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 a planned round handoff exists and needs to be implemented end-to-end via the 4-commit chain (entry-admin → BA design → dev body with inline CR + SE → state refresh +…
Install Execute Round
$ npx skills add Arch1eSUN/Arcgentic --skill execute-round -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Arch1eSUN/Arcgentic execute-round --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/Arch1eSUN/Arcgentic.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/execute-round .claude/skills/execute-round && 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 "execute-round" agent skill from https://github.com/Arch1eSUN/Arcgentic/tree/main/skills/execute-round into .claude/skills/execute-round/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execute-round", 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/Arch1eSUN/Arcgentic/tree/main/skills/execute-roundType 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 Arch1eSUN/Arcgentic --skill execute-round -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Arch1eSUN/Arcgentic execute-round --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Arch1eSUN/Arcgentic.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/execute-round .agents/skills/execute-round && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "execute-round" agent skill from https://github.com/Arch1eSUN/Arcgentic/tree/main/skills/execute-round into .agents/skills/execute-round/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execute-round", 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 Arch1eSUN/Arcgentic --skill execute-round -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Arch1eSUN/Arcgentic execute-round --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Arch1eSUN/Arcgentic.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/execute-round .cursor/skills/execute-round && 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 "execute-round" agent skill from https://github.com/Arch1eSUN/Arcgentic/tree/main/skills/execute-round into .cursor/skills/execute-round/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execute-round", 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/Arch1eSUN/Arcgentic.git --path skills/execute-round--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 Arch1eSUN/Arcgentic --skill execute-round -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Arch1eSUN/Arcgentic execute-round --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Arch1eSUN/Arcgentic.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/execute-round .gemini/skills/execute-round && 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 "execute-round" agent skill from https://github.com/Arch1eSUN/Arcgentic/tree/main/skills/execute-round into .gemini/skills/execute-round/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execute-round", 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 Arch1eSUN/Arcgentic execute-roundInstalls 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 Arch1eSUN/Arcgentic --skill execute-round -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Arch1eSUN/Arcgentic.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/execute-round .github/skills/execute-round && 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 "execute-round" agent skill from https://github.com/Arch1eSUN/Arcgentic/tree/main/skills/execute-round into .github/skills/execute-round/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execute-round", 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 Arch1eSUN/Arcgentic --skill execute-round -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Arch1eSUN/Arcgentic execute-round --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Arch1eSUN/Arcgentic.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/execute-round .opencode/skills/execute-round && 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 "execute-round" agent skill from https://github.com/Arch1eSUN/Arcgentic/tree/main/skills/execute-round into .opencode/skills/execute-round/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execute-round", 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
execute-round- GitHub stars
- 286
- Token cost
- ~954 tokens
- SKILL.md length
- 385 words
- Files
- 1
- Skills in repo
- 19
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when a planned round handoff exists and needs to be implemented end-to-end via the 4-commit chain (entry-admin → BA design → dev body with inline CR + SE → state refresh +…
- Works in 5 steps: Verify the handoff doc exists at… → Shell out → The CLI orchestrates 4 phases → …
- Testing & QA work in your project
- SKILL.md covers When to invoke, Prerequisites, Inputs and Workflow, plus 3 more sections
- Calls pipx and pip
What it does
Execute Round is an agent skill from Arch1eSUN/Arcgentic. Use when a planned round handoff exists and needs to be implemented end-to-end via the 4-commit chain (entry-admin → BA design → dev body with inline CR + SE → state refresh + self-audit). Dispatches ba-designer / developer / cr-reviewer / se-contract sequentially.
Its SKILL.md is about 950 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: Mechanical plan/dev/self-audit/external-audit gates for AI coding agents, with a configurable role-routing topology engine, an MCP-UI live status panel, and native-tooling Claude… The licence is MIT.
When your agent uses it
- Testing & QA work in your project
Example prompts
- “/execute-round”
Requirements
- Python 3
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Verify the handoff doc exists at handoff_path.
