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 lucianghinda/agentic-skills --skill improving-testinggit clone --depth 1 https://github.com/lucianghinda/agentic-skillsWrote 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/lucianghinda/agentic-skills/improving-testing)<a href="https://agentmods.dev/skills/lucianghinda/agentic-skills/improving-testing"><img src="https://agentmods.dev/badge/skills/lucianghinda/agentic-skills/improving-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/lucianghinda/agentic-skills/improving-testing"><img src="https://agentmods.dev/badge/skills/lucianghinda/agentic-skills/improving-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00070 | $0.01594 |
| Opus 5 | $0.00035 | $0.00797 |
| Sonnet 5 | $0.00014 | $0.00319 |
| Haiku 4.5 | $0.00007 | $0.00159 |
Grade A, and why
improving-testing 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improving Testing
When to Use
Use when user asks:
- "What should I test for this feature?"
- "How do I test edge cases?"
- "Review my tests"
- "What cases am I missing?"
- "Help me pick test cases"
- "How to test validation/permissions/state machines?"
Do NOT Use When
- User wants to run existing tests (use terminal)
- User wants test code generation without design planning
- User asks about test framework setup or tooling
- User asks about CI/CD pipeline configuration
Inputs (ask if missing)
- Feature in one sentence
- Biggest risks (user harm, money, trust, security)
- Inputs and constraints (types, ranges, formats)
- Roles and permissions
- States and transitions
If unknown, assume and state assumptions.
Workflow
Step 1: Define the goal
Pick the primary goal:
- Verify requirement
- Document behavior
- Prevent regressions in risky areas
Step 2: Identify risks
List 3 to 7 risks. Prefer:
- Permissions, security, privacy
- Money and data integrity
- Complex branching logic
- Stateful behavior
- Boundary and validation failures
Step 3: Design cases before writing tests
Pick the technique that matches the problem:
- Equivalence classes: representative per group
- Boundary values: min, max, just below, just above
- Decision table: combinations of conditions
- State transitions: allowed and forbidden transitions
For each rule, include:
- One positive case
- One negative case
- One edge case (boundary, empty, null, max length, weird chars)
Write each test idea as:
- Preconditions
- Inputs
- Action
- Expected result (oracle)
Step 4: Plan test data
For each case, define representative data:
- One value per equivalence class
- Boundary values for ranges and lengths
- Clearly named examples (avoid random data)
Step 5: Review and harden the tests
Check each test for:
- Correctness: matches requirement and risk
- Strength: fails for the right reason
- Relevance: covers risky paths, not only happy path
- Determinism: no time, randomness, network, ordering leaks
- Maintainability: clear setup, focused assertions, minimal noise
- Gaps: which risks have zero tests?
- Redundancy: which tests repeat the same behavior?
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.
- 9d ago First seen · 231 lines · 70 tokens per session scan A 76a17eaf4d7c
improving-testing is a skill published in the GitHub repository lucianghinda/agentic-skills (5 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,594 once invoked, about $0.0003 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 2026-08-31.
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.