OpenHarness End-to-End Evals
HKUDS/OpenHarness
Validates OpenHarness features by running real multi-turn agent loops with live LLM calls against an unfamiliar codebase, checking actual tool execution.
Select and run the smallest sufficient MMDmodoki verification set after code or configuration changes, then separate new failures from known baselines.
Install Mmd Test
$ npx skills add togechiyo/MMD_modoki --skill mmd-test -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install togechiyo/MMD_modoki mmd-test --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/togechiyo/MMD_modoki.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/mmd-test .claude/skills/mmd-test && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "mmd-test" agent skill from https://github.com/togechiyo/MMD_modoki/tree/main/.agents/skills/mmd-test into .claude/skills/mmd-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mmd-test", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/togechiyo/MMD_modoki/tree/main/.agents/skills/mmd-testType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add togechiyo/MMD_modoki --skill mmd-test -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install togechiyo/MMD_modoki mmd-test --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/togechiyo/MMD_modoki.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/mmd-test .agents/skills/mmd-test && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mmd-test" agent skill from https://github.com/togechiyo/MMD_modoki/tree/main/.agents/skills/mmd-test into .agents/skills/mmd-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mmd-test", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add togechiyo/MMD_modoki --skill mmd-test -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install togechiyo/MMD_modoki mmd-test --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/togechiyo/MMD_modoki.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/mmd-test .cursor/skills/mmd-test && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "mmd-test" agent skill from https://github.com/togechiyo/MMD_modoki/tree/main/.agents/skills/mmd-test into .cursor/skills/mmd-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mmd-test", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/togechiyo/MMD_modoki.git --path .agents/skills/mmd-test--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add togechiyo/MMD_modoki --skill mmd-test -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install togechiyo/MMD_modoki mmd-test --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/togechiyo/MMD_modoki.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/mmd-test .gemini/skills/mmd-test && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "mmd-test" agent skill from https://github.com/togechiyo/MMD_modoki/tree/main/.agents/skills/mmd-test into .gemini/skills/mmd-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mmd-test", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install togechiyo/MMD_modoki mmd-testInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add togechiyo/MMD_modoki --skill mmd-test -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/togechiyo/MMD_modoki.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/mmd-test .github/skills/mmd-test && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "mmd-test" agent skill from https://github.com/togechiyo/MMD_modoki/tree/main/.agents/skills/mmd-test into .github/skills/mmd-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mmd-test", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add togechiyo/MMD_modoki --skill mmd-test -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install togechiyo/MMD_modoki mmd-test --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/togechiyo/MMD_modoki.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/mmd-test .opencode/skills/mmd-test && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "mmd-test" agent skill from https://github.com/togechiyo/MMD_modoki/tree/main/.agents/skills/mmd-test into .opencode/skills/mmd-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mmd-test", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
mmd-test- GitHub stars
- 146
- Token cost
- ~936 tokens
- SKILL.md length
- 432 words
- Files
- 1
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
Select and run the smallest sufficient MMDmodoki verification set after code or configuration changes, then separate new failures from known baselines.
- Works in 4 steps: Confirm the working directory is the… → Inspect git status and the relevant… → Determine whether the user requested… → …
- Pre-commit checks
- SKILL.md covers Establish scope, Select checks, Execute and interpret and Report
- Calls git
What it does
Mmd Test is an agent skill from togechiyo/MMD_modoki. Select and run the smallest sufficient MMDmodoki verification set after code or configuration changes, then separate new failures from known baselines. Use for test requests, pre-commit checks, or deciding among lint, unit, typecheck, smoke, E2E, and manual verification. Do not use for packaging or release publication.
Its SKILL.md is about 940 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Testing & QA, covering End-to-end testing and Linting and formatting. It works with npm. The licence is MIT.
When your agent uses it
- Pre-commit checks
- Deciding among lint
- Manual verification
- Release publication
Example prompts
- “/mmd-test”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Confirm the working directory is the MMD_modoki repository and inspect package.json for the current scripts.
- Inspect git status and the relevant diff. Preserve unrelated user changes and untracked files.
