Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/greglas75/zuvonpx agentmods add skills/greglas75/zuvo/write-testsWrote 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/greglas75/zuvo/write-tests)<a href="https://agentmods.dev/skills/greglas75/zuvo/write-tests"><img src="https://agentmods.dev/badge/skills/greglas75/zuvo/write-tests/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/greglas75/zuvo/write-tests"><img src="https://agentmods.dev/badge/skills/greglas75/zuvo/write-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 381 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00087 | $0.22958 |
| Opus 5.5 | $0.00035 | $0.09183 |
| Sonnet 5.5 | $0.00017 | $0.04592 |
| Haiku 4.5 | $0.00009 | $0.02296 |
Grade A, and why
write-tests 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 — 1,008 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zuvo:write-tests — Single-File Test Pipeline
Generate high-quality tests for production code. Each file goes through the full pipeline individually — no batching of files or pipeline steps, no skipping verification in normal mode, no skipping the coverage gate or audit.
The pipeline's spine is inventory-first + executable proof: the public
surface is enumerated and FROZEN before the first test is written, and the only
authority on coverage completeness is scripts/test-coverage-gate.py — a
program, not the writer's own claim.
Scope: Existing production files with missing or partial test coverage.
Out of scope: New feature tests (use zuvo:build), mass anti-pattern repair (use zuvo:fix-tests), audit without writing (use zuvo:test-audit).
Argument Parsing
| Input | Behavior |
|---|---|
[file.ts] |
Write tests for one production file |
[directory/] |
Write tests for all production files in the directory |
auto |
Discover uncovered files, process one at a time until done |
--dry-run |
Run Phase 0 + Step 1 for all files, print plan, stop |
--no-cache |
Re-run discovery/classification from scratch: ignore any cached CodeSift index answer and any previously built queue for this run |
--resume <basename> |
Resume ONE file from its persisted checkpoint: load contracts/<basename>.coverage.json + contracts/<basename>.contract.md, verify production_sha256 against the file on disk (mismatch → refuse and demand re-inventory — the existing hash rule), take classification from the contract (skip Phase 0.5/Step 1 re-derivation), then jump by state: manifest inventory + contract present → Step 2; final → Step 3; final with Q-scores synced → Step 3.3 |
--invoked-by <skill> |
Run on behalf of the named skill (refactor's Phase 3.6 Step 0, for one): no snapshot, no closing commit, and the report ends with Backlog writes: <path>, … (or Backlog writes: none) for that skill's closing commit. Without it the run is standalone and commits its own writes |
--resume-run <ledger> |
Resume an auto-mode queue from its run ledger (see Auto-mode context boundary): reload run-level facts + remaining queue, continue with the next file in a clean window |
What ships with it
5 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 Changed · +27 lines 131241b54eea
- 8d ago Changed · +17 lines 1d73c294c296
- 9d ago Changed · +13 lines 3177cea940f7
- 10d ago Changed · +2 lines 721669d72a02
- 20d ago Changed · +5 lines e4218ca302b6
- 25d ago Changed · +9 lines 4e3f04c2d9cf
- 27d ago Changed · +84 lines c4395a24a671
- 1mo ago Changed · -5 lines 96d87a6e89bc
- 1mo ago First seen · 856 lines · 87 tokens per session scan A 83da2c2e14a3
write-tests is a skill published in the GitHub repository greglas75/zuvo (8 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 22,958 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
brooks-test
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…
ai-agent-bench
Compare Claude Code and Codex on the same code task, with isolated worktrees, common checks, time, and cost.
create-test
Define or implement regression proof: test strategy, black-box or integration tests, KPIs, thresholds, audits, or missing tests.
wrap-up-branch
Finish a feature branch: add missing tests, review and fix the code, align docs, then merge only after explicit confirmation.
eval-regression
Check skill routing or behavior, investigate a regression, or compare plugin changes with a base commit.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.