raalarcon9705/gated-dev-agents
Claude Code plugin: evidence-gated implementer, spec/code-quality reviewers, blind pre-mortem, QA verifier and e2e runner subagents + gate skills
stack: Shell
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit raalarcon9705/gated-dev-agents/agents ./rig-gated-dev-agents/agents $ npx degit raalarcon9705/gated-dev-agents/skills ./rig-gated-dev-agents/skills
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 raalarcon9705/gated-dev-agents/skills/implementing-with-gates .claude/skills/implementing-with-gates $ npx degit raalarcon9705/gated-dev-agents/skills/running-e2e-verification .claude/skills/running-e2e-verification $ npx degit raalarcon9705/gated-dev-agents/skills/verifying-changes .claude/skills/verifying-changes
$ curl -fsSL --create-dirs -o .claude/agents/code-quality-reviewer.md https://raw.githubusercontent.com/raalarcon9705/gated-dev-agents/main/agents/code-quality-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/diff-premortem.md https://raw.githubusercontent.com/raalarcon9705/gated-dev-agents/main/agents/diff-premortem.md $ curl -fsSL --create-dirs -o .claude/agents/e2e-runner.md https://raw.githubusercontent.com/raalarcon9705/gated-dev-agents/main/agents/e2e-runner.md $ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/raalarcon9705/gated-dev-agents/main/agents/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/qa-verifier.md https://raw.githubusercontent.com/raalarcon9705/gated-dev-agents/main/agents/qa-verifier.md $ curl -fsSL --create-dirs -o .claude/agents/spec-reviewer.md https://raw.githubusercontent.com/raalarcon9705/gated-dev-agents/main/agents/spec-reviewer.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 (3)
Subagents (6)
| code-quality-reviewer model: sonnet | Code quality reviewer for the subagent-driven-development code-quality step (and the final whole-branch review). Use ONLY after spec-reviewer returned ✅ — pass the task summary, the plan task text or |
| diff-premortem model: sonnet | Blind pre-mortem review of a diff. Use when verifying a change and an unbiased risk read is needed — pass ONLY the repo path and diff range/commit, never the ticket, plan or intent. |
| e2e-runner model: sonnet | Runs end-to-end browser flows or smoke tests against an environment (local/dev/staging/prod) and returns a PASS/FAIL verdict with evidence. Use proactively when a change needs real end-to-end verifica |
| implementer model: sonnet | Implements a scoped feature, bugfix or refactor in any repo from a plan task, ticket or bead, ending in committed, verified code. Use proactively for implementation tasks, and for the implementation s |
| qa-verifier model: sonnet | Independently verifies a change, PR, branch, ticket or bead against its acceptance criteria and returns a PASS/FAIL verdict with evidence. Use proactively after implementation, before merge or marking |
| spec-reviewer model: sonnet | Spec compliance reviewer for the subagent-driven-development spec-review step. Use after an implementer reports DONE on a task, before code quality review — pass the FULL task text, the implementer's |
Similar rigs
Tamircohen28/tamirs-superpowers
A portable agent toolkit — 31 skills, 10 specialist agents, worktree hooks and MCP stubs — shipped from one canonical source to six agent surfaces across five platforms: Claude Code, Claude Desktop, Codex, Cursor, Gemini CLI and OpenCode.
Orchestrator 7.0k tok · · Q18
zmilojevic/hearth
Keep your Claude Code sessions warm. Desktop app for Claude Code, Linux-first (also macOS/Windows): all your sessions in one sidebar, diffs, terminal, cache keep-warm, phone companion. Uses your Claude subscription, no API key.
Pragmatist 14.7k tok · · Q25
yellow-pine/noggin
Animatronic CyberBrick head that reacts to Claude Code
Minimalist 1.5k tok · · Q29
yhnocoder/agentrun
Run claude-code, codex and pi in a sandbox with one command, on macOS, Linux, cloud containers and docker.
Minimalist 1.1k tok · · Q15