- Determine whether the user requested verification only, diagnosis, or implementation. Verification does not authorize fixes.
- Identify the changed behavior, affected execution path, and the cheapest layer that can observe it.
What it can do on your machine
Read from SKILL.md and the folder at commit f5161f7. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Mmd Test loads about 936 tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 432 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from togechiyo/MMD_modoki at commit f5161f7, republished under its MIT licence (© togechiyo). 432 words, ~936 tokens.
Download SKILL.mdSave it as
.claude/skills/mmd-test/SKILL.md (or your agent's skills folder).- name
- mmd-test
- description
- Select and run the smallest sufficient MMD_modoki verification set after code or configuration changes, then separate new failures from known baselines. Use for test requests, pre-commit checks, or deciding among lint, unit, typecheck, smoke, E2E, and manual verification. Do not use for packaging or release publication.
MMD_modoki Test Selection
Verify the requested change with the narrowest set of checks that gives meaningful confidence. Follow the repository AGENTS.md; do not treat this skill as a replacement for it.
Establish scope
- Confirm the working directory is the MMD_modoki repository and inspect
package.jsonfor the current scripts. - Inspect
git statusand the relevant diff. Preserve unrelated user changes and untracked files. - Determine whether the user requested verification only, diagnosis, or implementation. Verification does not authorize fixes.
- Identify the changed behavior, affected execution path, and the cheapest layer that can observe it.
Select checks
Run only checks justified by the change.
| Change | Checks to consider |
|---|---|
| Markdown or insight cards only | link/front matter validation when applicable, then git diff --check; normally skip npm checks |
| TypeScript application code | npm.cmd run lint |
| Pure helper, Action, Command, diff, mergeKey, project conversion | focused unit test, then npm.cmd run test:unit |
| Types, runtime boundaries, exporter, catch paths | npm.cmd run typecheck and npm.cmd run typecheck:critical when useful; distinguish the non-blocking baseline from critical undefined-name errors |
| Main, preload, renderer startup, initialization, WebGPU startup | npm.cmd run smoke:launch in addition to lint |
| UI routes, menus, mode switches, registration operations | the narrowest relevant npm.cmd run test:e2e -- <spec>; use the full suite only when the change warrants it |
| Rendering quality or physics behavior | automated checks for logic/startup plus focused manual or user-device confirmation; do not claim visual correctness from smoke/E2E alone |
| Build/release configuration | validate the changed config and hand off packaging/publication to the appropriate workflow |
Read these only when the corresponding test layer is relevant:
- Unit-test strategy: testing-strategy-proposal.md
- Electron startup checks: electron-local-smoke-test-plan.md
- UI/runtime E2E: playwright-electron-e2e-operation-guide.md
Show full SKILL.md (166 more words)Show less
Execute and interpret
- Prefer a focused test before a broad suite while iterating.
- Do not run concurrent Electron/WebGPU checks that can compete for processes or GPU state.
- Do not use local PMX, PMD, VMD, texture, or other private assets unless the user explicitly authorizes those files for this verification.
- If a command fails, capture the command, exit status, and the smallest useful error excerpt.
- Compare typecheck and other known baselines before calling a failure new.
- Do not extend timeouts or fixed sleeps merely to make a flaky check pass; inspect the observable ready state and teardown first.
- Stop when the selected evidence is sufficient, a required environment is unavailable, or continuing would require new authorization.
Report
Lead with the overall result, then list:
- checks passed;
- checks failed, separated into new failures and known baseline failures;
- checks not run and why;
- manual or user-device confirmation still required.
Never describe an unrun check as passing. Do not commit, push, package, or publish unless the user separately requests it.
© togechiyo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/mmd-test of togechiyo/MMD_modoki.
