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 ondrej-svec/heart-of-gold-toolkit --skill test-writergit clone --depth 1 https://github.com/ondrej-svec/heart-of-gold-toolkitWrote 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/ondrej-svec/heart-of-gold-toolkit/test-writer)<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/test-writer"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/test-writer/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/ondrej-svec/heart-of-gold-toolkit/test-writer"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/test-writer.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 MCP Rug Pull · line 23 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00068 | $0.01582 |
| Opus 5 | $0.00034 | $0.00791 |
| Sonnet 5 | $0.00014 | $0.00316 |
| Haiku 4.5 | $0.00007 | $0.00158 |
Grade A, and why
test-writer 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 12d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Writer
Write failing tests that define what "done" means. Behavioral tests verify acceptance criteria. Conformance tests verify the architecture is followed — not faked.
Boundaries
This skill MAY: read stories and architecture docs, write test files, run the test suite. This skill MAY NOT: write implementation code, modify existing source files, fix failing tests by changing expectations.
ALL tests must FAIL when this skill completes. That's the point — RED state.
Common Rationalizations
| Shortcut | Why It Fails | The Cost |
|---|---|---|
| "Write tests that pass with mocks" | Tests that pass with mocks prove nothing about real behavior | False confidence → bugs in production |
| "Skip conformance tests — unit tests are enough" | Unit tests don't verify architecture compliance | Stubs pass tests, real deps aren't wired |
| "Relax assertions — they're too strict" | Loose assertions let wrong implementations pass | Tests are decoration, not verification |
| "Test the happy path only" | Edge cases are where bugs hide | Happy path works, edge cases crash |
Step 1: Read Stories
If $STORIES_PATH is set (pipeline mode):
- Read the stories file at
$STORIES_PATH - Extract all stories with their acceptance criteria and edge cases
If no env var (standalone mode):
- Search
docs/stories/for recent story files - If found: Use AskUserQuestion (header: "Stories", question: "Found stories: [list]. Which should I write tests for?") with each as an option
- If not found: Use AskUserQuestion (header: "Stories", question: "Where are the stories? Provide a path, or describe what to test.")
Exit: Stories loaded, acceptance criteria extracted.
Step 2: Read Architecture Doc
If $ARCH_PATH is set (pipeline mode):
- Read the architecture doc at
$ARCH_PATH - Extract: dependencies, integration pattern, file structure
If no env var (standalone mode):
- Look for
*.architecture.mdnear the stories file - If found: Read it automatically
- If not found: Use AskUserQuestion (header: "Architecture", question: "Is there an architecture doc? Provide path or skip.") with options: "Skip (behavioral tests only)" and "Provide path"
What ships with it
2 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.
- 12d ago First seen · 179 lines · 68 tokens per session scan A 7b8c53c56c70
test-writer is a skill published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 22d ago), licensed MIT. It adds 68 tokens to every session and 1,582 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 2026-08-30.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.