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 to build an XS (express-lane) feature in one pass — intake→implement→verify in a single context, no handoff chain, code-first.
Install Express
$ npx skills add swingerman/engineer --skill express -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install swingerman/engineer express --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/swingerman/engineer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/engineer/skills/express .claude/skills/express && 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 "express" agent skill from https://github.com/swingerman/engineer/tree/master/engineer/skills/express into .claude/skills/express/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "express", 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/swingerman/engineer/tree/master/engineer/skills/expressType 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 swingerman/engineer --skill express -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install swingerman/engineer express --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swingerman/engineer.git skills-src && mkdir -p .agents/skills && cp -r skills-src/engineer/skills/express .agents/skills/express && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "express" agent skill from https://github.com/swingerman/engineer/tree/master/engineer/skills/express into .agents/skills/express/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "express", 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 swingerman/engineer --skill express -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install swingerman/engineer express --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swingerman/engineer.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/engineer/skills/express .cursor/skills/express && 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 "express" agent skill from https://github.com/swingerman/engineer/tree/master/engineer/skills/express into .cursor/skills/express/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "express", 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/swingerman/engineer.git --path engineer/skills/express--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 swingerman/engineer --skill express -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install swingerman/engineer express --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swingerman/engineer.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/engineer/skills/express .gemini/skills/express && 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 "express" agent skill from https://github.com/swingerman/engineer/tree/master/engineer/skills/express into .gemini/skills/express/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "express", 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 swingerman/engineer expressInstalls 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 swingerman/engineer --skill express -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/swingerman/engineer.git skills-src && mkdir -p .github/skills && cp -r skills-src/engineer/skills/express .github/skills/express && 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 "express" agent skill from https://github.com/swingerman/engineer/tree/master/engineer/skills/express into .github/skills/express/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "express", 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 swingerman/engineer --skill express -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install swingerman/engineer express --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swingerman/engineer.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/engineer/skills/express .opencode/skills/express && 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 "express" agent skill from https://github.com/swingerman/engineer/tree/master/engineer/skills/express into .opencode/skills/express/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "express", 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
express- GitHub stars
- 154
- Token cost
- ~1.1k tokens
- SKILL.md length
- 525 words
- Files
- 1
- Skills in repo
- 27
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses to build an XS (express-lane) feature in one pass — intake→implement→verify in a single context, no handoff chain, code-first.
- Works in 7 steps: Resolve + branch — root + manifest via… → Pin behavior (test = spec) — write one… → Implement to green — build the minimum… → …
- Build an XS (express-lane) feature in one pass — intake→implement→verify in a single context
- SKILL.md covers When to use, Workflow, Handoff and References
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Express is an agent skill from swingerman/engineer. Use to build an XS (express-lane) feature in one pass — intake→implement→verify in a single context, no handoff chain, code-first. Triggers — "/engineer.express", "express build", building a feature whose gateprofile.lane is express.
Its SKILL.md is about 1.1k 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. The repository describes itself as: Disciplined Agentic Engineering — a methodology kit for Claude Code: acceptance-test-first specs, explicit checkpoints, and autonomy you can actually leave running. The engineer… The licence is MIT.
When your agent uses it
- Build an XS (express-lane) feature in one pass — intake→implement→verify in a single context
- No handoff chain
- — /engineer.express
- Building a feature whose gateprofile.lane is express
Example prompts
- “/engineer.express”
- “express build”
- “/express”
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Resolve + branch — root + manifest via ${CLAUDE_PLUGIN_ROOT}/scripts/dae_resolve.py;
- Pin behavior (test = spec) — write one Given/When/Then acceptance test
- Implement to green — build the minimum that passes the test. Code-first;
- Verify (light) — run the deterministic gates: the acceptance test + CRAP +
- Code-over-doc check — non-code doc chars must not exceed code chars for
- Escalation ratchet (one-way up) — if at any point the change is more than
- Land — open the PR; update the tracker row via the driver
What it can do on your machine
Read from SKILL.md and the folder at commit 32947eb. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Express loads about 1.1k tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 525 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 swingerman/engineer at commit 32947eb, republished under its MIT licence (© swingerman). 525 words, ~1,131 tokens.
Download SKILL.mdSave it as
.claude/skills/express/SKILL.md (or your agent's skills folder).- name
- express
- description
- Use to build an XS (express-lane) feature in one pass — intake→implement→verify in a single context, no handoff chain, code-first. Triggers — "/engineer.express", "express build", building a feature whose gate_profile.lane is express.
express
The express lane for size: XS features (${CLAUDE_PLUGIN_ROOT}/references/express-lane.md).
