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 agentmods add skills/naver/fixture-monkey/write-fixturenpx skills add naver/fixture-monkey --skill write-fixturegit clone --depth 1 https://github.com/naver/fixture-monkeyWhat 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 | $0.00042 | $0.07735 |
| Opus 5 | $0.00021 | $0.03868 |
| Sonnet 5 | $0.00008 | $0.01547 |
| Haiku 4.5 | $0.00004 | $0.00773 |
Grade A, and why
write-fixture 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 2d 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 — 455 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing tests with Fixture Monkey
Fixture Monkey generates test objects with random values. Two skills matter: choosing which cases to test, and knowing what not to set in each one.
Pin the properties that force the expected outcome. Leave everything else random.
A fixture that sets every field is a hand-rolled builder with extra ceremony — it breaks when an unrelated field is added, and it drags the test file into diffs it has nothing to do with.
Scope: tests only
Never modify production code. This work adds and edits tests. Production sources are read-only — read them to understand behaviour, never to change it.
That holds even when changing them would be easier:
| Temptation | Do instead |
|---|---|
Add @ConstructorProperties, a no-arg constructor, or a setter so the type generates |
Choose a different introspector, or instantiate a specific constructor |
| Relax a validation annotation that keeps rejecting samples | Pin the property to a valid value, or narrow the Arbitrary |
| Widen a field's visibility to reach it | Reach it through the constructor or an existing accessor |
Remove or weaken a @Nullable so defaultNotNull(true) reaches the field |
Leave the annotation alone: setNotNull the property, or empty the null-inject generator's nullable-annotation set — see Nullability comes first |
| "Fix" a bug the new test just exposed | Report it and leave the failing test — see step 6 |
If a test genuinely cannot be written without a production change, stop and say so, naming the change and why it is needed. Let the user decide. A production edit smuggled in with a test is the one thing a reviewer will not be looking for.
Procedure
Steps 1–4 decide which tests to write. Steps 5–6 write each one.
1. Identify the method under test
Name the exact method. Read its body and the types it takes and returns. If the request is vague ("write tests for the order service"), narrow it to specific methods and say which ones you picked.
What ships with it
3 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.
- 2d ago First seen · 455 lines · 42 tokens per session scan A a27aa0ac08dc
write-fixture is a skill published in the GitHub repository naver/fixture-monkey (697 stars, last pushed 9d ago), licensed Apache-2.0. It adds 42 tokens to every session and 7,735 once invoked, about $0.0002 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
plugin-code-review-orchestrated
Orchestrates a code review of the spring-plugin repository through scope/context passes, routing, domain reviewer subskills, and per-artifact validation. Use when asked to review a PR, diff, commit, branch, module, or file set, to run a full orchestrated review, or to produce a validated review report.
review-async-lifecycle
Normative reviewer for EDT safety, coroutines, cancellation, read/write actions, disposal, listeners and async lifecycle in the explyt spring-plugin. Use during orchestrated code review when the diff touches threading, background tasks, read or write actions, listeners, MessageBus, Disposable ownership or progress…
review-findings-validator
Normative per-artifact validator: reads exactly one reviewer artifact, re-verifies every claim against real source code, classifies findings as TP, FP, or Need more data, and writes exactly one validated artifact. Use during the validation wave of an orchestrated code review, when asked to validate reviewer findings…
review-psi-vfs-indexing
Normative reviewer for PSI lifecycle, VFS, indexing, UAST, references, inspections, intentions and PSI performance traps in the explyt spring-plugin. Use during orchestrated code review when the diff touches PsiElement handling, VirtualFile processing, caches, indexes, completion contributors, inspections, line…
review-ui-platform
Normative reviewer for IntelliJ UI, Action System, ToolWindow, DialogWrapper, JCEF, accessibility and UI state consistency in the explyt spring-plugin. Use during orchestrated code review when the diff touches actions, tool windows, dialogs, settings panels, wizard steps, notifications, popups, renderers, icons or…
review-statistic-coverage
Usage-statistics coverage check for explyt/spring-plugin code reviews — verify that new user-visible features (quick fixes, intentions, gutter actions, completions, actions, tool-window controls, wizard steps) register usage via StatisticService and StatisticActionId. Use when reviewing a diff or PR that adds or…