A test-running tool for plug-ins in a monorepo, meaning one repository that contains multiple related projects. It runs one selected plug-in's tests or all plug-in test suites and reports the results.

Use it to test a named plug-in or run every plug-in's test suite and receive per-plug-in and overall results.

It provides a concise pass-or-fail summary instead of requiring you to run and interpret each suite manually. It also checks that a requested plug-in exists.

test-run — Skill for Claude Code by gtapps/claude-code-hermit

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 gtapps/claude-code-hermit --skill test-run

Clone the repo

git clone --depth 1 https://github.com/gtapps/claude-code-hermit

Made for: Claude Code.

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/gtapps/claude-code-hermit/test-run/github.svg)](https://agentmods.dev/skills/gtapps/claude-code-hermit/test-run)

Your own site

<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/test-run"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/test-run/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/gtapps/claude-code-hermit/test-run"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/test-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 584 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00035	$0.00584
Opus 5.5	$0.00014	$0.00234
Sonnet 5.5	$0.00007	$0.00117
Haiku 4.5	$0.00003	$0.00058

Measured 1mo ago against content hash 741786fc35a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

test-run 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 1mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

test-run — 91% identical, 4 lines differ

.agents/skills/test-run/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Run

Run plugin test suites and report a concise summary. Operates on a single plugin when given a slug; otherwise loops every plugin in plugins/.

Usage

/test-run — run tests for every plugin in plugins/ and report a per-plugin summary plus an overall PASS/FAIL.

/test-run <plugin-slug> — run tests for just that plugin.

Examples:

/test-run claude-code-hermit
/test-run claude-code-homeassistant-hermit

Steps

0. Resolve target slugs

If no slug arg was passed, run bash scripts/test-all.sh from the repo root (launches every plugin's suite in parallel; wall time is bounded by the slowest suite instead of their sum) and report its summary table directly — skip Steps 0-1 below entirely.
If a slug arg was passed, validate plugins/<slug>/.claude-plugin/plugin.json exists. If not, abort with: Plugin 'plugins/<slug>/' not found. Available: <comma-separated slugs>. Then continue to Step 1 for that single plugin.

1. Run the suite (single-plugin arg only)

Plugins ship one of two test conventions. Detect and dispatch:

Bash entrypoint — if plugins/<slug>/tests/run-all.sh exists (dev/fitness/scribe/forge convention):
```
bash plugins/<slug>/tests/run-all.sh 2>&1
```
Bun entrypoint — else if any plugins/<slug>/tests/*.test.ts exists (core/HA/feed convention): cd plugins/<slug> && bun test 2>&1.
Neither marker — mark no tests configured and continue.

Capture full output. Extract pass/fail counts from the suite's summary line.

2. Report

Per-plugin block:

=== <slug> ===
Hook tests:     X passed, Y failed         (bash convention only)
Contract tests: X passed, Y failed         (bash convention only)
Script tests:   X passed, Y failed         (bash convention only)
Bun tests:      X passed, Y failed         (bun convention only)
Plugin result:  PASS / FAIL / SKIP

Final overall line:

Overall: PASS / FAIL  (<n> passed, <m> failed, <k> skipped across <p> plugins)

If any test failed, include the failure details below the summary so the developer can act on them immediately.

Read the full file on GitHub · 60 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.

1mo ago First seen · 60 lines · 35 tokens per session scan A 741786fc35a5

Subscribe to this mod's changes

test-run is a skill published in the GitHub repository gtapps/claude-code-hermit (82 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 584 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude Code Testing ai ai-agent anthropic claude claude-code-plugin

hermit-scribe

File a GitHub issue or post a comment on an existing issue via a GitHub App bot identity. Use when the operator says "file as a GH issue", "open an issue for PROP-NNN", "report this to the tracker", "add a comment to issue.

gtapps/hermitd · 60 tokens

mean-tester

Mean test another agent when someone asks you to test, check or break it. Invoke on "test @agent", "mean test @agent", "check whether @agent works", on "continue " or "rerun " in a new message, or on "continue" in a thread where you already reported a campaign, and on "Judge this recorded exchange".

curie-eng/curie · 81 tokens

test-run