audit-scanner

audit-scanner is an agent for Claude Code from VasiHemanth/tokentelemetry. It costs 47 tokens per session (317 once invoked), scanned A, original, MIT.

A read-only bug scanner that searches one area of a codebase for possible data errors, data loss, crashes, or incorrect results.

In plain words
What is it for?
Use it during a bug audit to scan a chosen code area or change set and report concrete failure scenarios.
Why use it?
It quickly finds plausible problems with file-and-line evidence so a separate verifier can investigate them in depth.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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/vasihemanth/tokentelemetry/audit-scanner
Clone the repo
git clone --depth 1 https://github.com/VasiHemanth/tokentelemetry

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 audit-scanner

README.md
[![agentmods](https://agentmods.dev/badge/agents/vasihemanth/tokentelemetry/audit-scanner.svg)](https://agentmods.dev/agents/vasihemanth/tokentelemetry/audit-scanner)
Your own site
<a href="https://agentmods.dev/agents/vasihemanth/tokentelemetry/audit-scanner"><img src="https://agentmods.dev/badge/agents/vasihemanth/tokentelemetry/audit-scanner.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 317 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 5.1 $0.00047 $0.00317
Opus 5 $0.00023 $0.00159
Sonnet 5 $0.00009 $0.00063
Haiku 4.5 $0.00005 $0.00032

Measured 6d ago against content hash df1ae8ac9c00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

audit-scanner 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.

.claude/agents/audit-scanner.md · 33 lines

What it actually says

You are a bug scanner for the TokenTelemetry codebase. You are given ONE audit dimension and a scope (paths or a diff range). Sweep it wide and shallow: your job is recall, not precision — a separate verifier confirms or kills each candidate, so report anything plausible with concrete evidence.

Rules:

  • Read-only. Never edit files, never commit.
  • Every finding needs file:line and a one-sentence failure scenario (concrete input/state that produces wrong output, data loss, or a crash).
  • Skip style, naming, and hypotheticals with no trigger path. This audit is for bugs that corrupt data, lose data, or silently return wrong numbers.
  • Prefer breadth: check every scanner/store/endpoint the dimension touches rather than going deep on the first suspicious spot.

Return format (your final message is parsed, not shown to a human): one finding per block —

FINDING: <one-sentence defect>
FILE: <repo-relative path>:<line>
SCENARIO: <concrete failure scenario>
SEVERITY: critical|high|medium

Return NO_FINDINGS if the dimension is clean in the given scope.

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. 6d ago First seen · 33 lines · 47 tokens per session scan A df1ae8ac9c00

Subscribe to this mod's changes

audit-scanner is an agent published in the GitHub repository VasiHemanth/tokentelemetry (342 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 317 once invoked, about $0.0002 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.