deepeshBodh/human-in-loop
SPEC-first multi-agent framework for Claude Code.
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 deepeshBodh/human-in-loop/.claude ./rig-human-in-loop # 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 deepeshBodh/human-in-loop/.claude/skills/auditing-agents .claude/skills/auditing-agents $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/analysis-codebase .claude/skills/analysis-codebase $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/analysis-iterative .claude/skills/analysis-iterative $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/analysis-screenshot .claude/skills/analysis-screenshot $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/analysis-specifications .claude/skills/analysis-specifications $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/authoring-constitution .claude/skills/authoring-constitution $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/authoring-design-system .claude/skills/authoring-design-system $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/authoring-requirements .claude/skills/authoring-requirements $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/authoring-roadmap .claude/skills/authoring-roadmap $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/authoring-technical-requirements .claude/skills/authoring-technical-requirements $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/authoring-user-stories .claude/skills/authoring-user-stories $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/brownfield-constitution .claude/skills/brownfield-constitution $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/brownfield-integration .claude/skills/brownfield-integration $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/executing-tdd-cycle .claude/skills/executing-tdd-cycle $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/patterns-api-contracts .claude/skills/patterns-api-contracts $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/patterns-entity-modeling .claude/skills/patterns-entity-modeling $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/patterns-flow-mapping .claude/skills/patterns-flow-mapping $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/patterns-interface-design .claude/skills/patterns-interface-design $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/patterns-technical-decisions .claude/skills/patterns-technical-decisions $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/patterns-vertical-tdd .claude/skills/patterns-vertical-tdd $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/strategy-core .claude/skills/strategy-core $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/strategy-implementation .claude/skills/strategy-implementation $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/strategy-specification .claude/skills/strategy-specification $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/syncing-claude-md .claude/skills/syncing-claude-md $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/testing-end-user .claude/skills/testing-end-user $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/using-git-worktrees .claude/skills/using-git-worktrees $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/using-github-issues .claude/skills/using-github-issues $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/validation-constitution .claude/skills/validation-constitution $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/validation-plan-artifacts .claude/skills/validation-plan-artifacts $ npx degit deepeshBodh/human-in-loop/plugins/humaninloop/skills/validation-task-artifacts .claude/skills/validation-task-artifacts
$ curl -fsSL --create-dirs -o .claude/agents/agent-auditor.md https://raw.githubusercontent.com/deepeshBodh/human-in-loop/main/.claude/agents/agent-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/release-manager.md https://raw.githubusercontent.com/deepeshBodh/human-in-loop/main/.claude/agents/release-manager.md $ curl -fsSL --create-dirs -o .claude/agents/skill-auditor.md https://raw.githubusercontent.com/deepeshBodh/human-in-loop/main/.claude/agents/skill-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/skill-creator.md https://raw.githubusercontent.com/deepeshBodh/human-in-loop/main/.claude/agents/skill-creator.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 (30)
auditing-agentsanalysis-codebaseanalysis-iterativeanalysis-screenshotanalysis-specificationsauthoring-constitutionauthoring-design-systemauthoring-requirementsauthoring-roadmapauthoring-technical-requirementsauthoring-user-storiesbrownfield-constitutionbrownfield-integrationexecuting-tdd-cyclepatterns-api-contractspatterns-entity-modelingpatterns-flow-mappingpatterns-interface-designpatterns-technical-decisionspatterns-vertical-tddstrategy-corestrategy-implementationstrategy-specificationsyncing-claude-mdtesting-end-userusing-git-worktreesusing-github-issuesvalidation-constitutionvalidation-plan-artifactsvalidation-task-artifacts
Subagents (4)
| agent-auditor model: opus | | |
| release-manager model: opus | Use this agent when preparing a plugin for release, conducting pre-release audits, or validating that all plugin components meet release-ready standards. This includes documentation updates, source co |
| skill-auditor model: opus | This agent MUST be invoked when the user says "audit skill", "review skill", "check compliance", or "validate skill". SHOULD also invoke when user mentions "skill quality", "SKILL-GUIDELINES complianc |
| skill-creator model: opus | This agent MUST be invoked when the user says "create skill", "new skill", "skill for", or "refactor skill". SHOULD also invoke when user mentions "SKILL-GUIDELINES", "skill authoring", or "skill comp |
Slash commands (1)
/agent-creator
Similar rigs
Rajan-Metaliya/claude-notes
A portable, clone-and-go starter kit for working with Claude Code alongside your Markdown notes — CLAUDE.md config, generalized slash commands, ready-to-use skills, and an organized notes vault (daily, projects, tasks, sessions).
Skill Collector 1.8k tok ·
jcarlosrodicio/norma
One task loop, one verification gate, one skill library for every coding agent - enforced by git. POSIX sh, no dependencies.
Skill Collector 2.3k tok ·
seanchatmangpt/claude-code-config-lsp
LSP 3.18 server for Claude Code config files (settings.json, CLAUDE.md, hooks, agents, skills)
Orchestrator 6.4k tok ·
hyhmrright/brooks-lint
AI code reviews grounded in 12 classic engineering books — decay risk diagnostics with book citations, severity labels, and 6 analysis modes including full-sweep auto-fix
Orchestrator 4.4k tok ·