

Context	Description	Testing Approach
Greenfield	New product, no existing code	TDD-first, appetite-specific coverage targets, clean slate
Brownfield	Existing product with features	TDD for critical paths, test-after for existing code, regression focus
Hybrid	Adding features to existing product	Separate new from existing, protect invariants

Read the full file on GitHub · 632 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.

7d ago First seen · 632 lines · 104 tokens per session scan A 40396392eb2e

Subscribe to this mod's changes

stelow-workflow-testing-ai-code is a skill published in the GitHub repository calionauta/stelow (10 stars, last pushed yesterday), licensed MIT. It adds 104 tokens to every session and 5,760 once invoked, about $0.0005 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 2026-08-30.

Planning Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

stelow-workflow-testing-ai-code