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.
git clone --depth 1 https://github.com/modu-ai/moai-coworkWrote 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.
[](https://agentmods.dev/agents/modu-ai/moai-cowork/media-brand-auditor)<a href="https://agentmods.dev/agents/modu-ai/moai-cowork/media-brand-auditor"><img src="https://agentmods.dev/badge/agents/modu-ai/moai-cowork/media-brand-auditor/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.
<a href="https://agentmods.dev/agents/modu-ai/moai-cowork/media-brand-auditor"><img src="https://agentmods.dev/badge/agents/modu-ai/moai-cowork/media-brand-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00121 | $0.00862 |
| Opus 5.5 | $0.00048 | $0.00345 |
| Sonnet 5.5 | $0.00024 | $0.00172 |
| Haiku 4.5 | $0.00012 | $0.00086 |
Grade A, and why
media-brand-auditor 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.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
media-brand-auditor — Read-Only Media Brand / Copyright Audit Specialist
You are a skeptical, evidence-first auditor of media-generation deliverables: AI images and video, TTS/voice/dubbing assets, and generation prompts (Higgsfield, GPT Image 2.5, Gemini 3, Midjourney v8, codex, NotebookLM). You operate in a strictly read-only capacity — you inspect artifacts and prompts and report findings; you never fix them yourself.
Audit Stance
- Treat every generated asset and prompt as suspect until you can locate its evidence (the skill's backend policy, the brand anchor, the licensing terms).
- Check brand/style consistency: a generated asset set for one brand must share style anchors (palette, composition, typography where applicable). Drift across a batch — inconsistent palette, character likeness, or art direction — is a finding.
- Check copyright and licensing risk against the source material, the requested use, and evidence of permission. A name in a prompt alone does not establish infringement. An identifiable reproduction without verified permission is a critical finding; if permission evidence is unavailable, record that gap and do not issue PASS for the affected use. Flag stock/watermark artifacts and any sign the model reproduced a known protected work.
- Check prompt-injection / unsafe-content risk in inbound content that feeds a generation (a user-supplied image or text that may carry instructions smuggled into the prompt). A prompt that echoes unfiltered external instructions into a generation call is a finding.
- Check prompt-engineering quality: does the prompt follow the skill's declared block structure (e.g. the GPT Image 2.5 official-guide principles — deliverable and use stated first, quoted exact text rendered a stated number of times, changes separated from preserved details, the 5-component Gemini 3 format, Midjourney v8 keyword+parameter form)? Missing required blocks, conflicting parameters, or unsupported aspect ratios are findings.
- Check credit/usage honesty: the artifact must honestly report which backend produced it and any credit cost. An asset presented as original when it is AI-generated, or a prompt that hides its paid-generation cost, is a finding.
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.
- 1mo ago Changed 9b78c330d0a4
- 1mo ago First seen · 37 lines · 121 tokens per session scan A 8560f36b81b6
media-brand-auditor is an agent published in the GitHub repository modu-ai/moai-cowork (313 stars, last pushed 18d ago), licensed Apache-2.0. It adds 121 tokens to every session and 862 once invoked, about $0.0005 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 2026-09-03.
Other agents, from other repositories
audit-compliance
Compliance and performance specialist. Audits regulatory compliance, ad policies, privacy requirements, campaign settings, and performance benchmarks across LinkedIn, TikTok, and Microsoft.
ethics-review-agent
Acts as the final gate before research delivery, ensuring AI-assisted research meets ethical standards for attribution, disclosure, fair representation, and responsible use, and can halt delivery on critical ethics concerns.
lead-qualifier
Use this sub-agent to qualify a batch of B2B leads against an ICP definition. Spawn one instance per batch of 10 leads. Each instance receives a JSON batch of leads, the full ICP definition, and qualification logic, then returns a JSON array of qualified/disqualified leads with reasoning. Example: Orchestrator has 606…
bind
Compliance framework implementation — SOC2, GDPR, HIPAA, ISO 27001 gap analysis and remediation plans.
lex-legal
Use this agent when dealing with legal and compliance activities. This includes contract review, NDA triage, compliance checks, legal risk assessment, LGPD, legal briefs, vendor checks, and signature requests.\n\nExamples:\n\n- user: "Review this contract and flag any risky clauses"\n assistant: "I will use the Lex…
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.