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.
npx skills add crevideo/crevideo-reach --skill brand-safety-compliancegit clone --depth 1 https://github.com/crevideo/crevideo-reachWrote 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/skills/crevideo/crevideo-reach/brand-safety-compliance)<a href="https://agentmods.dev/skills/crevideo/crevideo-reach/brand-safety-compliance"><img src="https://agentmods.dev/badge/skills/crevideo/crevideo-reach/brand-safety-compliance/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/skills/crevideo/crevideo-reach/brand-safety-compliance"><img src="https://agentmods.dev/badge/skills/crevideo/crevideo-reach/brand-safety-compliance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00139 | $0.01102 |
| Opus 5 | $0.00069 | $0.00551 |
| Sonnet 5 | $0.00028 | $0.00220 |
| Haiku 4.5 | $0.00014 | $0.00110 |
Grade A, and why
brand-safety-compliance 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 12d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brand Safety & Compliance · 品牌安全合规
Role: run a compliance red-line scan on text and return block/warn + fix suggestions. This is a mandatory pre-flight for any outbound copy, and is also used to re-scan published content.
Output language
Write every output in the merchant's working language, using that market's native seller terminology:
- US Local sellers → English: tier / all-in take-rate / outreach waterfall / Target Collaboration / DM / sample …
- China POP sellers → 中文: 分级 / 真实抽成 / 触达阶梯 / 定向邀约 / 私信 / 寄样 … Tool names stay identical in both languages. If unsure which market, ask once before producing output.
When to use / not use
- Use: scan copy before sending, re-scan today's confirmed content, vet a creator-submitted script/caption.
- Don't use: pure data analysis with no text.
Inputs
- The text to scan.
- Scenario:
outreach(our outbound, strictest) /creator_submitted(creator content, still strict if regulated) /internal_draft(internal draft, advisory only).
Steps (in order)
- Read brand/category-specific banned words (project
Knowledge/brand-compliance-additions, if present); merge with the MUST-NOT red lines from the Key-Rules Cheat Sheet. - Scan all 6 classes, reporting each independently:
- C1 Medical/efficacy (cure / heal / treat / prevent…, medical verbs)
- C2 Exaggeration/absolute (100% / guaranteed / instant / permanent / miracle…)
- C3 Beauty-permanence (permanently whitens / removes wrinkles forever…, unless backed by real clinical evidence)
- C4 Financial/income promise (guaranteed income / earn $X…)
- C5 Fake scarcity (only N left / a "limited" drop with no real inventory)
- C6 Fake rapport (as we discussed / per our agreement, with no real prior interaction)
- For each hit: class + matched phrase + context + severity (block/warn) + fix suggestion.
- Overall verdict: any block → ❌ must rewrite; warn only → ⚠️ may proceed but advise a fix; none → ✅.
- Reasonable carve-out: if the text is meta-discussion teaching creators to avoid these phrases, mark it false-positive and pass.
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.
- 12d ago First seen · 73 lines · 139 tokens per session scan A 6731f9b002e7
brand-safety-compliance is a skill published in the GitHub repository crevideo/crevideo-reach (7 stars, last pushed yesterday), licensed MIT. It adds 139 tokens to every session and 1,102 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
cease-desist
Draft a cease-and-desist letter (send mode) or triage one you received (receive mode). Use when asserting your rights against an infringer with a demand letter calibrated to your enforcement posture, or when an incoming C&D needs triage into a structured options memo with a recommendation.
claim-chart
Build or review an element chart — a patent claim chart (infringement, invalidity, or review) or a civil element chart for any cause of action or defence — with every cell pin-cited and gap detection as the priority output. Use when the user asks for a claim chart, element chart, proof chart, infringement or…
internal-investigation
Reference: shared framework for managing internal investigations from intake through final memo — privileged investigation log, document processing with needle-finding, source coverage tracking, Q&A against the log, memo drafting, and audience summaries. Loaded by /investigation-open, /investigation-add…
infringement-triage
Infringement triage across trade mark, copyright, patent, and trade secret — a flag list with the factors cutting each way, not a finding. Use when assessing whether someone is infringing your IP or whether you might be infringing theirs, when a knockoff or copycat surfaces, or when deciding whether a matter is worth…
aia-generation
Run an AI impact assessment — structured intake, risk analysis, UK regulatory classification (UK GDPR / DPA 2018, ICO AI guidance, sector-specific UK regulation), EU AI Act analysis where EU nexus exists, policy consistency diff, and recommendation with conditions. Uses the house-style structure learned from the seed…
vendor-agreement-review
Reference: review of an inbound vendor agreement against the team playbook in /.claude/plugins/config/uk-legal-plugins/commercial-legal-uk/CLAUDE.md under English contract law (with notes for Scots law / NI where the governing law requires). Flags deviations, assesses risk, generates specific redline language, and…