agentrigs
+ submit rig
~ / rigs / Remus3 / Legion-Wallpaper

Remus3/Legion-Wallpaper

Self-auditing AI image restoration pipeline (super-resolution, LaMa inpainting, face repair, metric-plus-vision gate ladder), built by a multi-agent Claude Code system with independent verifiers, git-hook gates and headless background lanes

↗ GitHub ★ 1 Apache-2.0 updated today project Claude CodeCodexGemini CLI
share on X
ARCHETYPE
Automator
Hooks on every lifecycle event: format, lint, notify, log.
CONTEXT TAX · EVERY TURN
~5.5k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
2/5
Pre-tool screening hook · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit Remus3/Legion-Wallpaper/.claude ./rig-legion-wallpaper  # 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.

$ curl -fsSL --create-dirs -o .claude/agents/verifier.md https://raw.githubusercontent.com/Remus3/Legion-Wallpaper/main/.claude/agents/verifier.md

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

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash|PowerShell|Read|Edit|Write|Grep|Glob|NotebookEdit|MultiEdit",
        "hooks": [
          {
            "type": "command",
            "command": "python \"$CLAUDE_PROJECT_DIR/ops/fleet_kit/fleet_subagent_first.py\""
          }
        ]
      },
      {
        "matcher": "Edit|Write|NotebookEdit|MultiEdit|Bash|PowerShell",
        "hooks": [
          {
            "type": "command",
            "command": "python \"$CLAUDE_PROJECT_DIR/ops/fleet_kit/fleet_claims.py\" hook"
          }
        ]
      },
      {
        "matcher": "Bash(git commit:*)",
        "hooks": [
          {
            "type": "command",
            "command": "pythonw \"$CLAUDE_PROJECT_DIR/tools/precommit_gate.py\""
          }
        ]
      },
      {
        "matcher": "PowerShell",
        "hooks": [
          {
            "type": "command",
            "command": "pythonw \"$CLAUDE_PROJECT_DIR/tools/precommit_gate.py\""
          }
        ]
      },
      {
        "matcher": "mcp__Windows-MCP__Scrape|mcp__computer-use__read_clipboard",
        "hooks": [
          {
            "type": "command",
            "command": "pythonw \"$CLAUDE_PROJECT_DIR/tools/text_first_guard.py\""
          }
        ]
      }
    ]
  }
}

Subagents (1)

verifierGround-truth verification subagent. Independently re-runs the test suite from a clean state, confirms cited test files exist on disk, and cross-checks an implementing agent's claims (test counts, gree

Hooks (16)

eventmatcherruns
PreToolUseBash|PowerShell|Read|Edit|Write|Grep|Glob|NotebookEdit|MultiEditpython "$CLAUDE_PROJECT_DIR/ops/fleet_kit/fleet_subagent_first.py"
PreToolUseEdit|Write|NotebookEdit|MultiEdit|Bash|PowerShellpython "$CLAUDE_PROJECT_DIR/ops/fleet_kit/fleet_claims.py" hook
PreToolUseBash(git commit:*)pythonw "$CLAUDE_PROJECT_DIR/tools/precommit_gate.py"
PreToolUsePowerShellpythonw "$CLAUDE_PROJECT_DIR/tools/precommit_gate.py"
PreToolUsemcp__Windows-MCP__Scrape|mcp__computer-use__read_clipboardpythonw "$CLAUDE_PROJECT_DIR/tools/text_first_guard.py"
PostToolUseEdit|Writepythonw "$CLAUDE_PROJECT_DIR/tools/pytest_guard.py"
PostToolUseEdit|Writepythonw "$CLAUDE_PROJECT_DIR/tools/edit_lint_check.py"
UserPromptSubmit*pythonw "$CLAUDE_PROJECT_DIR/tools/lw_facts.py" --inbox-only
Stop*pythonw "$CLAUDE_PROJECT_DIR/tools/claimed_green_gate.py"
Stop*pythonw "$CLAUDE_PROJECT_DIR/ops/fleet_kit/fleet_done.py" stop-hook
SessionStart*pythonw "$CLAUDE_PROJECT_DIR/tools/lw_facts.py"
SessionStart*pythonw "$CLAUDE_PROJECT_DIR/tools/caveman_default.py"
SessionStart*pythonw "$CLAUDE_PROJECT_DIR/tools/lw_window_guard.py"
SessionStart*pythonw "$CLAUDE_PROJECT_DIR/tools/install_git_hooks.py" --check
SessionStart*pythonw "$CLAUDE_PROJECT_DIR/tools/lw_checklist.py" session-start
SubagentStop*python "$CLAUDE_PROJECT_DIR/ops/fleet_kit/fleet_claims.py" release-hook

Slash commands (22)

/LW-Continue/adversarial-review/blast-radius/cleaning-pass/done/end-review/final-pass/first-pass/gemini-headless-upgrade/generate/headless-upgrade/intake/last-pass/orchestrated-run/pipeline-status/repo-insights/root-cause-fix/ship-batch/sync-all-md/test-driven-development/test-first-autopilot/weekly-hygiene

Similar rigs

leavemagic-cyber/earned-confidence
A behavior contract for AI coding agents — every rule added after a real failure. Ships with a verifier agent that cannot edit what it judges.
★ 3 project Claude Code 2 agents 2mo ago
Pragmatist 3.6k tok ·
vitaliikapliuk/modelharness
Make every model cheaper or better. Zero-config behavioral harness for Claude Code, with a reproducible 408-run benchmark
★ 36 setup Claude Code 3 skills 1 agents 4mo ago
Pragmatist 236 tok ·
NotRedFox/NotRedFoxs-Claude-skills
Claude Code skills: a docs fact-checker, a code auditor, a bug-memory log, a mod and more.
★ 1 project Claude Code 4 agents 4 hooks today
Automator 577 tok ·
itshig/AGENTS-template
Drop-in AGENTS.md template for Claude Code, Cursor, Codex, and other AI agents — with .agents/ for rules, personas, and workflows.
★ 1 collection Claude CodeCodexGemini CLI 5 agents 1mo ago
Orchestrator 3.0k tok ·
copied ✓