One born-die agent runs intake → implement → verify in a single context — no
CP2→CP8 handoff chain, no sub-agents, no acs.md/spec.md/plan.md. The
acceptance test is the spec; docs stay capped below code. Same tracker row and
deterministic gates as any feature — just without the per-checkpoint re-prime
that dominates a normal feature's cost.
Runs after feature-init has created the size: XS feature (or a converged
prototype landed at prototype_disposition: in-place).
When to use
feature-inithanded off a feature withgate_profile.lane: express.- A converged XS prototype (
in-place) — the prototype code is the starting implementation.
Not for: anything charter-flagged (payments/auth/migration/blast-radius),
autonomy_level: low, or bigger than ~1 PR — those take the full pipeline. If
you find yourself here on one of them, escalate (Step 5).
Workflow
Do the whole thing in one context. No sub-agents, no inter-phase handoffs.
- Resolve + branch — root + manifest via
${CLAUDE_PLUGIN_ROOT}/scripts/dae_resolve.py; loadfeature.md+CHARTER.md(+prototype/ifin-place). Enforce branch hygiene via${CLAUDE_PLUGIN_ROOT}/scripts/dae_branch.py. Re-check the guardrails — charter-flagged orautonomy_level: low→ stop, hand to the full pipeline (discover-acs); express is not for those. - Pin behavior (test = spec) — write one Given/When/Then acceptance test
that defines done. If a prototype is the seed, reverse-engineer the test from
what it demonstrates. This replaces
acs.md+spec.md; do not write them. - Implement to green — build the minimum that passes the test. Code-first;
the only prose allowed is a ≤5-line approach note in
feature.md, and only if the diff is not self-evident. Prototypein-place: the prototype code is the start — clean it, don't rewrite. - Verify (light) — run the deterministic gates: the acceptance test + CRAP +
${CLAUDE_PLUGIN_ROOT}/scripts/dae_ontology.py+dae_arch. LLM attention only on red. No mutation, no gauntlet, no review-panel. - Code-over-doc check — non-code doc chars must not exceed code chars for this feature; if they do, surface a one-line note (inform, don't block).
- Escalation ratchet (one-way up) — if at any point the change is more than
~1 PR (decomposition trips, hidden coupling, the acceptance test won't close),
promote to full S/M: write the missing
acs.md/spec.md/plan.md, hand todiscover-acs/plan, keep the tracker row and branch. Never downgrade silently. - Land — open the PR; update the tracker row via the driver
(
references/tracker.md). Back gate isverify: light— present it as a choice point (${CLAUDE_PLUGIN_ROOT}/references/choice-points.md): recommend merge on green gates,autonomy_level-dialed. Honor the external-write gate (PR merge is human unlessverify: auto+dae_mergereadygreen).
Show full SKILL.md (133 more words)Show less
Handoff
Emit per ${CLAUDE_PLUGIN_ROOT}/references/handoff-summary.md. One handoff for
the whole lane (not one per phase) — checkpoint: null: express is off the
numbered pipeline (like discuss/prototype), so it carries no CP2→CP8 stop
and its deterministic gates — not an independent LLM reviewer — are the verifier
(the disjoint-verifier principle is satisfied by the scripts, and the numbered-
pipeline completeness checks do not apply to an XS feature). recommended_next:
"review the PR" (or auto-merge note if verify: auto). On escalation, the
feature joins the numbered pipeline — emit status: escalated naming what
tripped and pointing at discover-acs (CP2 onward).
References
${CLAUDE_PLUGIN_ROOT}/references/express-lane.md— the XS contract, guardrails, ratchet${CLAUDE_PLUGIN_ROOT}/references/gate-profile.md— thesizedial (XS = this lane)${CLAUDE_PLUGIN_ROOT}/references/choice-points.md— the projection that sized it XS + the back-gate choice point- Sister skills:
feature-init(creates the XS feature),discover-acs(the escalation target),prototype(thein-placeseed).
© swingerman, 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 engineer/skills/express of swingerman/engineer.
