mark393295827/house-maint-ai/sandbox-runner

Claude Code and agent skill by mark393295827/house-maint-ai

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Recursive sandboxing for 100+ iterations before human review

Install

npx vskill@latest install mark393295827/house-maint-ai/sandbox-runner

SKILL.md

Sandbox Runner Skill

Run solutions through recursive sandboxing, iterating up to 100 times before presenting to human.

Concept

"Let agents fail 100 times in simulation so humans see only the winning solution."

Sandbox Loop

[Solution] → Sandbox → Test → Pass? → [Present to Human]
                 ↑        │
                 └── No ──┘ (iterate, max 100x)

Configuration

yaml
sandbox:
  max_iterations: 100
  early_exit_threshold: 0.95  # Confidence to stop early
  checkpoint_every: 10        # Save state every N iterations
  
  tests:
    - unit: "npm run test"
    - lint: "npm run lint"
    - build: "npm run build"
    
  success_criteria:
    all_tests_pass: true
    no_lint_errors: true
    build_success: true

Iteration Protocol

Per Iteration:
  1. Apply solution
  2. Run test suite
  3. Collect failures
  4. Analyze failures
  5. Generate fix
  6. Loop until pass OR max iterations
State Tracking:
yaml
iteration:
  number: 42
  status: running | passed | failed
  failures: ["test A", "test B"]
  fixes_attempted: [...]
  confidence: 0.72

Early Exit Conditions

Stop before 100 iterations if:

  • All tests pass (success)
  • Confidence > 0.95
  • Same failure 5x in a row (stuck)
  • Critical error detected

Output Format

yaml
sandbox_result:
  iterations_run: 47
  final_status: passed | failed
  
  solution:
    code_changes: [...]
    confidence: 0.89
    
  iteration_log:
    - iter: 1, status: failed, fixes: [...]
    - iter: 2, status: failed, fixes: [...]
    - iter: 47, status: passed
    
  ready_for_hitl: true

Integration

  • Input from: Swarm orchestrator
  • Output to: HITL auditor
  • Rollback: Restore to pre-sandbox state on failure

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

Repository stars
1
7-day trend score
8

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/mark393295827/house-maint-ai/sandbox-runner/badge)](https://verified-skill.com/skills/mark393295827/house-maint-ai/sandbox-runner)

Something wrong with this skill or its page? Tell us.