~ / rigs / Orange-hanter / cod-doc

Orange-hanter/cod-doc

Context Orchestrator for Documentation — MCP server + autonomous agent that keeps project docs honest. Docs, tasks, plans, stories, links, revisions in SQLite; markdown is a hash-verified projection, not the source of truth.

↗ GitHub ★ 0 MIT updated 8d ago project Claude CodeCodex Claude plugin
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~7.8k tokens
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 0/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit Orange-hanter/cod-doc/hooks ./rig-cod-doc/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 Orange-hanter/cod-doc/cod_doc/skills/adr-author .claude/skills/adr-author
$ npx degit Orange-hanter/cod-doc/cod_doc/skills/audit-cadence .claude/skills/audit-cadence
$ npx degit Orange-hanter/cod-doc/cod_doc/skills/doc-structure .claude/skills/doc-structure
$ npx degit Orange-hanter/cod-doc/cod_doc/skills/doc-style .claude/skills/doc-style
$ npx degit Orange-hanter/cod-doc/cod_doc/skills/drift-handling .claude/skills/drift-handling
$ npx degit Orange-hanter/cod-doc/cod_doc/skills/ground-truth-reconcile .claude/skills/ground-truth-reconcile
$ npx degit Orange-hanter/cod-doc/cod_doc/skills/module-audit .claude/skills/module-audit
$ npx degit Orange-hanter/cod-doc/cod_doc/skills/orchestrator .claude/skills/orchestrator
$ npx degit Orange-hanter/cod-doc/cod_doc/skills/plan-to-tasks .claude/skills/plan-to-tasks
$ npx degit Orange-hanter/cod-doc/cod_doc/skills/project-onboarding .claude/skills/project-onboarding
$ npx degit Orange-hanter/cod-doc/cod_doc/skills/rfc-authoring .claude/skills/rfc-authoring
$ npx degit Orange-hanter/cod-doc/cod_doc/skills/scenario-author .claude/skills/scenario-author
$ npx degit Orange-hanter/cod-doc/cod_doc/skills/task-standard .claude/skills/task-standard
$ npx degit Orange-hanter/cod-doc/cod_doc/skills/validation .claude/skills/validation
$ npx degit Orange-hanter/cod-doc/plugins/cod-doc/skills/doc-sync .claude/skills/doc-sync
$ npx degit Orange-hanter/cod-doc/plugins/cod-doc/skills/task-flow .claude/skills/task-flow

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 (16)

Similar rigs

copied ✓