HookTripwire
Statically audit agent hooks, workflows, permissions, and shell-backed automation before anything executes.
Local-first developer tools
Six focused open-source tools for AI-agent security, observability, and code intelligence—designed to produce a useful answer quickly without sending analyzed code, logs, traces, or API contracts to a hosted backend.
npx --yes github:mockingbird777/hooktripwire#v0.2.0 .claude .cursor .github/workflows
Audit surface
Audit coding-agent hooks and automation before execution. Catch dangerous commands, broad permissions, secret exfiltration, and mutable dependencies without running scanned code.
Choose a job. This tiny guide runs entirely in your browser and points to the smallest useful tool.
No signup, upload, or background request—just a local recommendation.
Statically audit agent hooks, workflows, permissions, and shell-backed automation before anything executes.
Every project has a documented quick-start path, realistic examples, documented trade-offs, tests, and a public roadmap.
Audit agent hooks, workflow permissions, and shell automation before execution.
Turn AI-agent traces into critical paths, retry signals, latency, token, and cost insight.
Map repository dependencies, cycles, hotspots, and high-coupling files locally.
Turn noisy logs into a redacted, clustered, shareable investigation report.
Catch breaking and security-relevant OpenAPI changes locally or in CI.
Rank the smallest useful set of skills and tools for a natural-language task.
Your code, logs, traces, and API contracts stay on your machine.
Stable structured output, meaningful exit codes, and CI-friendly workflows.
MIT licensed, with public roadmaps and contribution paths in every repository.