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.
npx skills add kumaran-is/claude-code-onboarding --skill ai-auditgit clone --depth 1 https://github.com/kumaran-is/claude-code-onboardingWrote 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.
[](https://agentmods.dev/skills/kumaran-is/claude-code-onboarding/ai-audit)<a href="https://agentmods.dev/skills/kumaran-is/claude-code-onboarding/ai-audit"><img src="https://agentmods.dev/badge/skills/kumaran-is/claude-code-onboarding/ai-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kumaran-is/claude-code-onboarding/ai-audit"><img src="https://agentmods.dev/badge/skills/kumaran-is/claude-code-onboarding/ai-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00103 | $0.03639 |
| Opus 5 | $0.00051 | $0.01819 |
| Sonnet 5 | $0.00021 | $0.00728 |
| Haiku 4.5 | $0.00010 | $0.00364 |
Grade A, and why
ai-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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Application Audit
Iron Law: Do not auto-fix. This skill produces reports and a remediation plan — not code changes. Every finding becomes a separate task for a follow-up session.
Run a comprehensive audit of an existing agentic application or AI feature against the AI Playbook. This is for verifying existing code, not designing new features.
The audit runs in five phases with explicit confirmation gates between each. Each phase produces a written artifact in the repo. The final output is a prioritized remediation plan.
When to use this vs. the individual skills
- Use
/ai-auditwhen you want a full pass against existing code and you're willing to let it run end-to-end. - Use the individual skills (
/ai-decision-record,/ai-launch-check,/ai-incident-response) and subagents (@ai-security-reviewer,@ai-eval-designer) when you want finer control between phases or you're only doing part of the work.
Operating procedure
Walk through the five phases below in order. Do not skip phases. Each phase has an explicit confirmation gate where the user can pause, redirect, or abort.
Before starting, load the ai-playbook skill if it isn't already in context.
Phase 0: Scoping (no artifact)
Before any audit work, get clarity on what's being audited. Ask the user:
- What is the feature slug? (Used for directory naming. If unsure, propose one from the repo structure.)
- Is this a single feature audit or a multi-feature codebase? (If multi-feature, ask which feature to audit first — running the full audit on multiple features in one shot is too token-heavy.)
- Where is the AI code? (Path or paths. If unknown, offer to scan and report back before continuing.)
- Is there an existing Decision Record? (Check
docs/ai-decisions/<feature-slug>.md. If yes, this skips Phase 1 and uses it as input.)
After confirming scope, summarize the plan:
Audit plan for: <feature-slug>
- AI code location: <paths>
- Phases to run:
1. Decision Record reverse-engineering (or skip if exists)
2. Security review via @ai-security-reviewer subagent
3. Eval audit via @ai-eval-designer subagent
4. Launch check (gate)
5. Consolidated remediation plan
- Estimated wall time: 60–120 minutes depending on codebase size
- Estimated token cost: significant (two subagents + main session). Confirm before proceeding.
Proceed? (yes / scope-down / abort)
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.
- 6d ago First seen · 341 lines · 103 tokens per session scan A f75c1d3c0461
ai-audit is a skill published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 103 tokens to every session and 3,639 once invoked, about $0.0005 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.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.