Open the folder on GitHubat commit 32947eb
Compare with similar skills
Express 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 |
|---|---|---|---|---|---|---|
| Express this skillswingerman/engineer | 154 | — | ~1.1k | Automated safety check: Pass | MIT | |
| OpenHarness End-to-End EvalsHKUDS/OpenHarness | 16k | 1 repos | ~2.1k | Automated safety check: Notes | MIT | |
| Clawteam DevHKUDS/ClawTeam | 5.5k | 1 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Acceptance Evidence for Deliverieslobehub/lobehub | 83k | — | ~9.7k | Automated safety check: Pass | Apache-2.0 | |
| Qwen Code E2E TestingQwenLM/qwen-code | 28k | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| Skill Testdatabricks-solutions/ai-dev-kit | 1.9k | — | ~1.9k | Automated safety check: Pass | Custom licence |
Similar skills
Clawteam Dev
HKUDS/ClawTeam
A skill your agent uses when working inside the ClawTeam repository itself: local development, debugging, reviewing, testing, validating multi-agent flows, or checking whether a code change actually…
Acceptance Evidence for Deliveries
lobehub/lobehub
Verifies a delivery end to end by driving the real product on a CLI, web, desktop or iOS Simulator surface, capturing evidence and publishing a round with the lh CLI.
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.
Skill Test
databricks-solutions/ai-dev-kit
Testing framework for evaluating Databricks skills. An agent skill from databricks-solutions/ai-dev-kit.
Adding LLM MCP Tools
TriliumNext/Trilium
A skill your agent uses when adding, changing, or reviewing an LLM/MCP tool in Trilium (the defineTools definitions under packages/trilium-core/src/services/llm/tools/ —…
More from swingerman/engineer
All 27 skills in this repoCrap Analyzer
swingerman/engineer
A skill your agent uses to produce a risk-based refactor + test plan for recently-changed code on a diff/branch/PR by computing CRAP (complexity × untested) on changed methods.
Atdd Mutate
swingerman/engineer
A skill your agent uses to add a third validation layer to the ATDD workflow — after acceptance tests verify WHAT and unit tests verify HOW, mutation testing verifies the tests actually catch bugs.
Fix
swingerman/engineer
A skill your agent uses to drive a bug fix from first report through close, with a "why didn't we catch it?" loop at the end.
Atdd
swingerman/engineer
A skill your agent uses to drive feature work through the Acceptance Test Driven Development workflow — Given/When/Then specs before code, a project-specific test pipeline, and two parallel test…
Harden
swingerman/engineer
Use after a feature passes Light Verify (CP7), to prove the tests actually catch bugs and, where the code warrants it, to formally check its invariants — Checkpoint 8.
Next
swingerman/engineer
Use at the start of a work session, or any time the question is "what should I pick up now" across the whole project.
Related
Categories
Questions about Express
What does Express do?
A skill your agent uses to build an XS (express-lane) feature in one pass — intake→implement→verify in a single context, no handoff chain, code-first. Express is an agent skill from swingerman/engineer. Use to build an XS (express-lane) feature in one pass — intake→implement→verify in a single context, no handoff chain, code-first.
When should I use Express?
Express fits situations like: build an XS (express-lane) feature in one pass — intake→implement→verify in a single context; no handoff chain; — /engineer.express; building a feature whose gateprofile.lane is express.
How do I install Express in Claude Code?
Run `npx skills add swingerman/engineer --skill express -a claude-code`. Or copy the skill folder (engineer/skills/express in swingerman/engineer) into .claude/skills/express in your project. Claude Code loads it when a task matches its description.
How do I install Express in Codex?
Run `npx skills add swingerman/engineer --skill express -a codex`. Or copy the skill folder (engineer/skills/express in swingerman/engineer) into .agents/skills/express in your project. Codex loads it when a task matches its description.
Can I use Express 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 swingerman/engineer --skill express -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/express, .gemini/skills/express, .github/skills/express and .opencode/skills/express in your project.
What does Express need to run?
SKILL.md names no scripts, command-line tools or credentials: Express is instructions for the agent only.
Does Express access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Express 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 Express use?
Express 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 Express use?
About 1.1k tokens (SKILL.md is roughly 4.5k 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 Express?
Skills that share tags, products or a category with Express: OpenHarness End-to-End Evals (HKUDS/OpenHarness, 16k stars), Clawteam Dev (HKUDS/ClawTeam, 5.5k stars), Acceptance Evidence for Deliveries (lobehub/lobehub, 83k stars) and Qwen Code E2E 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.
Who maintains Express?
swingerman (a GitHub user) maintains it in swingerman/engineer, which has 154 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on September 23, 2026.
Source: swingerman/engineer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.