CLSkills_Hub
← All agents

Debugger

$24.99
Standard tier

Reproduces the failure, runs hypothesis experiments until the cause is proven, then proposes the minimal fix. Applying the fix is human-gated.

How it runs

What it can touch

  • read files
  • git diff / log / blame
  • run the failing command
  • applying the fix — pauses for your approval

Guarantees

Proves the causeMinimal-fix disciplineNo guessingLangGraph state machinePython + TypeScriptSecurity-policy enforcedModel-agnosticSelf-evaluating output

What's in the download

agent.yamltyped goal contract + I/O schema + success test
policies/security.yamltool allowlist, secret handling, resource limits
policies/approval.yamlwhich actions pause for a human
python/runnable reference: graph, executor, adapters, entrypoint
typescript/the same agent, mirrored in TypeScript
docs/ARCHITECTURE, CONFIGURATION, SECURITY, EXTENDING
examples/a runnable sample + the exact output it produces
Browse all 20 →