- Shell out
- The CLI orchestrates 4 phases
- Read CLI output for result summary (per ExecuteRoundResult.summary())
- Report to user: 4 commit SHAs + findings counts + handoff path.
What it can do on your machine
Read from SKILL.md and the folder at commit 8539955. 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:
pipxpip
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pipx and pip, 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
Execute Round loads about 954 tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 385 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 Arch1eSUN/Arcgentic at commit 8539955, republished under its MIT licence (© Arch1eSUN). 385 words, ~954 tokens.
Download SKILL.mdSave it as
.claude/skills/execute-round/SKILL.md (or your agent's skills folder).- name
- execute-round
- description
- Use when a planned round handoff exists and needs to be implemented end-to-end via the 4-commit chain (entry-admin → BA design → dev body with inline CR + SE → state refresh + self-audit). Dispatches ba-designer / developer / cr-reviewer / se-contract sequentially.
execute-round
Orchestrates the 4-commit chain for an arcgentic round per spec § 4.2.3. Reads the planned
handoff (from plan-round skill or hand-authored), then executes Phase 1-4 via the
arcgentic Python CLI.
When to invoke
- User says "let's execute round R{N}" or "run the 4-commit chain for the handoff at ..."
- User runs
/execute-round <round_name>slash command - A handoff doc exists at
docs/superpowers/plans/...and dev work is ready to start
Prerequisites
Requires the arcgentic CLI:
- Stable:
pipx install arcgentic - Dev:
cd toolkit && pip install -e ".[dev]"
Requires a planned handoff doc — run /plan-round first if missing.
V1 projects must resolve the session-mode gate before implementation. If
project.session_mode.mode is already present in .agentic-rounds/state.yaml,
use it and do not ask again:
arcgentic session-mode recommend --round=$ROUND --handoff=$HANDOFF_PATH
arcgentic session-mode prompt --round=$ROUND --handoff=$HANDOFF_PATH --mode=multi-session --role=developerInputs
Parse from $ARGUMENTS:
round_name(e.g. "R10-L3-aletheia")handoff_path(defaults to most recentdocs/superpowers/plans/{date}-{round}-handoff.md)--dry-runflag (optional; skip all commits and pushes)
Workflow
When invoked:
Verify the handoff doc exists at
handoff_path.Shell out:
arcgentic execute-round-impl --round=$ROUND --handoff=$HANDOFF_PATH [--dry-run]The CLI orchestrates 4 phases:
- Phase 1 — Entry-admin commit: commit handoff + state-row updates
- Phase 2 — BA design pass: dispatch ba-designer → write design doc → commit
- Phase 3 — Dev body: dispatch developer → run pre-audit quality gates (mypy / pytest / ruff) → inline CR step → inline SE step (MANDATE #20: NO BA design in SE brief) → commit
- Phase 4 — State refresh + self-audit handoff: compose self-audit handoff doc with stable artifact/fixed-anchor facts → run
arcgentic audit-check --strict-extended→ write → commit
Read CLI output for result summary (per ExecuteRoundResult.summary()):
- 4 phase results with commit SHAs
- CR + SE findings counts
- Quality gate statuses
- Self-audit handoff path
Report to user: 4 commit SHAs + findings counts + handoff path.
Show full SKILL.md (125 more words)Show less
Known limitations (forward-debts)
- ER-RETRY: no retry-with-context loops; if any sub-agent dispatch fails, the run aborts. Re-invoke after fixing the failure manually.
- ER-AUDIT-FACTS-RICH: self-audit facts avoid mutable current-state / moving-HEAD assertions, but rich commit-chain / changed-file fact generation is future work.
- ER-STATE-ROW: Phase 1's CLAUDE.md state-row update is a NO-OP (project-agnostic).
See docs/tech-debt.md for the full forward-debt registry.
Failure modes
- Missing handoff doc: re-run
/plan-roundfirst. - CLI not installed: instruct user to
pipx install arcgentic. - Sub-agent dispatch failure: re-invoke after fixing (no automatic retry in v0.2.0 P0).
