stephennmiller/taskgraph-ai
Task management for AI coding agents. Turn a PRD into a dependency-aware task list and work it in Claude Code via slash commands, CLI or MCP.
field: Productivity workflow: DebuggingDocsPlanning & specsCI/CD & deployPR / code review runs claude in CI
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
up to ~6.1k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Heavy · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code
$ npx degit stephennmiller/taskgraph-ai/.claude ./rig-taskgraph-ai # 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 stephennmiller/taskgraph-ai/packages/claude-code-plugin/skills/research .claude/skills/research $ npx degit stephennmiller/taskgraph-ai/packages/claude-code-plugin/skills/taskgraph .claude/skills/taskgraph
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 *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| taskgraph-ai env: TASKGRAPH_TOOLS | local / custom | 2.5k |
Skills (2)
Slash commands (2)
/dedupe/go/pr-comments
Similar rigs
SynaLinks/synalinks
Keras based framework for neuro-symbolic LM systems
Minimalist 840 tok · · Q0
dmitry-markin/silta
Family AI assistant that runs on Claude Code and speaks Matrix
Pragmatist 2.6k tok · · Q15
GiaSip/giasip-skills
Turn research questions into reports with source links and open questions: Research for Codex and Claude Code, plus multi-model dispatch tooling for Claude Code.
Minimalist 248 tok · · Q0
111vandit111/ai-dev-team
Token-efficient multi-agent dev team for any AI coding agent (Claude Code, Codex, Gemini CLI, Cursor, OpenCode, Copilot): planner, parallel builders, verifier and web researchers for frontend and backend. Matches your repo's code style, use
Minimalist 255 tok · · Q0