Is the Dev Test skill free?

Yes. The skill itself is free from gtapps/claude-code-hermit. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Dev Test SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.

How do I install Dev Test?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Dev Test with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Dev Test

Runs the project's configured test command and writes a SHA-pinned pass/fail record other Hermit commands gate on.

by gtapps · gtapps/claude-code-hermit

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.8/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 20e83e2

Traced the actual record-test-result.ts source: the SKILL.md's stderr string 'commands.test not configured' is a byte-for-byte match to the script's real error message, and failed runs get auto-tagged with a likely_cause (oom/timeout/user-interrupt) inferred from the exit code — a diagnostic touch a naive `npm test` baseline wouldn't give you.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 5/5

What Dev Test does

Executes the operator-configured commands.test command and atomically records exit code, duration, git HEAD SHA, timestamp, and (for OOM/timeout/interrupt) a likely_cause into .claude-code-hermit/state/last-test.json. Triggers on requests for mid-task test verification or isolated failing-test debugging within the claude-code-hermit plugin workflow, and is consumed by /dev-pr as a cache so a fresh pass at the same HEAD skips re-running the suite.

How to install Dev Test

git clone https://github.com/gtapps/claude-code-hermit
cd claude-code-hermit
mkdir -p ~/.claude/skills
cp -r plugins/claude-code-dev-hermit/skills/dev-test ~/.claude/skills/dev-test

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Dev Test

/dev-test Runs the project's configured test command and writes a SHA-pinned pass/fail record other Hermit commands gate on.

It also activates on plain-language prompts like these:

Run our test suite and record whether it passed at this commit.
I need a structured pass/fail record before we merge this PR.
Verify the tests still pass here and log the result for later.

Frequently asked questions

Is the Dev Test skill free?: Yes. The skill itself is free from gtapps/claude-code-hermit. SkillProof publishes the install command and an independent test verdict at no cost.
Does Dev Test work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Works with setup. Traced the actual record-test-result.ts source: the SKILL.md's stderr string 'commands.test not configured' is a byte-for-byte match to the script's real error message, and failed runs get auto-tagged with a likely_cause (oom/timeout/user-interrupt) inferred from the exit code — a diagnostic touch a naive `npm test` baseline wouldn't give you.
What is the Dev Test SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
How do I install Dev Test?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Dev Test with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.