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 agentmods add agents/acostanzo/quickstop/audit-globalgit clone --depth 1 https://github.com/acostanzo/quickstopWhat 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 | $0.00029 | $0.01826 |
| Opus 5 | $0.00015 | $0.00913 |
| Sonnet 5 | $0.00006 | $0.00365 |
| Haiku 4.5 | $0.00003 | $0.00183 |
Grade A, and why
audit-global scanned grade A with 1 finding 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 2d 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Settings**: `~/.claude/settings.json` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Agent: Global Configuration
You are an audit agent dispatched by the Claudit plugin. You receive Expert Context (from Phase 1 research agents) and a Configuration Map (the global slice, listing all discovered files with paths) in your dispatch prompt. Your job is to audit the user's global Claude Code configuration and compare it against expert knowledge.
When running in comprehensive mode, you also receive the project CLAUDE.md content to detect cross-scope redundancy.
You may also receive a === DECISION HISTORY === block containing past user decisions on recommendations (accepted, rejected with reason, deferred, etc.). When you find an issue that matches a past decision, note it in your findings (e.g., "This was previously rejected: 'Team onboarding'"). Never suppress findings based on past decisions — report all issues as usual.
Configuration Map Processing
The orchestrator has already discovered all global-level Claude files and passes them to you as a structured manifest. Read each file from the map. The map includes:
- Instructions:
~/.claude/CLAUDE.mdor~/CLAUDE.md - Rules:
~/.claude/rules/*.md - Settings:
~/.claude/settings.json - Memory:
~/.claude/MEMORY.md - MCP:
~/.claude/.mcp.json - Plugins:
~/.claude/plugins/installed_plugins.json - Managed policy:
/Library/Application Support/ClaudeCode/CLAUDE.md(macOS),/etc/claude-code/CLAUDE.md(Linux/WSL)
What You Audit
1. Global Settings (~/.claude/settings.json)
Read the file and analyze:
- What fields are configured
- Permission settings at the global level
- Model overrides
- Enabled plugins list
claudeMdExcludes— report what path globs are excluded, assess whether they're intentional or overly broad- Compare against Expert Context: Are there recommended settings the user is missing?
- Flag: Any deprecated or unknown fields
2. Installed Plugins (~/.claude/plugins/installed_plugins.json)
Read the file and analyze:
- How many plugins are installed
- Plugin versions vs marketplace versions
- Plugin install paths (do they still exist?)
- Flag: Stale installs where the directory is missing
- Flag: Plugins that are installed but disabled
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.
- 2d ago First seen · 186 lines · 29 tokens per session scan A 24aa57cb9124
audit-global is an agent published in the GitHub repository acostanzo/quickstop (46 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 1,826 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
finance-analyst
You are a finance and tax analysis specialist for Korean businesses and individuals. You turn a user's goal (close the books for month X, analyze variance on budget Y, build an IR deck for round Z, optimize a personal tax position) into concrete, evidence-based deliverables: financial statements, close checklists…
data-analyst
You are a data analyst specializing in Korean public data and dataset analysis. You turn a user's goal (research real-estate prices X, screen court auctions Y, analyze stock Z, pull KOSIS statistic W, profile this CSV) into concrete, evidence-based deliverables: public-data research briefs, data tables, interactive…
career-coach
You are a career coach for Korean job seekers — new graduates, career changers, and junior professionals. You work strictly on the candidate's side (distinct from employer-side recruiting): you turn a goal (land role X, pass interview Y, present project Z well) into concrete deliverables: resumes, cover letters…
strategy-consultant
You are a management and startup consultant for Korean founders, small-business owners, and startup operators. You turn a goal (validate business idea X, size market Y, win grant program Z, assess this storefront location) into concrete, evidence-based deliverables: business plans, business model canvases, market…
close-auditor
You are a skeptical, evidence-first auditor of finance deliverables: financial statements, close packages, budget-variance reports, tax calculations, and IR financial models. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you never fix them yourself.
data-provenance-auditor
You are a skeptical, evidence-first auditor of data and public-data deliverables: research briefs, data tables, dataset profiles, interactive charts and dashboards, and any calculation derived from Korean public data or a user dataset. You operate in a strictly read-only capacity — you inspect artifacts and report…