claude

code-auditor-agent

Four-phase PR review pipeline and full codebase audit pipeline for Claude Code. PR review: code correctness swarm, claim verification, skeptical external review, security analysis with deduplication. Codebase audit: file inventory, grep triage, parallel discovery swarm, verification, gap-fill, consolidation, TODO generation, and optional fix loop.

2 on GitHubby Emasoftv4.4.1MITupdated 9 days agodeveloper-tools
/

Plugin code-auditor-agent from marketplace emasoft-plugins in Emasoft/emasoft-plugins. Commands read from the repo's manifest — 9 days ago.

What it installs

Skills (5)

  • caa-codebase-audit-and-fix-skill

    Trigger with /audit-codebase, 'audit the codebase', 'compliance audit', 'codebase audit', 'scan and fix the code'. Use when auditing a codebase (whole, scoped, or changed-since-a-ref) and optionally applying fixes.

  • caa-pr-review-and-fix-skill

    Trigger with 'review and fix the PR', 'review the PR and apply fixes', 'pre-merge review and fix'. Use when reviewing a GitHub PR AND then applying root-cause fixes to its changed files.

  • caa-pr-review-skill

    Trigger with 'review the PR', 'check the PR', 'audit the PR', 'pre-merge review'. Use when reviewing a GitHub PR or running a pre-merge quality gate.

  • caa-scenario-generator-skill

    Trigger with "/caa-extended-audit", "generate scenarios", "discover entry points". Use when an extended audit needs end-to-end scenario walks beyond line review. Emits scenarios.json for the ultracode engine's scenario-walk lens.

  • ecaa-self-test-24

    Trigger with "ecaa self test", "run efficacy gate". Use when verifying the ultracode engine catches every seeded bug in the bundled fixtures — before release or on a schedule. Runs the pytest gate plus one engine pass.

Slash commands (11)

  • /code-auditor-agent:caa-audit-codebase-cmd

    Legacy alias for the ultracode codebase audit. Superseded by /caa-scan (scan-only) and /caa-scan-and-fix (audit + root-cause fixes). Kept so existing "audit the codebase" muscle memory still resolves; it simply redirects to the new ultracode commands.

  • /code-auditor-agent:caa-delta-audit-cmd

    Legacy alias for the incremental (changed-since-a-ref) ultracode audit. Superseded by /caa-delta. Kept so existing "audit the changes" / "incremental audit" muscle memory still resolves; it simply redirects to the new ultracode command.

  • /code-auditor-agent:caa-delta

    Recheck recent changes — scan-only audit of files changed since a git ref (default origin/main…HEAD), via the shared caa-engine (map → filter → reduce). Optionally traces direct dependents of the changed files. No fixes, no git writes. Final report → reports/code-auditor-agent/.

  • /code-auditor-agent:caa-impl-compare

    Compare multiple candidate implementations of the same task against ONE fixed input/contract via the shared caa-engine (task=impl-compare): map (one opus evaluator per candidate, scoring correctness/edge-cases/performance/quality) → filter (adversarial verify of each correctness verdict) → reduce (a

  • /code-auditor-agent:caa-pr-review

    PR review — ultracode audit of a GitHub PR via the shared caa-engine `pr` lens-set: per-file scan of the changed files PLUS two PR-unique once-per-run lenses (claim-verification: PR description vs actual diff; cross-layer: cross-file mismatches) → one PR-review comment with a PASS/CONDITIONAL/FAIL v

  • /code-auditor-agent:caa-precommit

    Pre-commit gate — ultracode scan-only audit of the STAGED files only, via the shared caa-engine (map: one opus auditor per file → filter: adversarial verify → reduce: one consolidated gate report). PASS only when no CRITICAL/MAJOR survives; otherwise FAIL with the blocking findings. Fast, no fixes,

  • /code-auditor-agent:caa-scan-and-fix

    Scan AND fix — ultracode audit that also applies fixes, via the shared caa-engine: map (audit) → filter (verify) → reduce (scan report) → fix (one opus fixer edits its ONE file in place) → fix-verify (different reviewer confirms each fix, no regressions) → final fix report. Edits files in the workin

