agentmods.dev

opus48-audit

opus48-audit is an agent for Claude Code from roarista/awesome-harness. It costs 0 tokens per session (485 once invoked), scanned A, original, MIT.

A read-only code auditor for a completed unit of work. It compares the files with a written specification, runs the unit's tests, and reports findings with severity and file locations.

In plain words
What is it for?
Use it to review finished code against its goals and verification steps, then produce a pass-or-fix verdict with the most important findings.
Why use it?
It provides an independent check without changing files, helping catch incorrect behaviour, crashes, security issues, missing requirements, and tests that give false confidence.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions Codex.

not rated 1repo 4d ago A scan 0 tokens original MIT

Good fit Use it to review finished code against its goals and verification steps, then produce a pass-or-fix verdict with the most important findings.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/roarista/awesome-harness/opus48-audit
View source ↗ roarista/awesome-harness
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.

Clone the repo
git clone --depth 1 https://github.com/roarista/awesome-harness

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 opus48-audit

README.md
[![agentmods](https://agentmods.dev/badge/agents/roarista/awesome-harness/opus48-audit/github.svg)](https://agentmods.dev/agents/roarista/awesome-harness/opus48-audit)
Your own site
<a href="https://agentmods.dev/agents/roarista/awesome-harness/opus48-audit"><img src="https://agentmods.dev/badge/agents/roarista/awesome-harness/opus48-audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for opus48-audit

Your own site · 80×15
<a href="https://agentmods.dev/agents/roarista/awesome-harness/opus48-audit"><img src="https://agentmods.dev/badge/agents/roarista/awesome-harness/opus48-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 485 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.00485
Opus 5.5 $0.00000 $0.00194
Sonnet 5.5 $0.00000 $0.00097
Haiku 4.5 $0.00000 $0.00049

Measured 1mo ago against content hash ad8824d3d7b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

opus48-audit 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 1mo 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.

agents/opus48-audit.md · 20 lines

What it actually says

You are an independent auditor. You did not write this code. Read the spec and the files, attack them through the lenses the prompt names, run the unit's tests yourself, and report findings with severity (CRITICAL/HIGH/MEDIUM/LOW) + file:line + one-line fix. "No findings" must list what you attacked and found sound. Never edit files, never run git write commands, never make paid calls, never print secrets. Return at most 8 lines: verdict PASS/FIX, counts by severity, top finding, what you verified.

SHARED VERDICT RUBRIC (identical in opus, opus48-audit, codex-audit — 2026-10-01; supersedes any other verdict wording in this file)

Severity:

  • CRITICAL: data loss/corruption, security breach, secret leak, money moved wrongly — reachable in normal use.
  • HIGH: wrong behavior or crash on a normal path; invented/nonexistent API; spec GOAL not met.
  • MEDIUM: wrong on edge/malformed input; missing error handling on an I/O or external call; a risky branch with no test; a test that cannot fail (false green).
  • LOW: style, naming, minor perf, docs, harmless redundancy. Verdict (first line, exactly one of):
  • VERDICT: REJECT if any CRITICAL or HIGH; OR any MEDIUM touching money/auth/credentials/secrets/data-loss/prod data; OR the unit's VERIFY was not run or fails.
  • VERDICT: PASS WITH FIXES if only MEDIUM/LOW outside those classes — list each fix.
  • VERDICT: PASS only if nothing above LOW. A PASS must name what you attacked and found sound. Padded or speculative findings count against you exactly like misses.
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. 1mo ago First seen · 20 lines · 0 tokens per session scan A ad8824d3d7b2

Subscribe to this mod's changes

opus48-audit is an agent published in the GitHub repository roarista/awesome-harness (1 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 485 tokens. 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 2026-10-02.

Code reviewTesting
Related

opus48-audit compared with agents from other repositories

opus48-audit next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
opus48-auditroarista/awesome-harnessAgent14d agoMITA0Claude Code
thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claudeAgent4.1ktodayMITA68Claude Code
review-obsidian-guidelinesuphy/obsidian-reminderAgent662yesterdayMITA63Claude Code
karimo-implementeropensesh/KARIMOAgent29025d agoApache-2.0A49Claude Code
atomic-auditordamusix/atomic-claudeAgent1165d agoMITA169Claude Code
reviewergenkovich/sddAgent19922d agoMITA81Claude Code
Reviewermonkilabs/opencastleAgent80yesterdayMITA30Claude Code