XingMXTeam/frontend-harness-cli
Harness kernel for long-running frontend AI coding — per-feature rubrics with veto evaluation, a five-dimension code sensor, and a bundled skills pack.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/XingMXTeam/frontend-harness-cli MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit XingMXTeam/frontend-harness-cli/templates/skills/api-testing .claude/skills/api-testing $ npx degit XingMXTeam/frontend-harness-cli/templates/skills/bug-root-cause .claude/skills/bug-root-cause $ npx degit XingMXTeam/frontend-harness-cli/templates/skills/clarify-requirements .claude/skills/clarify-requirements $ npx degit XingMXTeam/frontend-harness-cli/templates/skills/component-from-design .claude/skills/component-from-design $ npx degit XingMXTeam/frontend-harness-cli/templates/skills/context-map .claude/skills/context-map $ npx degit XingMXTeam/frontend-harness-cli/templates/skills/deterministic-eval .claude/skills/deterministic-eval $ npx degit XingMXTeam/frontend-harness-cli/templates/skills/e2e-testing .claude/skills/e2e-testing $ npx degit XingMXTeam/frontend-harness-cli/templates/skills/fix-from-report .claude/skills/fix-from-report $ npx degit XingMXTeam/frontend-harness-cli/templates/skills/i18n-extract .claude/skills/i18n-extract $ npx degit XingMXTeam/frontend-harness-cli/templates/skills/implement-task .claude/skills/implement-task $ npx degit XingMXTeam/frontend-harness-cli/templates/skills/plan-before-code .claude/skills/plan-before-code $ npx degit XingMXTeam/frontend-harness-cli/templates/skills/ship-checklist .claude/skills/ship-checklist $ npx degit XingMXTeam/frontend-harness-cli/templates/skills/state-schema-first .claude/skills/state-schema-first $ npx degit XingMXTeam/frontend-harness-cli/templates/skills/sync-overview .claude/skills/sync-overview $ npx degit XingMXTeam/frontend-harness-cli/templates/skills/systematic-debugging .claude/skills/systematic-debugging $ npx degit XingMXTeam/frontend-harness-cli/templates/skills/verification-before-completion .claude/skills/verification-before-completion $ npx degit XingMXTeam/frontend-harness-cli/templates/skills/write-acceptance-criteria .claude/skills/write-acceptance-criteria $ npx degit XingMXTeam/frontend-harness-cli/templates/skills/write-dev-plan .claude/skills/write-dev-plan $ npx degit XingMXTeam/frontend-harness-cli/templates/skills/write-prd .claude/skills/write-prd $ npx degit XingMXTeam/frontend-harness-cli/templates/skills/write-quality-vision .claude/skills/write-quality-vision $ npx degit XingMXTeam/frontend-harness-cli/templates/skills/write-tech-design .claude/skills/write-tech-design
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (21)
api-testingbug-root-causeclarify-requirementscomponent-from-designcontext-mapdeterministic-evale2e-testingfix-from-reporti18n-extractimplement-taskplan-before-codeship-checkliststate-schema-firstsync-overviewsystematic-debuggingverification-before-completionwrite-acceptance-criteriawrite-dev-planwrite-prdwrite-quality-visionwrite-tech-design
Similar rigs
malkreide/claude-config
Personal Claude config: global CLAUDE.md, vendored Superpowers skills and helper scripts
Minimalist 1.0k tok · · Q0
Viqto0r/zames_pro
Terminal coding agent that drives chat.deepseek.com or chat.qwen.ai through Playwright — no API key required. Reads/edits files, runs commands, commits to git.
Pragmatist 11.3k tok · · Q8
ingeun92/claude-code-configs
—
Pragmatist 468 tok · · Q0
taiyyoson/my-claude-code
Version-controlled Claude Code setup with three working modes
Pragmatist 1.1k tok · · Q0