h4tcher-scoped-audit
OfficialAudit a small slice with fresh rigor.
Software Engineering#quality assurance#governance#codebase analysis#agentic workflow#severity findings#read-only review#scoped audit
Authorhatch3r
Version1.0.0
Installs0
System Documentation
What problem does it solve?
It helps you run a bounded, read-only quality audit on a maintainer-defined slice of a repository, producing actionable, severity-graded findings without doing a full 21-domain cycle.
Core Features & Use Cases
- Scoping by intent: Interprets a natural-language scope (single file, small group, subsystem) and resolves it to concrete file paths via globbing.
- Fresh checklist grounded in the rigor contract: Builds a 4–8 item checklist that is explicitly tied back to rigor-contract templates and pillar implications.
- Bounded, safe execution: Enforces a hard ceiling for scope growth and writes only sub-agent artifacts under
.audit-workspace/with a strict no-repo-writes guardrail. - Severity-graded in-chat reporting: Synthesizes deduped findings into an ≤80-line report including confidence, sources (only for empirical claims), and a recommended next step.
Quick Start
Ask your AI to run a scoped audit for "src/cli/ and related command wiring" and include any key files you consider critical so it can resolve the slice and grade findings by severity.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: h4tcher-scoped-audit Download link: https://github.com/hatch3r/hatch3r/archive/main.zip#h4tcher-scoped-audit Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.