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.
npx skills add lexler/skill-factory --skill bdd-with-approvalsgit clone --depth 1 https://github.com/lexler/skill-factoryWrote 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/lexler/skill-factory/bdd-with-approvals)<a href="https://agentmods.dev/skills/lexler/skill-factory/bdd-with-approvals"><img src="https://agentmods.dev/badge/skills/lexler/skill-factory/bdd-with-approvals/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/lexler/skill-factory/bdd-with-approvals"><img src="https://agentmods.dev/badge/skills/lexler/skill-factory/bdd-with-approvals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00023 | $0.00598 |
| Opus 5 | $0.00012 | $0.00299 |
| Sonnet 5 | $0.00005 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
bdd-with-approvals 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 11d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- bdd-with-approvals — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BDD with Approval Tests
The Problem
Specifications live in documents. They drift from reality because nothing enforces them.
Tests verify implementation. Written after code, they document what IS, not what SHOULD BE. They're noisy. You can't glance at them and quickly validate correctness.
You need an artifact that:
- Captures expected behavior before code exists
- Stays in sync because it's executable
- A human can validate at a glance
Executable Specifications
The fixture file IS that artifact. Write it BEFORE implementation.
Think through scenarios by creating approval files. Describe expected behavior in domain language. Implementation is driven by making these specs pass. Specs stay executable, never go stale.
A human looks at the fixture and immediately sees: correct or not. No translation between "spec" and "test". They're the same artifact.
For the approval testing technique itself (verify, scrubbers, combinations), see /approval-tests. For nulled infrastructure in system tests, see /nullables.
Approved Fixtures
Test files combining input and expected output in a format designed for human validation.
## Input
(context, parameters, initial state)
## Output
(expected results, side effects, final state)
Test runner reads fixtures, executes code, compares output. Adding test cases = adding files, not code.
Design the format for YOUR domain:
- Grid/spatial problems → ASCII art
- Transformations → before/after
- Workflows → step sequences with results
- API interactions → request/response pairs
See references/approved-fixtures.md for examples.
Format Design
The question: Can someone validate correctness in <5 seconds?
Design for human eyes, not machine parsing. Match the domain's natural representation. How you'd explain it on a whiteboard.
What makes formats scannable:
- Columnar layouts with visual alignment
- Consistent structure across all cases
- Whitespace that groups related elements
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 83 lines · 23 tokens per session scan A 8087b2d41cb3
bdd-with-approvals is a skill published in the GitHub repository lexler/skill-factory (234 stars, last pushed 15d ago), licensed Apache-2.0. It adds 23 tokens to every session and 598 once invoked, about $0.0001 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.
Other skills, from other repositories
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.
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".
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…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.