  • /code-auditor-agent:caa-scan

    Whole-codebase (or explicit-scope) scan-only audit via the shared caa-engine: map (one opus auditor per file) → filter (adversarial verify) → reduce (one consolidated audit report). No fixes, no git writes. Final report → reports/code-auditor-agent/. Whole-repo runs are expensive — the command estim

  • /code-auditor-agent:caa-spec-audit

    Audit a codebase against a specification / requirements document via the shared caa-engine (task=spec-compliance): map (one opus auditor per file, classifying which spec clauses it implements/violates) → filter (adversarial verify) → reduce (one consolidated report listing every MISSING spec clause

  • /code-auditor-agent:caa-verify-implementation-and-fix

    Verify an EXISTING implementation against a TRDD/spec AND repair it FIX-AS-YOU-GO via the shared caa-engine (task=spec-compliance, mode=scan-and-fix): each per-file opus agent classifies its file's spec clauses AND, in the SAME read, corrects every VIOLATED clause and completes every PARTIAL one in

  • /code-auditor-agent:caa-verify-implementation

    Verify that an EXISTING implementation correctly + completely fulfills a TRDD or a spec/requirements document, via the shared caa-engine (task=spec-compliance): map (one opus auditor per file classifying which spec clauses it IMPLEMENTS / VIOLATES / PARTIALLY implements) → filter (adversarial verify

Subagents (1)

  • code-auditor-agent-main-agent

    Main entry point for the code-auditor-agent role (quad-match #4). Use when invoked as `claude --agent code-auditor-agent-main-agent` or dispatched as the code-auditor role to audit code headlessly. Routes the request to the right ultracode command (pre-commit gate, PR review, delta audit, whole-code

View source on GitHub

More from Emasoft/emasoft-plugins

All 14 plugins →

Comprehensive validation suite for Claude Code plugins, marketplaces, hooks, skills, and MCP servers. Includes 17 Python validators, 2 expert agents, and 190+ validation rules.

52 skills · 14 commands · 14 agents

2

Expert agent plus 60 preserved Claude Code documentation chapters (mods, plugins, hooks, skills, subagents, marketplaces, settings) for creating, fixing, improving and evaluating Claude Code mods and plugins.

69 skills · 1 command · 2 agents

2

MCP server that offloads bounded LLM tasks from Claude Code to cheaper local (LM Studio, Ollama, vLLM, llama.cpp) or remote (OpenRouter) models. Profile-based configuration with ensemble mode, auto-batching, and secret scanning.

19 skills · 25 commands · 6 agents · hooks

2

High-accuracy skill activation (88%+) with AI-analyzed keywords, weighted scoring, synonym expansion, and three-tier confidence routing.

8 skills · 23 commands · 1 agent · hooks

2

Automatically reviews and fixes Claude's code changes using a separate Claude instance in a git worktree after commits. Two-phase pipeline: code correctness (Phase 1) then functionality verification (Phase 2).

1 skill · 2 agents · hooks

2

Universal terminal-menu system for Claude Code plugins. Any agent invokes scripts/menu_write.py via Bash (~25ms) to render a JSON menu spec to a tempfile; a bundled Stop hook emits it as systemMessage at main-session turn end — the menu appears in the user terminal exactly when they can type a reply. No subagent fork, no extended-thinking overhead, no token cost to the orchestrator.

2 commands · hooks

2

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

ecc

claudecodex

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

affaan-m/ECC 302,088

Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives

1 command

anthropics/claude-code 155,476

Design fluency for frontend development. 1 skill with 24 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.

1 skill · 4 agents · hooks

pbakaus/impeccable 109,099

Cross-installation agent federation with zero-trust security, PII-gated data flow, and compliance-grade audit trails

3 skills · 1 command · 1 agent

ruvnet/ruflo 81,589

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Imbad0202/academic-research-skills 56,698

Maintain code-auditor-agent?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins14 plugins