agentrigs
+ submit rig
~ / rigs / Cranot / roam-code

Cranot/roam-code

Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 commands, 246 MCP tools, change-safety gates, audit evidence, zero API keys.

↗ GitHub ★ 517 apache-2.0 updated 6d ago project Claude CodeCodex Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~18.1k tokens
Context hog · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ claude mcp add roam-code -e ROAM_MCP_PRESET=YOUR_ROAM_MCP_PRESET -- roam mcp
$ npx degit Cranot/roam-code/.claude ./rig-roam-code  # 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.

$ claude mcp add roam-code -e ROAM_MCP_PRESET=YOUR_ROAM_MCP_PRESET -- roam mcp
$ npx degit Cranot/roam-code/.agents/skills/roam-agent-guidance .claude/skills/roam-agent-guidance
$ npx degit Cranot/roam-code/.agents/skills/roam-evidence-hardening .claude/skills/roam-evidence-hardening
$ npx degit Cranot/roam-code/.agents/skills/roam-lesson-maintenance .claude/skills/roam-lesson-maintenance
$ npx degit Cranot/roam-code/.agents/skills/roam-measurement-design .claude/skills/roam-measurement-design
$ npx degit Cranot/roam-code/.agents/skills/roam-milestone-planning .claude/skills/roam-milestone-planning
$ npx degit Cranot/roam-code/.agents/skills/roam-product-writing .claude/skills/roam-product-writing
$ npx degit Cranot/roam-code/.agents/skills/roam-release-readiness .claude/skills/roam-release-readiness
$ npx degit Cranot/roam-code/.claude/skills/prompt-optimizer .claude/skills/prompt-optimizer
$ npx degit Cranot/roam-code/skills/roam .claude/skills/roam

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 *)"
    ]
  }
}

MCP servers (1)

serversourceest. tokens
roam · "roam-code"
env: ROAM_MCP_PRESET
 binary 2.5k

Skills (9)

roam-agent-guidanceroam-evidence-hardeningroam-lesson-maintenanceroam-measurement-designroam-milestone-planningroam-product-writingroam-release-readinessprompt-optimizerroam

Similar rigs

Emanuel-Walker/cyber-portfolio
My cyber + AI builder portfolio. Six projects, six months. The thought partner side: Obsidian second brain + AI agent setups (Claude Code, Codex, Grok, Muse, Dot). The security side: detection-as-code, hardened LLM triage, crown jewel triag
★ 2 project Codex 15 skills 1d ago
Skill Collector 1.6k tok ·
danieldeusing/seedr
Seed your coding agents with capabilities — CLI + registry for AI coding assistant content
★ 0 project Claude CodeCodex 24 skills 1 hooks today
Skill Collector 4.8k tok ·
balaji-dutt/dotfiles
Read-only mirror of the canonical GitLab repository.
★ 0 setup Claude CodeCodex 21 skills 9 agents 8 hooks 8d ago
Orchestrator 12.5k tok ·
getsentry/skills
Agent Skills used by the Sentry team for development.
★ 1,033 project Claude CodeCodex 28 skills 2 agents 10d ago
Skill Collector 2.6k tok ·
copied ✓