A static review of test and source files that finds skipped tests, untested public code, flaky patterns, and missing edge cases. It uses file patterns and does not run coverage tools.

Auditing a test directory or selected files, finding risky gaps, and identifying retries, sleeps, skipped tests, and other signs of test debt.

It shows where the test suite gives a false sense of safety or behaves unreliably, especially before a release.

test-debt — Skill for Claude Code by hereinthehive

Install

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.

Any agent

npx skills add hereinthehive/gotrino-assistant --skill test-debt

Clone the repo

git clone --depth 1 https://github.com/hereinthehive/gotrino-assistant

Made for: Claude Code.

Or install gotrino-assistant, the plugin that ships this one along with the rest of its 18 skills, 1 agent.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hereinthehive/gotrino-assistant/test-debt/github.svg)](https://agentmods.dev/skills/hereinthehive/gotrino-assistant/test-debt)

Your own site

<a href="https://agentmods.dev/skills/hereinthehive/gotrino-assistant/test-debt"><img src="https://agentmods.dev/badge/skills/hereinthehive/gotrino-assistant/test-debt/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hereinthehive/gotrino-assistant/test-debt"><img src="https://agentmods.dev/badge/skills/hereinthehive/gotrino-assistant/test-debt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 694 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00050	$0.00694
Opus 5	$0.00025	$0.00347
Sonnet 5	$0.00010	$0.00139
Haiku 4.5	$0.00005	$0.00069

Measured 10d ago against content hash 6a7b3fd49f96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

test-debt 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 10d 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.

skills/test-debt/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Debt

Surface debt in the test suite — what's skipped, what's untested, what's flaky by design.

Philosophy

"What confidence are we missing, and which code changes are riskier because of it?"

A test suite with a hundred skipped tests is lying to the team about what's covered. A retry loop in a test is telling you the real behavior isn't deterministic. Test debt is where the suite stops being a safety net.

Not a coverage report. This skill is pattern-based — it reads test files and source files, and spots the gaps between them. Runtime coverage is a complementary tool, not this skill's job.

Scope

User specifies a path, glob, or directory. If not specified, ask: "Which directory or test file should I audit?"

Config Integration

Follow references/config-migration.md for preflight.

Read .assistant-config.md for:

Test location (set by /teach-charter)
Stack (determines skip patterns per framework)
Acknowledged Debt

Stack Detection

Detect test framework from dev dependencies / manifest:

jest, vitest, mocha, cypress, playwright in package.json
pytest in requirements.txt / pyproject.toml
rspec in Gemfile
Built-in testing package for Go
junit / testng for JVM projects

Use the right skip patterns. See references/test-debt-patterns.md.

Process

1. Understand context

Locate the test directory. Count test files. Note the framework in use.

2. Scan

Skipped tests: Grep for framework-specific skip markers.
Flaky patterns: Grep for retry loops, sleep/setTimeout inside test files, high timeouts.
Untested public APIs: Glob source, identify exported symbols (language-specific), cross-reference against test files.

3. Group by location

Group by test file (for skips and flakiness) or by source module (for untested APIs).

4. Assess impact

High: skipped tests on critical paths, untested public APIs on entry points
Medium: flaky patterns in core test suites
Low: skipped tests with tracked issues, untested internal helpers

Read the full file on GitHub · 81 lines

Changes

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.

10d ago First seen · 81 lines · 50 tokens per session scan A 6a7b3fd49f96

Subscribe to this mod's changes

test-debt is a skill published in the GitHub repository hereinthehive/gotrino-assistant (5 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 694 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 2026-08-31.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

test-debt