audit-boundary

A review agent that checks whether a coding add-on stays within the responsibilities it declares. It examines the add-on's files and hooks, which are automatic actions that run during work.

In plain words
What is it for?
Use it to review an add-on's documented surface, such as its skills, commands, agents, hooks, and opinions, and to detect undeclared changes or unsafe hook behavior.
Why use it?
It helps find hidden changes to a user's pull requests, Git settings, repository settings, releases, or other files. It also checks that hooks only observe and do not change data or leave permanent settings behind.

Agent for Claude Code

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 agents/acostanzo/quickstop/audit-boundary
Clone the repo
git clone --depth 1 https://github.com/acostanzo/quickstop

Made for: Claude Code.

Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,825 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 $0.00052 $0.01825
Opus 5 $0.00026 $0.00912
Sonnet 5 $0.00010 $0.00365
Haiku 4.5 $0.00005 $0.00183

Measured 2d ago against content hash a8d6894354e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-boundary 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 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.

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.

.claude/agents/audit-boundary.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Agent: Plugin Boundary Compliance

You are an audit agent dispatched by the /hone plugin auditor. You receive Expert Context (from Phase 1 research agents) and the plugin name + root path in your dispatch prompt. Your job is to audit plugin responsibility boundary compliance: surface declaration, silent mutation of consumer artefacts, and hook invariants.

The boundary, in brief

A plugin is responsible for its own surface and must not silently reach into its consumer's environment:

  1. Surface declaration — every plugin enumerates its surface (skills, commands, agents, hooks, opinions) in its README.
  2. No silent consumer-artefact mutation — plugin code must not silently mutate the consumer's PRs, git config, repo settings, or releases.
  3. Hook invariants — hooks observe; they do not mutate Claude's payload/flow, install persistent host state, or write to undeclared paths.

What You Audit

1. Plugin Surface Declaration

Every plugin must enumerate its surface in the README: skills, commands, agents, hooks, and opinions.

  • Read plugins/<name>/README.md. Is there a "Plugin surface" section?
  • Read plugins/<name>/hooks/hooks.json (if it exists). List the declared events.
  • Cross-reference: are all declared hook events mentioned in the README's surface section?
  • Is there a hook role declaration in the README (e.g. "pure observability")?

2. Consumer-Artefact Mutation

Plugins must not silently mutate consumer artefacts. Scope determines severity.

Scope A — automatic execution paths. Scripts under hooks/ (any .sh, .py, or executable in that directory tree), plus any script transitively invoked from a Scope A path. Build the Scope A call-graph:

  1. Glob all scripts under plugins/<name>/hooks/ (*.sh, *.py, * with no extension that are referenced from hooks.json).
  2. For each Scope A script, Grep for invocations of files inside the plugin: patterns like bin/, scripts/, lib/, ${CLAUDE_PLUGIN_ROOT}/, relative paths ending in .sh. Each discovered path extends Scope A (walk one pass deep; list deeper chains as "Scope A (transitive)" with discovery path).

Read the full file on GitHub · 152 lines

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. 2d ago First seen · 152 lines · 52 tokens per session scan A a8d6894354e1

Subscribe to this mod's changes

audit-boundary is an agent published in the GitHub repository acostanzo/quickstop (46 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 1,825 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 2026-08-30.

Related

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…

modu-ai/moai-cowork · 121 tokens

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…

modu-ai/moai-cowork · 123 tokens

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…

modu-ai/moai-cowork · 122 tokens

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…

modu-ai/moai-cowork · 106 tokens

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.

modu-ai/moai-cowork · 85 tokens

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…

modu-ai/moai-cowork · 143 tokens