- Quality gate FAIL: developer output had errors; review BA design + fix dev output manually; re-invoke.
See also
agents/ba-designer.md/developer.md/cr-reviewer.md/se-contract.md— agents dispatchedtemplates/ba_design.md/self_audit_handoff.md— output structure templatestoolkit/src/arcgentic/skills_impl/execute_round.py— Python algorithmskills/session-mode/SKILL.md— V1 pre-dev identity gate- spec § 4.2 — full skill specification
© Arch1eSUN, 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 skills/execute-round of Arch1eSUN/Arcgentic.
Open the folder on GitHubat commit 8539955
Compare with similar skills
Execute Round 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 |
|---|---|---|---|---|---|---|
| Execute Round this skillArch1eSUN/Arcgentic | 286 | — | ~954 | 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 Arch1eSUN/Arcgentic
All 19 skills in this repoAudit Round
Arch1eSUN/Arcgentic
External-audit role for arcgentic rounds. An agent skill from Arch1eSUN/Arcgentic.
Orchestrate Round
Arch1eSUN/Arcgentic
Main-session orchestrator for arcgentic rounds. An agent skill from Arch1eSUN/Arcgentic.
Verify Gates
Arch1eSUN/Arcgentic
Runs the mechanical quality gates that the arcgentic state machine requires for state transitions.
Arcgentic
Arch1eSUN/Arcgentic
A skill your agent uses when the user mentions Arcgentic, or wants substantial AI-written code taken through a gated plan → development → self-audit → external audit workflow with role handoffs and…
Arcgentic
Arch1eSUN/Arcgentic
A skill your agent uses when the user says Arcgentic, asks to use Arcgentic, or wants an idea taken through a complete plan → development → self-audit → external audit workflow in Codex.
Claude Code Session Broker
Arch1eSUN/Arcgentic
A skill your agent uses when running Arcgentic V2 in Claude Code and fixed Planner, Developer, and Auditor role sessions must be coordinated through a broker.
Related
Categories
Questions about Execute Round
What does Execute Round do?
A skill your agent uses when a planned round handoff exists and needs to be implemented end-to-end via the 4-commit chain (entry-admin → BA design → dev body with inline CR + SE → state refresh +…. Execute Round is an agent skill from Arch1eSUN/Arcgentic. Use when a planned round handoff exists and needs to be implemented end-to-end via the 4-commit chain (entry-admin → BA design → dev body with inline CR + SE → state refresh + self-audit).
When should I use Execute Round?
Execute Round fits situations like: testing & QA work in your project.
How do I install Execute Round in Claude Code?
Run `npx skills add Arch1eSUN/Arcgentic --skill execute-round -a claude-code`. Or copy the skill folder (skills/execute-round in Arch1eSUN/Arcgentic) into .claude/skills/execute-round in your project. Claude Code loads it when a task matches its description.
How do I install Execute Round in Codex?
Run `npx skills add Arch1eSUN/Arcgentic --skill execute-round -a codex`. Or copy the skill folder (skills/execute-round in Arch1eSUN/Arcgentic) into .agents/skills/execute-round in your project. Codex loads it when a task matches its description.
Can I use Execute Round 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 Arch1eSUN/Arcgentic --skill execute-round -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/execute-round, .gemini/skills/execute-round, .github/skills/execute-round and .opencode/skills/execute-round in your project.
What does Execute Round need to run?
Going by SKILL.md and its folder, Execute Round needs the command-line tools its instructions call (pipx and pip). Our summary lists: Python 3.
Does Execute Round access the network?
SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Execute Round 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 Execute Round use?
Execute Round 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 Execute Round use?
About 954 tokens (SKILL.md is roughly 3.8k 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 Execute Round?
Skills that share tags, products or a category with Execute Round: 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 Execute Round?
Arch1eSUN (a GitHub user) maintains it in Arch1eSUN/Arcgentic, which has 286 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 2, 2026.
Source: Arch1eSUN/Arcgentic on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.