audit-deep

audit-deep is a skill for Claude Code, Codex from LucasSantana-Dev/sharekit. It costs 66 tokens per session (1,459 once invoked), scanned A, original, MIT.

A combined project health check that reviews tests, configuration, hooks, performance, security, connectors, plugins, and related checks in one report.

In plain words
What is it for?
It is for weekly maintenance, pre-release checks, reviews after major architecture changes, and onboarding checks on an unfamiliar repository.
Why use it?
It removes the need to run several separate audits and manually combine their findings. The result is a severity-ranked list with a prioritized repair plan.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/lucassantana-dev/sharekit/audit-deep
Any agent
npx skills add LucasSantana-Dev/sharekit --skill audit-deep
Clone the repo
git clone --depth 1 https://github.com/LucasSantana-Dev/sharekit

Made for: Claude Code, Codex.

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 audit-deep

README.md
[![agentmods](https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/audit-deep.svg)](https://agentmods.dev/skills/lucassantana-dev/sharekit/audit-deep)
Your own site
<a href="https://agentmods.dev/skills/lucassantana-dev/sharekit/audit-deep"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/audit-deep.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,459 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00066 $0.01459
Opus 5 $0.00033 $0.00730
Sonnet 5 $0.00013 $0.00292
Haiku 4.5 $0.00007 $0.00146

Measured 3d ago against content hash c0af93cedeec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-deep 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.

sharekit-profile/.claude/skills/audit-deep/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Deep

Runs every audit skill in parallel against one repo, reconciles findings by severity, and proposes a single prioritized remediation plan. Replaces the "run six audits manually and try to remember what each said" pattern.

Auto-invocation triggers

  • User asks "is this project healthy", "audit this repo", "tech debt review"
  • Weekly per-active-repo via launchd (combine with diagnostic-skills schedule)
  • Pre-release (before any version bump on a production-bound repo)
  • After significant architecture change or new team member onboarding

Workflow

Phase 1 — Parallel audit dispatch (always)

Invoke in parallel via Agent tool or sequential Skill calls:

  • test-health — suite proportionality, coverage, runtime
  • config-drift-detect — gate compatibility
  • hook-effectiveness — hooks fire/exit/latency stats
  • performance-audit or performance-test — runtime perf
  • security-audit — secrets, deps, OWASP
  • mcp-audit — MCP server usage
  • plugin-audit — plugin enabled-vs-used
  • socket-audit — supply chain (npm only)
  • forge-audit — if Forge ecosystem repo
  • scripts/check-harness-manifest.sh — verifies .harness/manifest.json sha256 fingerprints match tracked files and MCP policy invariants hold (defaultDeny=true, non-empty dangerousPatterns + approvedServers). Run from repo root when .harness/ exists; non-zero exit is a CRITICAL finding.
  • skills/catalog-gardener — detects dead links, stale artifacts, oversize skills (>8KB body, >150 lines), orphan skills, and frontmatter completeness issues. Outputs severity-ranked report with remediation hints. Run as part of Phase 1 parallel audit dispatch.

Each returns a structured verdict + findings.

Phase 2 — Reconcile by severity

Aggregate all findings into one ranked list:

  • CRITICAL — blocks merge / release / production safety
  • HIGH — degrades workflow significantly
  • MEDIUM — measurable but not blocking
  • INFO — track but no action

Cross-reference: a HIGH from config-drift that explains a HIGH from test-health is reported as one root cause, not two findings.

Read the full file on GitHub · 140 lines

Files

What ships with it

4 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 · 140 lines · 66 tokens per session scan A c0af93cedeec

Subscribe to this mod's changes

audit-deep is a skill published in the GitHub repository LucasSantana-Dev/sharekit (1 stars, last pushed 3d ago), licensed MIT. It adds 66 tokens to every session and 1,459 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 2026-08-31.

Related

Other skills, from other repositories

prpm-development

Use when developing PRPM (Prompt Package Manager) - comprehensive knowledge base covering architecture, format conversion, package types, collections, quality standards, testing, and deployment.

pr-pm/prpm · 36 tokens

creating-cursor-rules-skill

Expert guidance for creating effective Cursor IDE rules with best practices, patterns, and examples.

pr-pm/prpm · 24 tokens

creating-opencode-plugins

Use when creating OpenCode plugins that hook into command, file, LSP, message, permission, server, session, todo, tool, or TUI events - provides plugin structure, event API specifications, and implementation patterns for JavaScript/TypeScript event-driven modules.

pr-pm/prpm · 59 tokens

thoroughness

Use when implementing complex multi-step tasks, fixing critical bugs, or when quality and completeness matter more than speed - ensures comprehensive implementation without shortcuts through systematic analysis, implementation, and verification phases.

pr-pm/prpm · 40 tokens

Cursor rules for Convex development with best practices

Skill "Cursor rules for Convex development with best practices" from AmariahAK/atlarix-skills, covering cursor rules for convex development with best practices, when to use this skill, source, convex guidelines and function guidelines.

AmariahAK/atlarix-skills · 9 tokens

Cursor rules for setting up email-to-Telegram forwarding via Cloudflare Email Ro

Cursor rules for setting up email-to-Telegram forwarding via Cloudflare Email Routing and Workers using the mail2tg CLI.

AmariahAK/atlarix-skills · 16 tokens