audit-agents

Included with Lifetime

$97 forever

Audit Claude Code subagents for quality, compliance, and maintainability. Use after creating or modifying agents, before releases, or for periodic quality checks.

AI Agents

What this skill does


# Audit Agents Command

Audit Claude Code subagents for quality, compliance with official documentation, and maintainability.

## Initialization

Before auditing, initialize the environment:

Get the current UTC date, capture the project root path, ensure the temp directory exists, and clean up stale audit files (unless `--recover`). The `subagent-development` skill provides authoritative validation guidance (auto-loaded when this command runs).

## What Gets Audited

- YAML frontmatter (name, description, tools, model, color)
- Naming conventions (lowercase kebab-case, max 64 chars)
- Description quality (third person, "PROACTIVELY use when..." guidance)
- Tool access configuration appropriateness
- Model selection correctness (haiku/sonnet/opus based on complexity)

## Command Arguments

| Argument | Description |
| --- | --- |
| *(none)* | Smart mode: audit modified, never-audited, or stale (>90 days) agents |
| `--force` | Audit ALL agents regardless of status |
| `--skip-validation` | Skip finding validation (faster, but may include false positives) |
| `--plugin-only` | Only audit local plugin agents |
| `--project-only` | Only audit project agents (`.claude/agents/`) |
| `--global-only` | Only audit globally installed plugin agents |
| `--recover` | Recover results from interrupted audit |
| `agent-name` | Audit specific agent(s) by name |

## Step 1: Discover Agent Sources

Detect all agent sources in local repo and globally installed plugins.

For local discovery, check marketplace repos, single plugin repos, and `.claude/agents/`. Track plugin names for deduplication.

For global discovery, check `~/.claude/plugins/` (Unix) or `%USERPROFILE%\.claude\plugins\` (Windows). Skip globals with local dev versions.

## Step 2: Determine Audit Queue

If specific agents named, audit those. If `--force`, audit all. Otherwise, audit modified/stale agents.

## Step 3: Present Audit Plan

Display mode, sources discovered, deduplication status, and audit queue.

## Step 4: Execute Audits

For each agent, spawn the `agent-auditor` subagent with source, path, and last audit date. Run in parallel batches of 3-5.

Subagents write findings to `.claude/temp/`. The main conversation thread collects results and updates audit logs using its Write/Edit tools.

## Step 4.5: Validate Findings

**Unless `--skip-validation` flag is present:**

1. Spawn the `audit-finding-validator` agent with:
   - `project_root`: The captured project root path
   - `audit_type`: "agent"
   - `audit_files`: List of `.claude/temp/audit-*-agent-*.json` file paths
2. Wait for validation to complete
3. Read updated JSON files with validation results
4. Filter out FALSE_POSITIVE findings completely before aggregation
5. Note: Filtered findings are logged to `.claude/temp/audit-filtered-findings.json`

**If `--skip-validation` flag is present:**

- Skip validation phase entirely (current speed preserved)
- Present all findings without filtering
- Note in summary: "Validation: Skipped"

## Step 5: Final Summary

Report total audited by source, results, and details table. Note that global agent fixes must be applied manually.

**Include validation statistics (if validation was performed):**

- Validation performed: Yes/No
- Findings validated: X
- False positives filtered: Y
- Verified findings: Z
- Unverified findings: W

## Scoring

- **PASS** (85+): Ready for use
- **PASS WITH WARNINGS** (70-84): Functional with improvement opportunities
- **FAIL** (<70): Issues that should be addressed

## Audit Log Location

All audit results are written to `.claude/audit/agents.md`.

Use `/audit-log agents` to view current audit status.

## Recovery

If context collapses mid-audit, use `/audit-agents --recover` to recover from `.claude/temp/` JSON files.

## Example Usage

### Example 1: Audit All Agents

```text
User: /audit-agents

Claude: Discovering agent sources...

## Audit Plan
**Mode**: SMART
- Plugin: claude-ecosystem (12 agents)
- Plugin: code-quality (3 agents)
- Deduplicated: claude-ecosystem (global skipped)

**Will audit**: 5 agents

[Spawns agent-auditor subagents]

## Audit Complete
| Source | Agent | Result | Score |
| --- | --- | --- | --- |
| plugin | code-reviewer | PASS | 100/100 |
```

### Example 2: Audit Specific Agent

```text
User: /audit-agents plugin:code-reviewer
Claude: PASS (Score: 100/100)
```

Files: 1

Size: 4.6 KB

Complexity: 13/100

Category: AI Agents

Source: https://github.com/melodic-software/claude-code-plugins/tree/main/plugins/claude-ecosystem/skills/audit-agents

Related in AI Agents

skill-development

Included

Comprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.

AI Agentsscripts

reprompter

Included

Transform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.

AI Agentsscripts

adaptive-compaction

Included

Adaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.

AI Agentsscripts

agent-skill-creator

Included

Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.

AI Agentsscripts

llm-wiki

Included

Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.

AI Agentsscripts

skill-master

Included

Agent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.

AI Agentsscripts