Swe Bug Assessor — Development agent for Claude Code
Codebase risk assessor that cross-references complexity, coverage, structural risk factors, and git history to identify where bugs are most likely to lurk.
How to install Swe Bug Assessor
Installs to ~/.claude/agents/chrisallenlane-claude-swe-workflows-swe-bug-assessor.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/chrisallenlane/claude-swe-workflows/HEAD/agents/swe-bug-assessor.md -o ~/.claude/agents/chrisallenlane-claude-swe-workflows-swe-bug-assessor.md Restart Claude Code, or start a new session, for it to be picked up.
What Swe Bug Assessor does
name: SWE - Bug Assessor description: Codebase risk assessor that cross-references complexity, coverage, structural risk factors, and git history to identify where bugs are most likely to lurk. Produces a ranked hotspot list for focused investigation. model: opus
Purpose
Analyze a codebase to identify where bugs are most likely to lurk. Cross-reference multiple signals — code complexity, test coverage gaps, structural risk factors, and optionally git history — to produce a ranked lis
Alternatives in Development
- Engram Assessor — Independent grader of learner productions for the Engram learning plugin 1.4k ★
- Refactor Engineer — Behavior-preserving refactoring specialist 221 ★
- Tech Debt Assessor — Use this agent to assess technical debt and code quality in a bounded region of the Revel codebase 107 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Thunderstruck Investigator
Forensic failure-mode analyst for one thunderstruck hotspot bundle. Reads the flagged code and its change hist
Swe Dev Verifier First Thinking
Treats ideas, analogies, skills, and claimed understanding as computational objects. Applies complexity-theore
Swe Dev Visible Thinking Coach
Coach essays, interviews, GCSE/A-level/IB/Oxbridge, law, history, theology, English, TOK and humanities work.
Swe Bug Hunter
Focused bug investigator that deep-dives into specific code regions, writes reproducing tests for suspected bu
Perf Adversary
Red-team performance reviewer for in-flight code diffs. Reads a git diff and produces a ranked critique focuse
Edge Case Adversary
Independently brainstorm the edge cases a builder likely MISSED for a given deliverable, countering the "bound
Related Skills
Ext Attack Paths
Launch the ext-attack-planner agent to reason from the enumerated exposures to likely footholds, then present
Permissions Audit
Review settings.json permissions — flag overly broad rules, identify likely-unused ones, suggest pruning.
Swe Marketplace
A plugin marketplace focused mostly on software-development with Claude Code.