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.
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.
$ npx skills add InsForge/InsForge --skill e2e-testing -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install InsForge/InsForge e2e-testing --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/InsForge/InsForge.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/insforge-dev/e2e-testing .claude/skills/e2e-testing && 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 "e2e-testing" agent skill from https://github.com/InsForge/InsForge/tree/main/.codex/skills/insforge-dev/e2e-testing into .claude/skills/e2e-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "e2e-testing", 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/InsForge/InsForge/tree/main/.codex/skills/insforge-dev/e2e-testingType 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 InsForge/InsForge --skill e2e-testing -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install InsForge/InsForge e2e-testing --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/InsForge/InsForge.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.codex/skills/insforge-dev/e2e-testing .agents/skills/e2e-testing && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "e2e-testing" agent skill from https://github.com/InsForge/InsForge/tree/main/.codex/skills/insforge-dev/e2e-testing into .agents/skills/e2e-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "e2e-testing", 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 InsForge/InsForge --skill e2e-testing -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install InsForge/InsForge e2e-testing --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/InsForge/InsForge.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.codex/skills/insforge-dev/e2e-testing .cursor/skills/e2e-testing && 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 "e2e-testing" agent skill from https://github.com/InsForge/InsForge/tree/main/.codex/skills/insforge-dev/e2e-testing into .cursor/skills/e2e-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "e2e-testing", 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/InsForge/InsForge.git --path .codex/skills/insforge-dev/e2e-testing--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 InsForge/InsForge --skill e2e-testing -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install InsForge/InsForge e2e-testing --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/InsForge/InsForge.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.codex/skills/insforge-dev/e2e-testing .gemini/skills/e2e-testing && 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 "e2e-testing" agent skill from https://github.com/InsForge/InsForge/tree/main/.codex/skills/insforge-dev/e2e-testing into .gemini/skills/e2e-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "e2e-testing", 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 InsForge/InsForge e2e-testingInstalls 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 InsForge/InsForge --skill e2e-testing -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/InsForge/InsForge.git skills-src && mkdir -p .github/skills && cp -r skills-src/.codex/skills/insforge-dev/e2e-testing .github/skills/e2e-testing && 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 "e2e-testing" agent skill from https://github.com/InsForge/InsForge/tree/main/.codex/skills/insforge-dev/e2e-testing into .github/skills/e2e-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "e2e-testing", 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 InsForge/InsForge --skill e2e-testing -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install InsForge/InsForge e2e-testing --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/InsForge/InsForge.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.codex/skills/insforge-dev/e2e-testing .opencode/skills/e2e-testing && 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 "e2e-testing" agent skill from https://github.com/InsForge/InsForge/tree/main/.codex/skills/insforge-dev/e2e-testing into .opencode/skills/e2e-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "e2e-testing", 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.
e2e-testingA 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.
E2E Testing is an agent skill from InsForge/InsForge. Use this skill when an InsForge maintainer has finished an OSS repo change and is ready to open, update, or submit the InsForge PR. Runs the release-quality deterministic E2E gate by building a package.json-derived InsForge test image tag, deciding whether sibling agent-e2e fixture coverage must change, dispatching the Deterministic Fixture E2E workflow, waiting for results, and triaging failures before PR submission.
Its SKILL.md is about 1.5k 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. It works with npm. The repository describes itself as: The all-in-one, open-source backend platform for agentic coding. InsForge gives your coding agent database, auth, storage, compute, hosting, and AI gateway to ship full-stack… The licence is Apache-2.0.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 2ec64b6. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
ghnpmFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
github.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
E2E Testing loads about 1.5k tokens when it runs. Until then it costs about 108 tokens; SKILL.md has 705 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.
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.
The full file from InsForge/InsForge at commit 2ec64b6, republished under its Apache-2.0 licence (© InsForge). 705 words, ~1,524 tokens.
.claude/skills/e2e-testing/SKILL.md (or your agent's skills folder).Use this skill after local implementation and normal InsForge pre-PR checks pass, and before opening, updating, or submitting the InsForge OSS PR.
This is an additional release-quality gate. It does not replace local typecheck, lint, test, or build validation from the parent insforge-dev skill.
InsForge/agent-e2e.Use the remote InsForge/agent-e2e repository for workflow dispatch and read-only workflow checks. Do not rely on a developer-specific local checkout path. Create or use a local checkout only when the deterministic fixture tests must be edited.
package.json version.v<major>.<minor>.<patch+1>-<feature-or-issue-slug>Example: root version 2.2.3 and feature storage returning rls becomes v2.2.4-storage-returning-rls.
Use the package.json version as the only source of truth for the base version. Ignore higher existing test tags when calculating the base version.
