~ / rigs / anatomia-dev / anatomia

anatomia-dev/anatomia

Spec-driven agent harness for Claude Code and Codex — five-agent pipeline (scope, plan, build, verify, learn) with an auditable proof chain.

↗ GitHub ★ 32 mit updated 3mo ago project Claude CodeCodex
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~957 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit anatomia-dev/anatomia/.claude ./rig-anatomia  # 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 anatomia-dev/anatomia/.ana/skills/coding-standards .claude/skills/coding-standards
$ npx degit anatomia-dev/anatomia/.ana/skills/deployment .claude/skills/deployment
$ npx degit anatomia-dev/anatomia/.ana/skills/git-workflow .claude/skills/git-workflow
$ npx degit anatomia-dev/anatomia/.ana/skills/testing-standards .claude/skills/testing-standards
$ npx degit anatomia-dev/anatomia/.ana/skills/troubleshooting .claude/skills/troubleshooting
$ npx degit anatomia-dev/anatomia/packages/cli/templates/.claude/skills/ai-patterns .claude/skills/ai-patterns
$ npx degit anatomia-dev/anatomia/packages/cli/templates/.claude/skills/api-patterns .claude/skills/api-patterns
$ npx degit anatomia-dev/anatomia/packages/cli/templates/.claude/skills/data-access .claude/skills/data-access
$ curl -fsSL --create-dirs -o .claude/agents/ana-build.md https://raw.githubusercontent.com/anatomia-dev/anatomia/main/.claude/agents/ana-build.md
$ curl -fsSL --create-dirs -o .claude/agents/ana-learn.md https://raw.githubusercontent.com/anatomia-dev/anatomia/main/.claude/agents/ana-learn.md
$ curl -fsSL --create-dirs -o .claude/agents/ana-plan.md https://raw.githubusercontent.com/anatomia-dev/anatomia/main/.claude/agents/ana-plan.md
$ curl -fsSL --create-dirs -o .claude/agents/ana-setup.md https://raw.githubusercontent.com/anatomia-dev/anatomia/main/.claude/agents/ana-setup.md
$ curl -fsSL --create-dirs -o .claude/agents/ana-verify.md https://raw.githubusercontent.com/anatomia-dev/anatomia/main/.claude/agents/ana-verify.md
$ curl -fsSL --create-dirs -o .claude/agents/ana.md https://raw.githubusercontent.com/anatomia-dev/anatomia/main/.claude/agents/ana.md
$ curl -fsSL --create-dirs -o .claude/agents/ana-build.md https://raw.githubusercontent.com/anatomia-dev/anatomia/main/packages/cli/templates/.claude/agents/ana-build.md
$ curl -fsSL --create-dirs -o .claude/agents/ana-learn.md https://raw.githubusercontent.com/anatomia-dev/anatomia/main/packages/cli/templates/.claude/agents/ana-learn.md
$ curl -fsSL --create-dirs -o .claude/agents/ana-plan.md https://raw.githubusercontent.com/anatomia-dev/anatomia/main/packages/cli/templates/.claude/agents/ana-plan.md
$ curl -fsSL --create-dirs -o .claude/agents/ana-setup.md https://raw.githubusercontent.com/anatomia-dev/anatomia/main/packages/cli/templates/.claude/agents/ana-setup.md
$ curl -fsSL --create-dirs -o .claude/agents/ana-verify.md https://raw.githubusercontent.com/anatomia-dev/anatomia/main/packages/cli/templates/.claude/agents/ana-verify.md
$ curl -fsSL --create-dirs -o .claude/agents/ana.md https://raw.githubusercontent.com/anatomia-dev/anatomia/main/packages/cli/templates/.claude/agents/ana.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 (8)

Subagents (12)

ana-build
model: opus[1m]
AnaBuild — reads spec, produces working code, tests, and build report. The builder.
ana-learn
model: opus[1m]
Ana Learn — quality gardener. Triages findings, promotes rules, routes observations.
ana-plan
model: opus[1m]
AnaPlan — reads scope, produces implementation spec. The architect.
ana-setup
model: opus[1m]
Setup orchestrator — calibrates Ana's knowledge with your project's identity, architecture, and values.
ana-verify
model: opus[1m]
AnaVerify — fault-finder and code reviewer. Runs mechanical checks, forms independent findings about the code.
ana
model: opus[1m]
Ana — your project-aware thinking partner. Scopes, decomposes, navigates, advises, routes.
ana-build
model: opus[1m]
AnaBuild — reads spec, produces working code, tests, and build report. The builder.
ana-learn
model: opus[1m]
Ana Learn — quality gardener. Triages findings, promotes rules, routes observations.
ana-plan
model: opus[1m]
AnaPlan — reads scope, produces implementation spec. The architect.
ana-setup
model: opus[1m]
Setup orchestrator — calibrates Ana's knowledge with your project's identity, architecture, and values.
ana-verify
model: opus[1m]
AnaVerify — fault-finder and code reviewer. Runs mechanical checks, forms independent findings about the code.
ana
model: opus[1m]
Ana — your project-aware thinking partner. Scopes, decomposes, navigates, advises, routes.

Hooks (1)

eventmatcherruns
SessionStart*ana _capture

Similar rigs

copied ✓