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 mracal/vibe-engineering --skill golden-file-testinggit clone --depth 1 https://github.com/mracal/vibe-engineeringWrote 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/mracal/vibe-engineering/golden-file-testing)<a href="https://agentmods.dev/skills/mracal/vibe-engineering/golden-file-testing"><img src="https://agentmods.dev/badge/skills/mracal/vibe-engineering/golden-file-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/mracal/vibe-engineering/golden-file-testing"><img src="https://agentmods.dev/badge/skills/mracal/vibe-engineering/golden-file-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 | $0.00034 | $0.00765 |
| Opus 5.5 | $0.00014 | $0.00306 |
| Sonnet 5.5 | $0.00007 | $0.00153 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
vibe-golden-file-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 2mo 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.
This is a copy
100% identical to vibe-golden-file-testing — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibe-golden-file-testing
Golden file tests are powerful but brittle. This skill makes them robust.
When to Use This Skill
- Implementing tests that compare output against saved expected output
- Tests that currently break because dates, timestamps, or IDs change
- API response testing with dynamic fields
- CLI output testing
When NOT to Use This Skill
- Simple unit tests with static assertions
- Tests where the exact output IS the requirement (byte-for-byte)
- Performance benchmarks
The Problem
Golden tests break when they contain:
- Dates/timestamps (
2026-02-28→ different tomorrow) - UUIDs/IDs (random each run)
- Hostnames/ports (different per environment)
- File paths (absolute paths differ per machine)
- Durations (
took 1.23s→ varies by machine)
Steps
-
Identify dynamic fields in the output being tested
-
Create normalizer function:
func normalizeOutput(s string) string { // Dates: 2026-02-28 → REDACTED_DATE s = dateRegex.ReplaceAll(s, "REDACTED_DATE") // UUIDs: 550e8400-... → REDACTED_UUID s = uuidRegex.ReplaceAll(s, "REDACTED_UUID") // Timestamps: 1709136000 → REDACTED_TS s = tsRegex.ReplaceAll(s, "REDACTED_TS") // Durations: 1.23s → REDACTED_DURATION s = durationRegex.ReplaceAll(s, "REDACTED_DURATION") return s } -
Apply normalization to BOTH:
- The actual output (at test time)
- The golden file (at generation time)
-
Generate golden file with update flag:
if os.Getenv("UPDATE_GOLDEN") == "1" { os.WriteFile(goldenPath, normalized, 0644) } -
Document update command:
# To update golden files: UPDATE_GOLDEN=1 go test ./...
Common Normalizations
| Pattern | Regex | Replacement |
|---|---|---|
| ISO Date | \d{4}-\d{2}-\d{2} |
REDACTED_DATE |
| ISO DateTime | \d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2} |
REDACTED_DATETIME |
| UUID | [0-9a-f]{8}-[0-9a-f]{4}-... |
REDACTED_UUID |
| Unix timestamp | \b1[6-9]\d{8}\b |
REDACTED_TS |
| Duration | \d+\.?\d*[µnm]?s |
REDACTED_DURATION |
| Absolute path | /home/\w+/ or C:\\Users\\ |
REDACTED_PATH |
| Port | :\d{4,5}\b |
:REDACTED_PORT |
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.
- 2mo ago First seen · 89 lines · 34 tokens per session scan A b21e0bd54c4a
vibe-golden-file-testing is a skill published in the GitHub repository mracal/vibe-engineering (3 stars, last pushed 24d ago), licensed MIT. It adds 34 tokens to every session and 765 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to vibe-golden-file-testing, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
agent-tester
Agent skill for tester - invoke with $agent-tester.
moai-ref-testing-pyramid
Test pyramid strategy, coverage targets, test patterns, and quality metrics reference. Agent-extending skill that amplifies manager-develop test-creation and quality-validation work with production-grade testing patterns. NOT for: production code implementation, architecture design, DevOps, security audits.
spec-execution
6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.
quality-checklist
Validate implementation quality through custom checklists, scoring against constitution standards, specification coverage, and producing remediation recommendations.
test-automation
Execute Vitest and Playwright test suites with result collection and failure analysis.
test-enforcement
Automated test validation, coverage checking, and quality metrics with aggressive defaults.