aidemd-mcp/server
MCP server that teaches any AI agent the AIDE spec methodology — progressive disclosure specs alongside code
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit aidemd-mcp/server/.claude ./rig-server # 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 aidemd-mcp/server/.claude/skills/aide-brain-author .claude/skills/aide-brain-author $ npx degit aidemd-mcp/server/.claude/skills/aide-handoff .claude/skills/aide-handoff $ npx degit aidemd-mcp/server/.claude/skills/aide .claude/skills/aide $ npx degit aidemd-mcp/server/.claude/skills/brain .claude/skills/brain $ npx degit aidemd-mcp/server/.claude/skills/kanban .claude/skills/kanban $ npx degit aidemd-mcp/server/.claude/skills/study-playbook .claude/skills/study-playbook
$ curl -fsSL --create-dirs -o .claude/agents/aide-aligner.md https://raw.githubusercontent.com/aidemd-mcp/server/main/.claude/agents/aide/aide-aligner.md $ curl -fsSL --create-dirs -o .claude/agents/aide-architect.md https://raw.githubusercontent.com/aidemd-mcp/server/main/.claude/agents/aide/aide-architect.md $ curl -fsSL --create-dirs -o .claude/agents/aide-auditor.md https://raw.githubusercontent.com/aidemd-mcp/server/main/.claude/agents/aide/aide-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/aide-domain-expert.md https://raw.githubusercontent.com/aidemd-mcp/server/main/.claude/agents/aide/aide-domain-expert.md $ curl -fsSL --create-dirs -o .claude/agents/aide-explorer.md https://raw.githubusercontent.com/aidemd-mcp/server/main/.claude/agents/aide/aide-explorer.md $ curl -fsSL --create-dirs -o .claude/agents/aide-implementor.md https://raw.githubusercontent.com/aidemd-mcp/server/main/.claude/agents/aide/aide-implementor.md $ curl -fsSL --create-dirs -o .claude/agents/aide-maintainer.md https://raw.githubusercontent.com/aidemd-mcp/server/main/.claude/agents/aide/aide-maintainer.md $ curl -fsSL --create-dirs -o .claude/agents/aide-qa.md https://raw.githubusercontent.com/aidemd-mcp/server/main/.claude/agents/aide/aide-qa.md $ curl -fsSL --create-dirs -o .claude/agents/aide-spec-writer.md https://raw.githubusercontent.com/aidemd-mcp/server/main/.claude/agents/aide/aide-spec-writer.md $ curl -fsSL --create-dirs -o .claude/agents/aide-strategist.md https://raw.githubusercontent.com/aidemd-mcp/server/main/.claude/agents/aide/aide-strategist.md $ curl -fsSL --create-dirs -o .claude/agents/kanban-maintainer.md https://raw.githubusercontent.com/aidemd-mcp/server/main/.claude/agents/kanban/kanban-maintainer.md
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 (6)
Subagents (11)
| aide-aligner model: opus | Use this agent when you need to verify that specs across the intent tree are internally consistent — comparing child outcomes against ancestor outcomes to detect intent drift. This agent walks the ful |
| aide-architect model: opus | Use this agent when a .aide spec is ready and needs to be translated into an implementation plan. The agent reads the spec (frontmatter; body sections if present), reads brief.aide if present, consult |
| aide-auditor model: opus | Use this agent when existing, working code needs to be reviewed for drift from coding playbook conventions. This agent reads the implementation, consults the coding playbook, and produces plan.aide wi |
| aide-domain-expert model: sonnet | Use this agent when the brain needs domain knowledge before the spec body can be filled. This agent does volume research — web, brain, external sources — and persists findings to the brain filed by do |
| aide-explorer model: sonnet | Use this agent for read-only investigation of the AIDE codebase — finding code, tracing bugs, answering questions about how modules work, or understanding the cascading intent tree. This agent underst |
| aide-implementor model: sonnet | Use this agent when you have plan.aide ready and need to execute it into working code (build mode), or when you need to fix exactly one todo.aide item (fix mode). This agent reads the plan, writes cod |
| aide-maintainer model: sonnet | Use this agent when a feature's pipeline phase has fully closed for a module — its plan.aide (if the module has one) has every step checked, any todo.aide is fully checked, and the retro (if QA wrote |
| aide-qa model: sonnet | Use this agent when implementation is complete and needs to be verified against the .aide intent spec. This agent compares actual output against outcomes.desired and outcomes.undesired, then produces |
| aide-spec-writer model: opus | Use this agent to write a structured AIDE file from orchestrator-supplied context. This agent handles TWO file types: (1) `.aide` intent spec frontmatter — the durable intent contract that drives ever |
| aide-strategist model: opus | Use this agent when the .aide frontmatter is complete and the feature is a pipeline — several modules handing off to each other in a specific order. This agent writes how the modules interact, from th |
| kanban-maintainer model: sonnet | Use this agent for every read or write of the project's kanban tasks, so the tasks' full text never lands in the caller's context. Folders are the board: each project has its own folder with one subfo |
Slash commands (14)
/aide/aide/align/aide/brain/aide/build/aide/fix/aide/handoff/aide/plan/aide/qa/aide/refactor/aide/research/aide/spec/aide/synthesize/aide/update-playbook/aide/upgrade
Similar rigs
Cazy00/brain
A second brain that stays true: your knowledge as markdown in a git repo you own, reachable from any MCP-capable agent. Supersede protocol, commit-time schema gate, validated link graph.
Pragmatist 7.7k tok · · Q23
rensftw/.dotfiles
Personal dotfiles and setup scripts
Minimalist 1.5k tok · · Q0
jeremylongshore/bobs-big-brain-plugin
Bob's Big Brain — the governed team brain, as a local-first Claude Code + Cowork plugin. Turn your own files into cited (qmd://) memory with a tamper-evident, SHA-256 hash-chained audit trail. ONE plugin, two modes: local needs no daemon or
Pragmatist 7.7k tok · · Q8
insanum/dotfiles
My dotfiles!
Pragmatist 1.2k tok · · Q0