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 reidemeister94/development-skills --skill create-testgit clone --depth 1 https://github.com/reidemeister94/development-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/reidemeister94/development-skills/create-test)<a href="https://agentmods.dev/skills/reidemeister94/development-skills/create-test"><img src="https://agentmods.dev/badge/skills/reidemeister94/development-skills/create-test/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/reidemeister94/development-skills/create-test"><img src="https://agentmods.dev/badge/skills/reidemeister94/development-skills/create-test.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 | $0.00029 | $0.00673 |
| Opus 5.5 | $0.00012 | $0.00269 |
| Sonnet 5.5 | $0.00006 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
create-test 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 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.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create test
Start with the user need or business rule that must always hold, not files, coverage, or internal calls. Inspect for facts; ask only for business decisions that cannot be discovered.
Define the regression contract
Establish:
- actors, goals, and externally observable outcomes;
- business rules and invariants that must never change;
- critical paths and relevant rejection, timeout, retry, permission, concurrency, and partial-failure cases;
- the current baseline and every intended behavior change;
- KPIs with window, data set, acceptable variance, and justified pass or fail threshold;
- systems crossed, production-like data needs, and evidence the available environment can provide.
Never invent a metric or threshold; record the gap. Match the proof's inputs and environment to the context it claims to model. A subprocess that represents normal runtime must not inherit test-only environment variables.
Choose the proof
Prefer the highest reliable boundary:
- black-box tests through the public API, UI, job, event, or CLI;
- deep integration with the real database, queue, connector, or protocol;
- contract, replay, property, or characterization tests for narrower risks;
- unit tests for isolated rules where a wider test adds no confidence.
Mock only beyond the verified boundary. For database or migration work, read integration patterns. When proving a process manager, worker, container entrypoint, or deployed artifact, use the real container or operating-system image. Verify worker replacement, signal handling, and graceful shutdown only when those boundaries apply.
For strategy or audit only, return the contract, prioritized scenarios, proof method, and blind spots. Judge tests by failures caught, not assertion or coverage counts. Ask which states the proof covers and whether it includes the most fragile states.
Prove a refactor differently
A refactor keeps behavior. Capture a characterization baseline and observe it green on the unchanged code and after the refactor. Never break working behavior to watch a refactor test fail. If the baseline cannot run, name what is missing instead of lowering the proof standard.
What ships with it
1 file 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.
- 1mo ago Changed · +23 lines 76cb7a968848
- 1mo ago First seen · 45 lines · 29 tokens per session scan A 9086b09d490f
create-test is a skill published in the GitHub repository reidemeister94/development-skills (12 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 673 once invoked, about $0.0001 per session on Opus 5.5. 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
mutation-test
Mutation testing with two engines. Uses the project's NATIVE mutation runner (StrykerJS / Infection / mutmut / PIT / cargo-mutants) when one is configured — installing it on explicit consent when it is not — for a reproducible, comparable score; and an LLM-guided engine for the mutation classes native mutators cannot…
write-tests
Write tests for existing production code. Processes ONE file at a time through a full pipeline: analyze, inventory (frozen BEFORE writing), write, executable coverage gate, verify, blind coverage audit, adversarial review, log. Uses CodeSift for discovery and analysis when available. Modes: [path] (specific target)…
code-audit
Batch audit of production files against CQ1-CQ40 quality gates and CAP1-CAP29 anti-patterns. Tiered output (A/B/C/D), critical gate enforcement, evidence-backed scoring, cross-file pattern analysis, and prioritized execution plan. Flags: zuvo:code-audit all | [path] | [file] | --deep | --quick | --services |…
pentest
Hybrid white-box + black-box penetration testing across 7 dimensions (PT1-PT7). Stack-aware source-to-sink tracing, exploit verification, CMS overlay, and deterministic finding aggregation. Uses explicit candidate schemas, canonical-key deduplication, score caps, and MUST-GATE enforcement. Flags: zuvo:pentest [path] |…
plan
Analyzes architecture, selects patterns, assesses testability, then decomposes work into ordered TDD tasks with exact verification commands and explicit acceptance mapping. Works from an approved spec (zuvo:brainstorm output) or directly from a user-provided description.
api-audit
API and endpoint integrity audit across 10 dimensions (D1-D10) plus optional contract stability (D11) and optional OWASP API Security Top 10 (D12: BOLA/BOPLA/BFLA, mass assignment, JWT alg-confusion, GraphQL introspection). Covers validation, payloads, pagination, errors, caching, HTTP semantics, waterfalls, rate…