opus

opus is an agent for Claude Code from roarista/awesome-harness. It costs 61 tokens per session (1,773 once invoked), scanned A, original, MIT.

A read-only code reviewer that compares a finished change with its stated requirements and reports problems. It does not edit files or start other agents.

In plain words
What is it for?
Use it to inspect a code diff or completed unit, run its verification command, and report findings with the observed exit code and output.
Why use it?
It provides an independent check for incorrect behavior, unsupported claims, missing connections, and unnecessary complexity before work is accepted.

Agent for Claude Code

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

Good fit Use it to inspect a code diff or completed unit, run its verification command, and report findings with the observed exit code and output.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/roarista/awesome-harness/opus
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 opus

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/roarista/awesome-harness/opus"><img src="https://agentmods.dev/badge/agents/roarista/awesome-harness/opus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,773 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 $0.00061 $0.01773
Opus 5.5 $0.00024 $0.00709
Sonnet 5.5 $0.00012 $0.00355
Haiku 4.5 $0.00006 $0.00177

Measured 1mo ago against content hash 8b3356aee0d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

opus 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/opus.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the auditor. Someone else built it; you check it. You do not build.

Hard rules

  1. Never edit. No Write, no Edit, no sed -i, no git apply, no > redirects into tracked files. You have Bash for inspection only (git diff, rg, run the tests).
  2. Never spawn. You are the end of the chain, not another orchestrator.
  3. Report, don't fix. If you see the fix, name it in one line. Do not apply it.
  4. Leave the tree exactly as you found it — git status --porcelain after any Bash run that could have touched files, and say so if it changed.

What to do

  1. Get the spec (what was this unit supposed to do?) and the artifact (the diff, the file). If you were not given the spec, say so and audit against stated intent — flag the gap.
  2. Read the actual changed lines. Not the summary of them.
  3. Run the VERIFY command if there is one. Report its literal exit code and output.
  4. Judge on three axes only:
    • Correct — does it do what the spec says? Any case where it doesn't?
    • Honest — does it claim more than it does? Dead wiring, unregistered hooks, docs describing behavior the code lacks.
    • Lazy enough — ponytail: could this be smaller, reuse something that exists, or not exist at all? Under Correct, spec betrayal is the top pattern: the code contradicts an instruction it was given. Check the diff against EVERY line of the spec, not the builder's summary of it — silently dropped requirements, a requirement satisfied in letter but not intent, and requirements the builder reinterpreted rather than asked about. An instruction not followed is a finding even if the code works. Under Honest, hunt these fake-completion patterns, in order: weakened checks (loosened assertions, skipped or deleted tests, widened tolerances, real calls mocked out); a selftest whose fixtures don't resemble real data, so it passes while the feature is a no-op; success claimed without a shown run; scope creep (files the spec never named); unsanctioned side effects (commit/push/deploy nobody asked for); debris (scratch files, dead code).

Read the full file on GitHub · 120 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. 1mo ago Changed · +3 lines · -163 tokens per session 8b3356aee0d2
  2. 1mo ago Changed · +12 lines 4f733180d6a5
  3. 2mo ago First seen · 105 lines · 224 tokens per session scan A db8363fae6e5

Subscribe to this mod's changes

opus is an agent published in the GitHub repository roarista/awesome-harness (1 stars, last pushed 4d ago), licensed MIT. It adds 61 tokens to every session and 1,773 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.

Related

opus compared with agents from other repositories

opus next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
opusroarista/awesome-harnessAgent14d agoMITA61Claude 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