Open the folder on GitHubat commit f5161f7
Compare with similar skills
Mmd Test next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Mmd Test this skilltogechiyo/MMD_modoki | 146 | — | ~936 | Automated safety check: Pass | MIT | |
| OpenHarness End-to-End EvalsHKUDS/OpenHarness | 16k | 1 repos | ~2.1k | Automated safety check: Notes | MIT | |
| Qwen Code E2E TestingQwenLM/qwen-code | 28k | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| E2E TestingInsForge/InsForge | 13k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| RStudio Playwright Test Runnerrstudio/rstudio | 5.1k | — | ~801 | Automated safety check: Pass | Custom licence | |
| tmux Real User TestingQwenLM/qwen-code | 28k | — | ~2.3k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Qwen Code E2E Testing
QwenLM/qwen-code
Guides end-to-end testing of the Qwen Code CLI in headless mode with real model calls, MCP test servers and inspection of raw API traffic.
E2E Testing
InsForge/InsForge
A skill your agent uses when an InsForge maintainer has finished an OSS repo change and is ready to open, update, or submit the InsForge PR.
RStudio Playwright Test Runner
rstudio/rstudio
Runs RStudio's Playwright end-to-end tests against the desktop app or a server build with the project's npm scripts, asking you which mode to use first.
tmux Real User Testing
QwenLM/qwen-code
Drives Qwen Code in a real tmux session the way a user would and saves a readable step-by-step transcript of each screen for maintainers to review.
Interactive CLI Testing With tui-test
slopus/happy
Tests interactive CLI and TUI programs with Microsoft's tui-test, driving prompts, arrow keys and screen output in a real pseudo-terminal.
More from togechiyo/MMD_modoki
Mmd Insight Curation
togechiyo/MMD_modoki
Curate reusable MMDmodoki knowledge from completed work, explicit owner decisions, verification results, docs, and diffs into insights cards and indexes.
Mmd Release
togechiyo/MMD_modoki
Prepare or execute an MMDmodoki version release by reconciling version files, feedback ledger, release notes, verification, CI packages, tags, and GitHub Release assets.
Mmd Rendering Triage
togechiyo/MMD_modoki
Diagnose MMDmodoki viewport or exported-image rendering artifacts by separating shadow, transparency, geometry, depth precision, and pipeline causes.
Related
Works with
Categories
Questions about Mmd Test
What does Mmd Test do?
Select and run the smallest sufficient MMDmodoki verification set after code or configuration changes, then separate new failures from known baselines. Mmd Test is an agent skill from togechiyo/MMD_modoki. Select and run the smallest sufficient MMDmodoki verification set after code or configuration changes, then separate new failures from known baselines.
When should I use Mmd Test?
Mmd Test fits situations like: pre-commit checks; deciding among lint; manual verification; release publication.
How do I install Mmd Test in Claude Code?
Run `npx skills add togechiyo/MMD_modoki --skill mmd-test -a claude-code`. Or copy the skill folder (.agents/skills/mmd-test in togechiyo/MMD_modoki) into .claude/skills/mmd-test in your project. Claude Code loads it when a task matches its description.
How do I install Mmd Test in Codex?
Run `npx skills add togechiyo/MMD_modoki --skill mmd-test -a codex`. Or copy the skill folder (.agents/skills/mmd-test in togechiyo/MMD_modoki) into .agents/skills/mmd-test in your project. Codex loads it when a task matches its description.
Can I use Mmd Test in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add togechiyo/MMD_modoki --skill mmd-test -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mmd-test, .gemini/skills/mmd-test, .github/skills/mmd-test and .opencode/skills/mmd-test in your project.
What does Mmd Test need to run?
Going by SKILL.md and its folder, Mmd Test needs the command-line tools its instructions call (git).
Does Mmd Test access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Mmd Test safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Mmd Test use?
Mmd Test is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Mmd Test use?
About 936 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Mmd Test?
Skills that share tags, products or a category with Mmd Test: OpenHarness End-to-End Evals (HKUDS/OpenHarness, 16k stars), Qwen Code E2E Testing (QwenLM/qwen-code, 28k stars), E2E Testing (InsForge/InsForge, 13k stars) and RStudio Playwright Test Runner (rstudio/rstudio, 5.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Mmd Test?
togechiyo (a GitHub user) maintains it in togechiyo/MMD_modoki, which has 146 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 9, 2026.
Source: togechiyo/MMD_modoki on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.