auditor:deep-review

auditor:deep-review is a command for Claude Code from solanabr/auditor-skill. It costs 29 tokens per session (198 once invoked), scanned A, original, MIT.

A detailed security review of one instruction or function, including how it works and how an attacker might misuse it.

In plain words
What is it for?
Use it to document a function's purpose, inputs, assumptions, and risks, then report confirmed or suspected vulnerabilities.
Why use it?
It provides a focused examination when a single piece of code needs more scrutiny than a broad scan can provide.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the auditor plugin — 1 skill, 15 commands, 8 agents shipped together

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 commands/solanabr/auditor-skill/deep-review
Clone the repo
git clone --depth 1 https://github.com/solanabr/auditor-skill

Made for: Claude Code.

Or install auditor, the plugin that ships this one along with the rest of its 1 skill, 15 commands, 8 agents.

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 auditor:deep-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/solanabr/auditor-skill/deep-review.svg)](https://agentmods.dev/commands/solanabr/auditor-skill/deep-review)
Your own site
<a href="https://agentmods.dev/commands/solanabr/auditor-skill/deep-review"><img src="https://agentmods.dev/badge/commands/solanabr/auditor-skill/deep-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 198 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 $0.00029 $0.00198
Opus 5 $0.00015 $0.00099
Sonnet 5 $0.00006 $0.00040
Haiku 4.5 $0.00003 $0.00020

Measured 6d ago against content hash ed6f1c764ab8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

auditor:deep-review 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.

commands/deep-review.md · 17 lines

What it actually says

auditor-skill — Deep Review

Arguments: $ARGUMENTS

  1. Read the target file completely.
  2. Run Phase 0.5 Context Reconstruction on the target function (templates/context-worksheet.md): purpose, inputs, invariants (≥3), assumptions (≥5), external-interaction risks (≥3) — each cited to L#.
  3. Fill templates/instruction-worksheet.md; cross-reference code that shares state.
  4. Adversarially model exploitation. Any high-severity finding (N≥6) must pass the Rule 5b validation gate.
  5. Report per-item verdicts + findings for this unit only.
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 · 17 lines · 29 tokens per session scan A ed6f1c764ab8

Subscribe to this mod's changes

auditor:deep-review is a command published in the GitHub repository solanabr/auditor-skill (53 stars, last pushed 3d ago), licensed MIT. It adds 29 tokens to every session and 198 once invoked, about $0.0001 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.