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 ckorhonen/swe-skills --skill test-gap-huntgit clone --depth 1 https://github.com/ckorhonen/swe-skillsWrote 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/ckorhonen/swe-skills/test-gap-hunt)<a href="https://agentmods.dev/skills/ckorhonen/swe-skills/test-gap-hunt"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/test-gap-hunt/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/ckorhonen/swe-skills/test-gap-hunt"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/test-gap-hunt.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 | $0.00121 | $0.02110 |
| Opus 5 | $0.00060 | $0.01055 |
| Sonnet 5 | $0.00024 | $0.00422 |
| Haiku 4.5 | $0.00012 | $0.00211 |
Grade A, and why
swe:test-gap-hunt 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.
How it starts
The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SWE Test Gap Hunt
What This Skill Does
Use this skill to run a bounded, evidence-led pass over a repository's tests.
The job is to:
- Detect the existing test and coverage workflow
- Rank the best test-improvement opportunities
- Add or strengthen a small number of high-value tests
- Improve weak test structure when it materially improves confidence or speed
- Leave a ranked backlog for the next incremental pass
This skill is language agnostic. Reuse the repository's own tooling, file layout, and test conventions instead of forcing a new framework.
When To Use
Use this skill when the user wants to:
- Improve coverage incrementally without broad rewrites
- Find the most important uncovered or weakly tested code paths
- Strengthen fragile, assertion-light, or over-mocked tests
- Add missing edge, error, branch, or boundary cases
- Run recurring or scheduled test-improvement passes over time
Do Not Use
Do not use this skill for:
- First-time test framework selection or migration
- Large production refactors done in the name of testability
- Coverage-number campaigns with no quality bar
- Pure performance profiling that is unrelated to test speed or test structure
- Broad QA or bug hunting without a test-improvement goal
Inputs To Confirm
Confirm or infer:
- Repository or package scope
- Whether the user wants execution or report-only output
- Runtime budget for validation and coverage commands
- Any no-touch areas or flaky suites to avoid
- Whether recent CI, coverage, or bug history is available
If the user does not specify a budget, default to a small incremental pass:
- rank the workspace
- improve the top 1-3 opportunities
- stop after targeted validation
Parallelization Rule
Create one session per cleanly separated package, module, or service when the environment supports parallel agent work.
- Run only on disjoint write surfaces
- Cap concurrency to a level the repo can validate safely
- Give each session a bounded target and explicit test files or directories
- Have each session return raw evidence, changed files, and validation output
- Keep prioritization, deduplication, and final validation in the parent session
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 · 307 lines · 121 tokens per session scan A ba55d85f67b6
swe:test-gap-hunt is a skill published in the GitHub repository ckorhonen/swe-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 121 tokens to every session and 2,110 once invoked, about $0.0006 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.
Other skills, from other repositories
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
test-gen
Generate and verify tests — happy path, edge cases, error paths — using the project's own framework and patterns.
meta-skill-tester
A testing tool for checking the quality of coding-agent skills. It compares results with and without a skill, runs regression and chain tests, measures usage and time, and produces a scored report.
verify
Self-test the Citadel hook pipeline from within a live session. Exercises real tool calls (Write, Edit, Bash, Read) and checks that hooks fired, telemetry accumulated, and no errors occurred. Reports HOOK HEALTH: PASS or HOOK HEALTH: FAIL with a per-hook breakdown.
autoresearch
Autonomous goal-directed iteration loop that continuously improves prompts, templates, configs, or code. Two evaluation modes — deterministic (eval.py with proxy heuristics) or AI judge (LLM rubric scoring). Uses four-way separation in both modes. Inspired by Karpathy's autoresearch.