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 Redtropig/harness-anchor --skill test-coverage-designgit clone --depth 1 https://github.com/Redtropig/harness-anchorWrote 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/redtropig/harness-anchor/test-coverage-design)<a href="https://agentmods.dev/skills/redtropig/harness-anchor/test-coverage-design"><img src="https://agentmods.dev/badge/skills/redtropig/harness-anchor/test-coverage-design/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/redtropig/harness-anchor/test-coverage-design"><img src="https://agentmods.dev/badge/skills/redtropig/harness-anchor/test-coverage-design.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 | $0.00086 | $0.01307 |
| Opus 5 | $0.00043 | $0.00654 |
| Sonnet 5 | $0.00017 | $0.00261 |
| Haiku 4.5 | $0.00009 | $0.00131 |
Grade A, and why
test-coverage-design 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 9d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Coverage Design
A passing test suite proves only that the tests you wrote pass — not that they exercise what the feature actually requires or where the code is actually risky. This skill is the post-implementation discipline for closing that gap: derive what must be tested, check it against what the suite runs, and design the smallest test set that covers it.
Altitude — where this sits vs. superpowers TDD
| Phase | Owner | What |
|---|---|---|
| Pre-implementation (spec-driven, test-first) | superpowers test-driven-development |
Red-green-refactor; write the failing test before the code. Deliberately code-blind. |
| Post-implementation (code-aware) | this skill + coverage-analyst |
Read the actual code for risk; confirm the spec's obligations are met and actually run. |
Do not reimplement TDD's process here. Use TDD first for the spec-driven cases; use this after the
code exists for the cases TDD structurally can't see (its discipline forbids looking at the
implementation). The design techniques in coverage-reference.md serve both phases.
Two failure modes this prevents
- Obligation gap — a behaviour / edge case / risky construct the feature needs is never tested
(e.g. nothing checks
checksum()on large input, so a fixed-width-accumulator overflow ships). - Run-scope gap — a test or binary that would exercise the risk exists but the project's runner
never executes it (e.g. a binary built with
add_executablebut neveradd_test-registered, so/sanitize+/verifysilently skip it and report "clean").
These are classic confident-wrong traps, and a line-coverage tool misses them: the line can run under a small input yet never at the magnitude / in the scope where the bug bites.
Method (gray-box, post-implementation)
- Black-box obligations from the spec —
feature_list.jsondescription +done_criteria,AGENTS.md, anydocs/superpowers/specs|plans/*. List behaviours incl. malformed / empty / boundary inputs the spec implies. - White-box / risk obligations from the code — scan the implementation against the risk-construct
checklist in
coverage-reference.md. These are the ones the spec never names but the code reveals. - Check both against the suite AND the run scope — for each obligation, is there a test the runner actually executes that exercises it? An unexercised obligation, or one exercised only by a binary outside the runner's scope, is a gap.
- Design the minimal closing set — equivalence-partitioning + boundary-value + pairwise for fewest
cases, widest coverage (see
coverage-reference.md).
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.
- 9d ago First seen · 86 lines · 86 tokens per session scan A cd1acb6accc6
test-coverage-design is a skill published in the GitHub repository Redtropig/harness-anchor (13 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 1,307 once invoked, about $0.0004 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
testing-e2e
End-to-end testing patterns with Playwright — page objects, AI agent testing, visual regression, accessibility testing with axe-core, and CI integration. Use when writing E2E tests, setting up Playwright, implementing visual regression, or testing accessibility.
bare-eval
Run isolated eval and grading calls using CC 2.1.81 --bare mode. Constructs claude -p --bare invocations for skill evaluation, trigger testing, and LLM grading without plugin/hook interference. Use when running eval pipelines, grading skill outputs, benchmarking prompt quality, or testing trigger accuracy in isolation.
golden-dataset
Golden dataset lifecycle patterns for curation, versioning, quality validation, and CI integration. Use when building evaluation datasets, managing dataset versions, validating quality scores, or integrating golden tests into pipelines.
testing-llm
LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing AI features, validating LLM outputs, or building evaluation pipelines.
paired-probe
Refuse a verdict a probe did not earn. Runs a check where the fault IS present and where it is NOT, and blocks the answer when both arms print the same thing, because a check that cannot disagree with you has measured nothing. Also catches the zero-sample sweep that reads as "clean" and the swallowed error that reads…
testing-patterns
Redirect — testing-patterns was split into 5 focused sub-skills. Use when looking for testing-patterns, writing tests, or test automation. Redirects to testing-unit, testing-e2e, testing-integration, testing-llm, or testing-perf.