Slug rules:
Dispatch the InsForge Build and Push Docker Image workflow with the test tag:
gh workflow run "Build and Push Docker Image" --repo InsForge/InsForge --ref <insforge-feature-branch> -f test_tag=<test-tag>Then wait for the matching run to complete:
gh run list --repo InsForge/InsForge --workflow "Build and Push Docker Image" --limit 10
gh run watch --repo InsForge/InsForge <run-id>Do not start the cross-repo E2E workflow until the image build succeeds.
agent-e2e Must ChangeInspect the InsForge diff and compare it with deterministic fixture coverage in InsForge/agent-e2e.
For read-only checks, prefer remote GitHub access such as gh api, gh repo view, or remote file reads. Use a local checkout only when editing fixture files or when remote inspection is not enough to understand coverage.
Update agent-e2e when the InsForge change adds, removes, or changes behavior that the deterministic fixture should assert, including:
Do not update agent-e2e for internal refactors, docs-only changes, local test-only changes, or behavior already covered by the deterministic fixture with no assertion change needed.
Ignore Support Desk Agent E2E (Exploratory). It is not part of this gate.
Run the deterministic fixture workflow from agent-e2e main:
gh workflow run "Deterministic Fixture E2E" --repo InsForge/agent-e2e --ref main -f insforge_tag=<test-tag>Find and watch the run:
gh run list --repo InsForge/agent-e2e --workflow "Deterministic Fixture E2E" --limit 10
gh run watch --repo InsForge/agent-e2e <run-id>Work in a local checkout of the remote InsForge/agent-e2e repo only for the fixture update.
https://github.com/InsForge/agent-e2e.git into an isolated workspace.origin and start from origin/main.codex/<short-topic>.npm run typecheck
npm run lint
npm run fixture:e2e:dryRun broader validation when the changed fixture area supports it.
agent-e2e PR for the fixture update.agent-e2e branch that contains the fixture update:gh workflow run "Deterministic Fixture E2E" --repo InsForge/agent-e2e --ref <agent-e2e-branch> -f insforge_tag=<test-tag>If the deterministic fixture workflow passes:
agent-e2e PR was required, link that PR too.If the deterministic fixture workflow fails:
agent-e2e branch, rerun local validation, then rerun E2E from that branch.When finished, report:
agent-e2e changed.agent-e2e PR if any, and workflow runs.© InsForge, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .codex/skills/insforge-dev/e2e-testing of InsForge/InsForge.
Open the folder on GitHubat commit 2ec64b6
E2E Testing 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 |
|---|---|---|---|---|---|---|
| E2E Testing this skillInsForge/InsForge | 13k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| 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 | |
| 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 | |
| Interactive CLI Testing With tui-testslopus/happy | 24k | — | ~603 | Automated safety check: Pass | MIT |
HKUDS/OpenHarness
Validates OpenHarness features by running real multi-turn agent loops with live LLM calls against an unfamiliar codebase, checking actual tool execution.
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.
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.
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.
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.
Kiln-AI/Kiln
Look at Kiln's UI in a real browser, and run its end-to-end tests.
InsForge/InsForge
Write, edit, and maintain documentation. An agent skill from InsForge/InsForge.
InsForge/InsForge
A skill your agent uses when contributing to InsForge's backend package.
InsForge/InsForge
A skill your agent uses when contributing to InsForge's shared dashboard package.
InsForge/InsForge
A skill your agent uses when contributing to InsForge's product documentation in this repository.
InsForge/InsForge
Use this skill set when contributing to the InsForge monorepo itself.
InsForge/InsForge
A skill your agent uses when contributing to InsForge's shared schema package.
Works with
Categories
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. E2E Testing is an agent skill from InsForge/InsForge. Use this skill when an InsForge maintainer has finished an OSS repo change and is ready to open, update, or submit the InsForge PR.
E2E Testing fits situations like: an InsForge maintainer has finished an OSS repo change and is ready to open; submit the InsForge PR.
Run `npx skills add InsForge/InsForge --skill e2e-testing -a claude-code`. Or copy the skill folder (.codex/skills/insforge-dev/e2e-testing in InsForge/InsForge) into .claude/skills/e2e-testing in your project. Claude Code loads it when a task matches its description.
Run `npx skills add InsForge/InsForge --skill e2e-testing -a codex`. Or copy the skill folder (.codex/skills/insforge-dev/e2e-testing in InsForge/InsForge) into .agents/skills/e2e-testing in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add InsForge/InsForge --skill e2e-testing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/e2e-testing, .gemini/skills/e2e-testing, .github/skills/e2e-testing and .opencode/skills/e2e-testing in your project.
Going by SKILL.md and its folder, E2E Testing needs the command-line tools its instructions call (gh and npm). Our summary lists: Docker.
SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
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.
E2E Testing is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with E2E Testing: OpenHarness End-to-End Evals (HKUDS/OpenHarness, 16k stars), Qwen Code E2E Testing (QwenLM/qwen-code, 28k stars), RStudio Playwright Test Runner (rstudio/rstudio, 5.1k stars) and tmux Real User Testing (QwenLM/qwen-code, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
InsForge (a GitHub organization) maintains it in InsForge/InsForge, which has 13,064 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 6, 2026.
Source: InsForge/InsForge on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.