befund

Plugin befund from marketplace werkstoff in Anselmoo/werkstoff. Commands read from the repo's manifest — 11 days ago.

Skills (16)

• befund-arch-health

  Reads the full stage_graph.json from befund-stage-map and finds god-modules, circular dependencies, and layering violations, verifying each against actual code. Use when the user asks to "find architecture deficiencies", "find god-objects or god-modules", "detect dependency cycles", "check for layer

• befund-autopilot

  Runs befund's full workflow (CHECK → PLAN → approval gate → FIX+VALIDATE) with andon-loop, halting on unproven wires or unmet blockers. Use when the user asks to "run the auto-pilot", "check, plan, fix and validate this repo", or wants the full befund value stream.

• befund-ci-topology

  Audits git remote topology and CI/CD configuration for redundancy, mirror risk, doc-vs-config drift, and commit-signing inconsistencies, masking every credential to a short preview. Use when the user asks to "audit our git remotes", "check CI setup", "find redundant mirrors", "verify docs about CI/C

• befund-code-idiom

  Judges idioms against the actual language version declared in the repo's manifest, never a fixed list, and categorizes each finding as modernization or smell. Use when the user asks to "find modernization opportunities", "check for deprecated idioms", "find code smells", or as part of befund-autopil

• befund-complexity-score

  Computes a relative complexity/attention-priority index per stage using the fixed formula 2.94 x (KSLOC)^1.10, and lists unmeasured stages plainly rather than inventing numbers. Use when the user asks "which module needs attention first", "score complexity per stage", "what's our tech debt hotspot",

• befund-docs-drift

  Extracts falsifiable claims about current code state from CLAUDE.md, README.md, DECISIONS.md, ARCHITECTURE.md, and ADR files, and verifies each against the cited code. Use when the user asks to "check documentation accuracy", "find doc drift", "verify our docs match the code", or as part of befund-a

• befund-extract-rules

  Mines executable calculations, validations, and state transitions into Given/When/Then rules, looping to convergence and requiring a scored judge verdict to pass for any P0 rule. Use when the user asks to "extract business logic", "document the domain rules hidden in this code", "turn tribal knowled

• befund-idiom-fix

  Applies only eligible modernization-category findings from code_idiom_summary.json, gated behind idiom_fix.mode="fix", one remediator dispatch per (file, kind) cluster, then hands off to andon-verify without self-verifying. Use when the user explicitly asks to "apply the modernization findings", "fi

• befund-lint-audit

  Extracts discrete, checkable rules from .claude/house-rules.md (or CLAUDE.md as a best-effort fallback) and dispatches finders to verify violations against the actual code, capping dispatch at lint_max_rules. Reports violations only -- for mechanical fixes see befund-idiom-fix. Use when the user ask

• befund-portfolio

  Grades each repo in a directory of git repositories Red/Amber/Green/Gray by worst-signal-wins, and requires an explicit portfolio directory when cwd is itself a git repo. Use when the user asks to "sweep multiple repos", "assess our whole portfolio", "grade all our projects", or names a parent direc

• befund-preflight

  Verifies language detection, tool availability, smoke-parseability, house-rules presence, git/CI presence, and doc presence, then assigns a Ready/Ready-with-gaps/Not-ready verdict per downstream skill. Use when the user asks to "check if this repo is ready for befund", "run preflight", "can befund a

• befund-stage-map

  Extracts the real import/use graph per detected language, clusters files into stages by shallowest package boundary (never by manifest directory), and writes the full stage graph other befund skills depend on. Use when the user asks to "map the repo's architecture", "show me the real module boundari

• befund-status

  Reports which befund artifacts exist, whether they're stale relative to the latest commit, and never fabricates data for a skill that has not run. Use when the user asks "where does befund stand", "what's stale in our analysis", "what should we run next", or "befund status".

• befund-transform-brief

  Synthesizes stage-map, arch-health, and every other domain summary into a phased, ranked, read-only transformation plan. Use after befund's finding skills have run, when the user asks to "synthesize the findings into a plan", "write the modernization brief", "what should we fix and in what order", o

• befund-transform-execute

  Applies exactly one human-authorized phase of MODERNIZATION_BRIEF.md to the codebase. Use when the user explicitly asks to "execute phase N from the modernization brief", "apply this transform phase", or "run the merge/split transform-execute proposed". It applies exactly one human-authorized phase

• befund-ui-audit

  Statically audits JSX/TSX, Vue/Svelte, HTML, and CSS/SCSS source for accessibility, semantic-markup, and design-token problems -- never running or rendering the app. Use when the user asks to "audit UI accessibility", "check our components for a11y issues", "find hardcoded design values", "review th

Subagents (11)

• arch-health-auditor

  Use this agent when a repository's real stage/wire dependency graph (as built by stage-mapper) needs to be judged for god-modules, circular dependencies, or layering violations, with every candidate confirmed against actual source.

• business-rules-miner

  Use this agent when a codebase's executable business/domain logic needs mining into testable Given/When/Then rule specs with file:line citations, priority, and confidence.

• ci-topology-auditor

  Use this agent when a repository's git remote topology and CI configuration need auditing for redundancy, mirror risk, or drift against CI documentation.

• complexity-surveyor

  Use this agent when one stage, module, or language slice of the repo needs SLOC, file count, and cyclomatic-complexity measurement for a tech-debt prioritization index.

• convention-auditor

  Use this agent when code needs to be verified against documented project conventions from CLAUDE.md, house-rules.md, CONTRIBUTING, ADRs, or linter config.

• docs-drift-auditor

  Use this agent when documentation needs checking for drift against the actual current state of the codebase.

• idiom-auditor

  Use this agent when a codebase needs checking for deprecated language/library idioms judged against the actual version the repo targets, plus generic code smells.

• idiom-remediator

  Use this agent when a cluster of same-file, same-idiom-kind, already-verified befund-code-idiom "modernization"-category findings needs exactly those mechanical rewrites applied at their cited locations, and nothing else. Typical trigger is befund-idiom-fix dispatching one remediator per (file, kind

• stage-mapper

  Use this agent when a repository's real import/use graph needs extraction and clustering into architectural stages by shallowest package boundary, never by manifest directory.

• transform-executor

  Use this agent when a single, already-authorized phase from MODERNIZATION_BRIEF.md (a Merge, Split, or layering-violation fix) needs its code changes actually applied, with every Open Question for that phase already resolved by a human.

• ui-auditor

  Use this agent when a codebase's UI surface (JSX/TSX, Vue/Svelte, HTML, CSS/SCSS) needs a static, read-only audit for accessibility, semantic-markup, and hardcoded design-value problems.

Hooks (1)

• PreToolUse

  python3 -B "${CLAUDE_PLUGIN_ROOT}/hooks/guard_target_edit.py"

Similar plugins