danylo-morhun/taskly-test-agent
AI unit-test agent (Claude Code) with reusable skills and an agentic GitHub PR workflow, built on the Taskly full-stack app
field: unknown workflow: Testing & TDDPR / code reviewFrontend & designSecurity review runs claude in CI
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit danylo-morhun/taskly-test-agent/.claude ./rig-taskly-test-agent # inspect, then merge into .claude/ 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 danylo-morhun/taskly-test-agent/.claude/skills/backend-unit-tests .claude/skills/backend-unit-tests $ npx degit danylo-morhun/taskly-test-agent/.claude/skills/frontend-unit-tests .claude/skills/frontend-unit-tests $ npx degit danylo-morhun/taskly-test-agent/.claude/skills/test-impact-analysis .claude/skills/test-impact-analysis $ npx degit danylo-morhun/taskly-test-agent/.claude/skills/test-report .claude/skills/test-report $ npx degit danylo-morhun/taskly-test-agent/.claude/skills/test-verification .claude/skills/test-verification
$ curl -fsSL --create-dirs -o .claude/agents/unit-test-agent.md https://raw.githubusercontent.com/danylo-morhun/taskly-test-agent/main/.claude/agents/unit-test-agent.md 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 (5)
Subagents (1)
| unit-test-agent | Senior test engineer agent. Analyzes a code change (a pull request diff or explicit target files), decides where unit tests are warranted, writes or updates them for the backend (Express/Prisma) and f |
Permissions
deny (0)
—
ask (0)
—
allow (12)
Bash(node .claude/skills/test-impact-analysis/scripts/detect-changes.mjs *)
Bash(node .claude/skills/test-verification/scripts/run-tests.mjs *)
Bash(node .claude/skills/test-verification/scripts/patch-coverage.mjs *)
Bash(node .claude/skills/test-verification/scripts/mutation-test.mjs *)
Bash(node .claude/skills/test-verification/scripts/check-test-policy.mjs *)
Bash(node .claude/skills/test-verification/scripts/verify.mjs *)
Bash(node .claude/skills/test-report/scripts/render-report.mjs *)
Bash(node .claude/skills/test-report/scripts/validate-report.mjs *)
Bash(git diff *)
Bash(git log *)
Bash(git show *)
Bash(git status *)
Similar rigs
gdtknight/dotconfig
Declarative cross-platform dotfiles for macOS & Ubuntu: Neovim (LazyVim), 3-vendor AI agent harness (Claude/Gemini/Codex), Dev Container 2.0 CLI & multi-account Git.
Orchestrator 1.7k tok · · Q3
wangqiqi/cursor-ai
无关用户, 无关系统, 无关项目,开箱复制即用! code faster, code better;
Skill Collector 2.8k tok · · Q0
slasher-bot/slasher
Slasher: Human in the loop harness
Skill Collector 3.8k tok · · Q18
anomalyco/opencode
The open source coding agent.
Pragmatist 14.3k tok · · Q8