Is the Dev Dry Run skill free?

Yes. The skill itself is free from raphaelchristi/harness-evolver. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Dev Dry Run SkillProof Score?

8.0/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 3/5.

How do I install Dev Dry Run?

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 Dry Run 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 Dry Run

Smoke-tests the harness-evolver pipeline offline (syntax/argparse/cross-ref) or online with a mock agent.

by raphaelchristi · raphaelchristi/harness-evolver

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.0/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 4894495

Ran its offline check against 3 planted tool scripts (one with a syntax error, one missing from the evolve skill's references) and it caught both real breakages a plain 'just run the files' pass missed; but a bare cp of just this folder leaves it stranded without the sibling tools/ dir and $HOME/.evolver venv it silently assumes.

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

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 3/5

What Dev Dry Run does

Runs a structured smoke test of the harness-evolver plugin's tool belt: an offline mode that validates Python syntax, --help wiring, and cross-references against skills/evolve/SKILL.md, plus an online mode that pushes a mock agent through setup/eval/read/trace. Triggers on 'dry run', 'smoke test', or 'test pipeline'.

How to install Dev Dry Run

git clone https://github.com/raphaelchristi/harness-evolver
cd harness-evolver
mkdir -p ~/.claude/skills
cp -r .claude/skills/dev-dry-run ~/.claude/skills/dev-dry-run

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

Commands — how to trigger Dev Dry Run

/dev-dry-run Smoke-tests the harness-evolver pipeline offline (syntax/argparse/cross-ref) or online with a mock agent.

It also activates on plain-language prompts like these:

Do a dry run of the evolve pipeline before I ship this change
Smoke test the harness-evolver tools against skills/evolve/SKILL.md
Run the online mock agent through setup, eval, read, and trace

Frequently asked questions

Is the Dev Dry Run skill free?: Yes. The skill itself is free from raphaelchristi/harness-evolver. SkillProof publishes the install command and an independent test verdict at no cost.
Does Dev Dry Run work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Works with setup. Ran its offline check against 3 planted tool scripts (one with a syntax error, one missing from the evolve skill's references) and it caught both real breakages a plain 'just run the files' pass missed; but a bare cp of just this folder leaves it stranded without the sibling tools/ dir and $HOME/.evolver venv it silently assumes.
What is the Dev Dry Run SkillProof Score?: 8.0/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 3/5.
How do I install Dev Dry Run?: 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 Dry Run 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.