agentrigs
+ submit rig
~ / rigs / azalio / map-framework

azalio/map-framework

Plan-then-build AI coding for Claude Code & Codex CLI — you approve the plan before the model writes a line of code. SPEC → PLAN → TEST → CODE → REVIEW → LEARN

↗ GitHub ★ 156 mit updated 10d ago project Claude CodeCodex Claude plugin
share on X
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
CONTEXT TAX · EVERY TURN
~2.6k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
4/5
Blocks destructive commands · Protects secrets · Pre-tool screening hook · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit azalio/map-framework/.claude ./rig-map-framework  # 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 azalio/map-framework/.agents/skills/map-architecture .claude/skills/map-architecture
$ npx degit azalio/map-framework/.agents/skills/map-auto .claude/skills/map-auto
$ npx degit azalio/map-framework/.agents/skills/map-check .claude/skills/map-check
$ npx degit azalio/map-framework/.agents/skills/map-debug .claude/skills/map-debug
$ npx degit azalio/map-framework/.agents/skills/map-efficient .claude/skills/map-efficient
$ npx degit azalio/map-framework/.agents/skills/map-explain .claude/skills/map-explain
$ npx degit azalio/map-framework/.agents/skills/map-fast .claude/skills/map-fast
$ npx degit azalio/map-framework/.agents/skills/map-learn .claude/skills/map-learn
$ npx degit azalio/map-framework/.agents/skills/map-memory-now .claude/skills/map-memory-now
$ npx degit azalio/map-framework/.agents/skills/map-plan .claude/skills/map-plan
$ npx degit azalio/map-framework/.agents/skills/map-prd-review .claude/skills/map-prd-review
$ npx degit azalio/map-framework/.agents/skills/map-release .claude/skills/map-release
$ npx degit azalio/map-framework/.agents/skills/map-resume .claude/skills/map-resume
$ npx degit azalio/map-framework/.agents/skills/map-review .claude/skills/map-review
$ npx degit azalio/map-framework/.agents/skills/map-skill-eval .claude/skills/map-skill-eval
$ npx degit azalio/map-framework/.agents/skills/map-so-search .claude/skills/map-so-search
$ npx degit azalio/map-framework/.agents/skills/map-state .claude/skills/map-state
$ npx degit azalio/map-framework/.agents/skills/map-task .claude/skills/map-task
$ npx degit azalio/map-framework/.agents/skills/map-tdd .claude/skills/map-tdd
$ npx degit azalio/map-framework/.agents/skills/map-tokenreport .claude/skills/map-tokenreport
$ npx degit azalio/map-framework/.agents/skills/map-understand .claude/skills/map-understand
$ npx degit azalio/map-framework/.agents/skills/map-upgrade .claude/skills/map-upgrade
$ npx degit azalio/map-framework/.agents/skills/map-wayfind .claude/skills/map-wayfind
$ curl -fsSL --create-dirs -o .claude/agents/actor.md https://raw.githubusercontent.com/azalio/map-framework/main/.claude/agents/actor.md
$ curl -fsSL --create-dirs -o .claude/agents/documentation-reviewer.md https://raw.githubusercontent.com/azalio/map-framework/main/.claude/agents/documentation-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/evaluator.md https://raw.githubusercontent.com/azalio/map-framework/main/.claude/agents/evaluator.md
$ curl -fsSL --create-dirs -o .claude/agents/final-verifier.md https://raw.githubusercontent.com/azalio/map-framework/main/.claude/agents/final-verifier.md
$ curl -fsSL --create-dirs -o .claude/agents/monitor.md https://raw.githubusercontent.com/azalio/map-framework/main/.claude/agents/monitor.md
$ curl -fsSL --create-dirs -o .claude/agents/predictor.md https://raw.githubusercontent.com/azalio/map-framework/main/.claude/agents/predictor.md
$ curl -fsSL --create-dirs -o .claude/agents/reflector.md https://raw.githubusercontent.com/azalio/map-framework/main/.claude/agents/reflector.md
$ curl -fsSL --create-dirs -o .claude/agents/research-agent.md https://raw.githubusercontent.com/azalio/map-framework/main/.claude/agents/research-agent.md
$ curl -fsSL --create-dirs -o .claude/agents/task-decomposer.md https://raw.githubusercontent.com/azalio/map-framework/main/.claude/agents/task-decomposer.md

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "permissions": {
    "deny": [
      "Edit(**/.env*)",
      "Edit(**/*credentials*.yaml)",
      "Edit(**/*credentials*.yml)",
      "Edit(**/*credentials*.json)",
      "Edit(**/*credentials*.toml)",
      "Edit(**/*credentials*.env)",
      "Edit(**/*secret*.yaml)",
      "Edit(**/*secret*.yml)",
      "Edit(**/*secret*.json)",
      "Edit(**/*secret*.toml)",
      "Edit(**/*secret*.env)",
      "Bash(rm -rf)",
      "Bash(git push --force origin main)",
      "Bash(git push --force origin master)",
      "Bash(git reset --hard)"
    ]
  },
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Edit|Write|Read|MultiEdit|Bash",
        "hooks": [
          {
            "type": "command",
            "command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/safety-guardrails.py"
          }
        ]
      },
      {
        "matcher": "Edit|Write|MultiEdit",
        "hooks": [
          {
            "type": "command",
            "command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/workflow-gate.py"
          }
        ]
      },
      {
        "matcher": "Edit|Write|MultiEdit|Bash",
        "hooks": [
          {
            "type": "command",
            "command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/workflow-context-injector.py"
          }
        ]
      }
    ]
  }
}

