agentops-audit

agentops-audit is a skill for Claude Code from ivegamsft/basecoat. It costs 63 tokens per session (611 once invoked), scanned A, original, MIT.

A review and improvement process for agent and skill specifications. It scores their clarity, safety, tool use, ambiguity handling, cost, and readiness for evaluation, then suggests revisions.

In plain words
What is it for?
Use it to audit agent or skill definitions, find instruction and policy gaps, assess model and tool fit, and produce revised specifications.
Why use it?
Agent instructions can be unclear, unsafe, or difficult to route correctly. This process identifies those weaknesses and turns them into concrete fixes and routing guidance.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to audit agent or skill definitions, find instruction and policy…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ivegamsft/basecoat/agentops-audit
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ivegamsft/basecoat --skill agentops-audit
Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agentops-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/ivegamsft/basecoat/agentops-audit.svg)](https://agentmods.dev/skills/ivegamsft/basecoat/agentops-audit)
Your own site
<a href="https://agentmods.dev/skills/ivegamsft/basecoat/agentops-audit"><img src="https://agentmods.dev/badge/skills/ivegamsft/basecoat/agentops-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 611 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.00611
Opus 5 $0.00032 $0.00305
Sonnet 5 $0.00013 $0.00122
Haiku 4.5 $0.00006 $0.00061

Measured 3d ago against content hash d47dc72f0898, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agentops-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/agentops-audit/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Operations Audit Skill

Audit agent or skill specifications and produce an actionable scorecard, risk list, and revised spec.

USE FOR

  • Scoring existing specs using a 0-5 rubric
  • Finding ambiguity, safety gaps, and tool-policy issues
  • Recommending concrete, prioritized fixes
  • Producing a revised spec with measurable success criteria
  • Generating routing rationale and estimated turn profile
  • Auditing model IDs and reasoning-effort compatibility against the generated capability catalog
  • Supporting audit and create_and_audit flows in agent-designer

DO NOT USE FOR

  • Writing product application code
  • Infrastructure deployment and operations
  • General-purpose code review outside agent/skill definitions

Required Scoring Dimensions (0-5)

  • clarity
  • safety_compliance
  • tool_correctness
  • ambiguity_handling
  • cost_latency_fit
  • eval_readiness

Audit Deliverables

  • scorecard
  • risks
  • concrete_fixes
  • revised_spec

Output Contract

Always include:

  1. Task-shaping classification (execution_mode, estimated_turns, tool_profile, uncertainty)
  2. Routing profile:
    • recommended_class: Fast | Balanced | Deep | Tool-Strict
    • rationale
    • estimated_turns: 1 | 2-3 | 4+
    • risk_mitigations
  3. Artifacts:
    • audit_report
    • agent_spec when a revised or regenerated spec is produced

Guardrails

  • Do not assume model family names are portable across providers.
  • Prefer measurable success criteria over subjective language.
  • Escalate when constraints conflict (for example: fast + deep reasoning + lowest cost).
  • Read docs/reference/model-capabilities.json before recommending a model.
  • Treat reasoning_depth as task metadata; do not emit reasoning_effort unless the selected model advertises configurable reasoning.
  • Report unknown model IDs and fixed-effort models separately. Effective organization and user entitlement remains a runtime check.
  • agent-design — authoring and scaffolding agent/skill assets

Read the full file on GitHub · 84 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 84 lines · 63 tokens per session scan A d47dc72f0898

Subscribe to this mod's changes

agentops-audit is a skill published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 611 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

agent-builder

Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code…

shareAI-lab/learn-claude-code · 125 tokens

code-review

Perform thorough code reviews with security, performance, and maintainability analysis. Use when user asks to review code, check for bugs, or audit a codebase.

shareAI-lab/learn-claude-code · 35 tokens

mcp-builder

Build MCP (Model Context Protocol) servers that give Claude new capabilities. Use when user wants to create an MCP server, add tools to Claude, or integrate external services.

shareAI-lab/learn-claude-code · 38 tokens

pdf

Process PDF files - extract text, create PDFs, merge documents. Use when user asks to read PDF, create PDF, or work with PDF files.

shareAI-lab/learn-claude-code · 32 tokens

crypto-arbitrage-bot-automated-trading

To orchestrate and deploy this execution skill dynamically via Autonomous AI Agent frameworks (LangChain, AutoGen, CrewAI), point your agent environment definition to the repository root and establish runtime parameters.

Cortex-AI-Network/crypto-arbitrage-bot-automated-trading · 0 tokens

AgentPrecept

A project workflow for coordinating several coding agents on the same software project. It uses shared project structure, decisions, handoffs, checklists, and memory so agents can continue each other's work.

rg8diaoa/AgentPrecept · 0 tokens