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 Eliyce/paqad-ai --skill test-runner-discoverygit clone --depth 1 https://github.com/Eliyce/paqad-aiWrote 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/eliyce/paqad-ai/test-runner-discovery)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/test-runner-discovery"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/test-runner-discovery/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/eliyce/paqad-ai/test-runner-discovery"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/test-runner-discovery.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 | $0.00055 | $0.01007 |
| Opus 5 | $0.00028 | $0.00504 |
| Sonnet 5 | $0.00011 | $0.00201 |
| Haiku 4.5 | $0.00006 | $0.00101 |
Grade A, and why
test-runner-discovery 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 today.
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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What It Does
Decides how the project's own test runner parallelizes when paqad's script detection could not
(checks plan printed test: sequential (unknown)). It reads the project's manifests and lockfiles,
identifies the runner the project's test script invokes, and decides whether a parallel mode exists
and its prerequisite is installed — never assuming, never installing anything. It emits a small
JSON record; the paqad-ai checks record-runner verb validates and stores it.
Use This When
- A feature-development
checks runreportedtest ran sequentially: parallel mode unknown, and you want the next run to be fast. Run this once; the recorded decision makes every later run fast.
Do not run this when checks plan already shows parallel, native, or a concrete
sequential (<reason>) — the script has already decided.
Inputs
project_root— the project to inspect.test_command— the project'scommands.test; the parallel command MUST start with its runner invocation and only add allowlisted parallel flags.- Read
references/allowed-flags.mdfor the exact tokens atest_parallelmay add.
Procedure
- Read the ecosystem manifest and lockfile:
composer.json/composer.lock,package.jsonand its lockfile,pyproject.toml/requirements*.txt/poetry.lock/uv.lock,Gemfile.lock,build.gradle(.kts),go.mod,Cargo.toml,pubspec.yaml. - Identify the runner the project's own test script invokes (mocha, tap, ava, …).
- Decide whether a parallel mode exists AND its prerequisite is present in the lockfile. If the
prerequisite is missing, the mode is
unavailable— never propose installing it. - When
available, buildtest_parallelfromtest_commandby adding only tokens listed inreferences/allowed-flags.md, with<processes>exactly once. Never add any other token. - Write
<scratch>/test-runner.json(see Output Contract) and hand it to the pipeline:npx paqad-ai checks record-runner <scratch>/test-runner.json. That verb runs the deterministic guard and rejects anything outside the allowlist — do not re-implement that check here.
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.
- today First seen · 92 lines · 55 tokens per session scan A 918a964beabc
test-runner-discovery is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,007 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 2026-09-12.
Other skills, from other repositories
auto-qa
QAMESH project QA mesh — plan, run, report, and publish deterministic QA evidence.
auto-canary
A deployment health-check skill for testing whether a recently deployed or staging website is working. It runs build, end-to-end, and browser checks, then reports a pass, warning, or failure.
tdd
A Test-Driven Development guide. TDD means writing a failing test first, adding the smallest implementation that passes it, and then improving the code while keeping the tests passing.
testing-strategy
A testing guide that explains how to combine unit, integration, contract, and end-to-end tests. End-to-end tests check complete user flows, while integration tests check components working together.
debugging
A structured method for finding and fixing software bugs. It starts by writing a test that reproduces the failure, then investigates its underlying cause before making a small fix.
database-verification
Shell-based database connectivity and integrity checks. Verifies that databases are reachable, schemas match expectations, and data integrity constraints hold.