boshu2/agentops
DevOps discipline for AI coding agents: shape the work, track it as a graph, and get each change judged by a context that didn't write it.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code $ npx degit boshu2/agentops/agents ./rig-agentops/agents $ npx degit boshu2/agentops/skills ./rig-agentops/skills $ npx degit boshu2/agentops/hooks ./rig-agentops/hooks
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 boshu2/agentops/packs/agentops-executor/agents/implementer-claude/skills/implement .claude/skills/implement $ npx degit boshu2/agentops/packs/agentops-executor/agents/validator/skills/validate .claude/skills/validate $ npx degit boshu2/agentops/packs/agentops-executor/skills/using-gc .claude/skills/using-gc $ npx degit boshu2/agentops/skills/agent-native .claude/skills/agent-native $ npx degit boshu2/agentops/skills/agy-native .claude/skills/agy-native $ npx degit boshu2/agentops/skills/claude-exec .claude/skills/claude-exec $ npx degit boshu2/agentops/skills/codex-exec .claude/skills/codex-exec $ npx degit boshu2/agentops/skills/council .claude/skills/council $ npx degit boshu2/agentops/skills/craft-goal .claude/skills/craft-goal $ npx degit boshu2/agentops/skills/doc .claude/skills/doc $ npx degit boshu2/agentops/skills/domain .claude/skills/domain $ npx degit boshu2/agentops/skills/idea-genie .claude/skills/idea-genie $ npx degit boshu2/agentops/skills/interview .claude/skills/interview $ npx degit boshu2/agentops/skills/memory .claude/skills/memory $ npx degit boshu2/agentops/skills/navigate .claude/skills/navigate $ npx degit boshu2/agentops/skills/orchestrate .claude/skills/orchestrate $ npx degit boshu2/agentops/skills/plan .claude/skills/plan $ npx degit boshu2/agentops/skills/postmortem .claude/skills/postmortem $ npx degit boshu2/agentops/skills/premortem .claude/skills/premortem $ npx degit boshu2/agentops/skills/reality-check .claude/skills/reality-check $ npx degit boshu2/agentops/skills/refactor .claude/skills/refactor $ npx degit boshu2/agentops/skills/research .claude/skills/research $ npx degit boshu2/agentops/skills/reverse-engineer .claude/skills/reverse-engineer $ npx degit boshu2/agentops/skills/review .claude/skills/review $ npx degit boshu2/agentops/skills/rpi .claude/skills/rpi $ npx degit boshu2/agentops/skills/security .claude/skills/security $ npx degit boshu2/agentops/skills/skill-builder .claude/skills/skill-builder $ npx degit boshu2/agentops/skills/skill-eval .claude/skills/skill-eval
$ curl -fsSL --create-dirs -o .claude/agents/bulk-reader.md https://raw.githubusercontent.com/boshu2/agentops/main/agents/bulk-reader.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/boshu2/agentops/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/code-writer.md https://raw.githubusercontent.com/boshu2/agentops/main/agents/code-writer.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/boshu2/agentops/main/agents/researcher.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (28)
implementvalidateusing-gcagent-nativeagy-nativeclaude-execcodex-execcouncilcraft-goaldocdomainidea-genieinterviewmemorynavigateorchestrateplanpostmortempremortemreality-checkrefactorresearchreverse-engineerreviewrpisecurityskill-builderskill-eval
Subagents (4)
| bulk-reader model: haiku | Read large files or many files on the caller's behalf and return short line-referenced summaries with coverage. Use when a file exceeds the read budget or the read-budget guard blocked a Read. |
| code-reviewer model: sonnet | Expert code review specialist. Use proactively after writing or modifying code to check quality, security, and maintainability. |
| code-writer model: haiku | Write one file from a spec plus a required reference file, matching the reference's patterns, and return a receipt (path, line count, check result) without echoing the content. Use for patterned or bo |
| researcher model: haiku | Deep codebase exploration and analysis. Use for understanding code architecture, finding patterns, and gathering context before making changes. |
Similar rigs
pruthvidarji1993/ai-automation-jira
AI-assisted dev workflow: Jira ticket in, reviewed PR out. Claude Code plugin + GitHub Copilot prompts with human approval gates (plan, diff).
Pragmatist 2.0k tok ·
kento-cell/claude-dotfiles
Portable Claude Code environment: settings, custom skills, agents, memory, and one-command setup script
Pragmatist 756 tok ·
lamngockhuong/aiteamkit
Multi-harness AI plugin for Claude Code, Cursor and Codex CLI: skills that run the delivery lifecycle of a project team - intake, estimate, design, spec, breakdown, plan, implement, fix, review, QA, verify, release, incident, retro, onboard
Skill Collector 26.8k tok ·
nicodiansk/turboflow
Opinionated engineering pipeline for Claude Code with 10 skills, 5 agents, 2 hooks. Replaces ad-hoc agent sprawl with brainstorm → story → plan → build → review → ship.
Orchestrator 1.9k tok ·