Skills (23)

map-architecturemap-automap-checkmap-debugmap-efficientmap-explainmap-fastmap-learnmap-memory-nowmap-planmap-prd-reviewmap-releasemap-resumemap-reviewmap-skill-evalmap-so-searchmap-statemap-taskmap-tddmap-tokenreportmap-understandmap-upgrademap-wayfind

Subagents (9)

actor
model: sonnet # Balanced: code generation qual
Generates production-ready implementation proposals (MAP)
documentation-reviewer
model: sonnet
Reviews technical documentation for completeness, external dependencies, and architectural consistency
evaluator
model: sonnet # Evaluation requires nuanced ju
Evaluates solution quality and completeness (MAP)
final-verifier
model: opus
Adversarial verifier with Root Cause Analysis (Ralph Loop)
monitor
model: sonnet # Balanced: quality validation r
Reviews code for correctness, standards, security, and testability (MAP)
predictor
model: sonnet # Impact analysis requires compl
Predicts consequences and dependency impact of changes (MAP)
reflector
model: sonnet
Extracts structured lessons from successes and failures
research-agent
model: haiku
Heavy codebase reading with compressed output. Use PROACTIVELY before Actor implementation to gather context without polluting implementation context.
task-decomposer
model: opus
Breaks complex goals into atomic, testable subtasks (MAP)

Hooks (18)

eventmatcherruns
SessionStartcompact"$CLAUDE_PROJECT_DIR"/.claude/hooks/post-compact-context.py
SessionStart*"$CLAUDE_PROJECT_DIR"/.claude/hooks/map-memory-finalize.py
SessionStart*"$CLAUDE_PROJECT_DIR"/.claude/hooks/map-memory-recall.py
SessionEnd*"$CLAUDE_PROJECT_DIR"/.claude/hooks/map-memory-endmark.py
PreToolUseEdit|Write|Read|MultiEdit|Bash"$CLAUDE_PROJECT_DIR"/.claude/hooks/safety-guardrails.py
PreToolUseEdit|Write|MultiEdit"$CLAUDE_PROJECT_DIR"/.claude/hooks/workflow-gate.py
PreToolUseEdit|Write|MultiEdit|Bash"$CLAUDE_PROJECT_DIR"/.claude/hooks/workflow-context-injector.py
PostToolUseEdit|Write|MultiEdit|Bash"$CLAUDE_PROJECT_DIR"/.claude/hooks/ralph-iteration-logger.py
PreCompact*"$CLAUDE_PROJECT_DIR"/.claude/hooks/ralph-context-pruner.py
PreCompact*"$CLAUDE_PROJECT_DIR"/.claude/hooks/pre-compact-save-transcript.py
SubagentStop*"$CLAUDE_PROJECT_DIR"/.claude/hooks/map-token-meter.py
Stop*"$CLAUDE_PROJECT_DIR"/.claude/hooks/scrub-internal-ids.py
Stop*"$CLAUDE_PROJECT_DIR"/.claude/hooks/end-of-turn.sh
Stop*"$CLAUDE_PROJECT_DIR"/.claude/hooks/map-token-meter.py
Stop*"$CLAUDE_PROJECT_DIR"/.claude/hooks/map-memory-capture.py
UserPromptSubmit*"$CLAUDE_PROJECT_DIR"/.claude/hooks/detect-clarification-triggers.py
UserPromptSubmit*"$CLAUDE_PROJECT_DIR"/.claude/hooks/context-meter.py
UserPromptSubmit*"$CLAUDE_PROJECT_DIR"/.claude/hooks/map-memory-recall.py

Permissions

deny (15)
Edit(**/.env*)
Edit(**/*credentials*.yaml)
Edit(**/*credentials*.yml)
Edit(**/*credentials*.json)
Edit(**/*credentials*.toml)
Edit(**/*credentials*.env)
Edit(**/*secret*.yaml)
Edit(**/*secret*.yml)
Edit(**/*secret*.json)
Edit(**/*secret*.toml)
Edit(**/*secret*.env)
Bash(rm -rf)
Bash(git push --force origin main)
Bash(git push --force origin master)
Bash(git reset --hard)
ask (0)
—
allow (20)
Edit(.claude/agents/*)
Edit(.claude/commands/*)
Edit(.claude/references/*)
Bash(mapify *)
Bash(pytest *)
Bash(make lint)
Bash(make test)
Bash(ruff *)
Bash(black *)
Bash(git status)
Bash(git diff)
Bash(git log)
Bash(git branch)
Bash(git rev-parse *)
Bash(git add)
Bash(git commit)
Bash(helm template *)
Bash(go vet *)
Bash(gofmt *)
Bash(kubectl get *)

Similar rigs

tigerless-labs/autoharness
Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.
★ 7,647 setup Claude Code 1 mcp 1 skills 2 agents 7d ago
Pragmatist 2.6k tok ·
chamirusenarath96/spec-driven-sdlc-template
Spec-driven, agent-run SDLC template: GitHub Issues/Projects + Claude Code subagents + gh-aw agentic workflows
★ 0 collection Claude CodeCodex 3 agents 2mo ago
Minimalist 1.5k tok ·
pedroromeroluna/peter-brain
🧠 Tu segundo cerebro en Markdown, manejado por agentes de Claude Code. Template basado en PARA (Projects, Areas, Resources, Archives).
★ 7 project Claude Code 1 skills 3 agents 1mo ago
YOLO Cowboy 2.3k tok ·
Gidntsquia/claude-config
My Claude Code agents, skills and settings
★ 1 setup Claude Code 4 skills 3 agents today
Pragmatist 673 tok ·
copied ✓