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 offer-policy-checkergit 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/offer-policy-checker)<a href="https://agentmods.dev/skills/crevideo/crevideo-reach/offer-policy-checker"><img src="https://agentmods.dev/badge/skills/crevideo/crevideo-reach/offer-policy-checker/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/offer-policy-checker"><img src="https://agentmods.dev/badge/skills/crevideo/crevideo-reach/offer-policy-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 47 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00120 | $0.01190 |
| Opus 5 | $0.00060 | $0.00595 |
| Sonnet 5 | $0.00024 | $0.00238 |
| Haiku 4.5 | $0.00012 | $0.00119 |
Grade A, and why
offer-policy-checker 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Offer Policy Checker · 报价与合规校验
Role: a pass/warn/block checker, not a policy database. It judges whether an offer/outbound crosses a line and gives fixes. Does not set tier (creator-tier-resolver), does not write copy.
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: validate a proposed commission, a creator counter-offer, a batch flat commission; the pre-send "does this fit policy?" check.
- Don't use: tier not yet decided (run creator-tier-resolver first).
Inputs
- Proposed commission/offer + the creator's tier (Open/T1/T2/T3).
- Scenario: first offer / counter-offer / batch.
- Optional: product (to check ACTIVATE), intended channel + anti-spam params.
Steps (in order)
- Tier commission-cap check (numbers from the Cheat Sheet): within range → pass; over default but under cap → warn (needs explicit human confirm); over cap → reject (must lower the price or re-judge the tier).
- All-in take-rate gate: estimate all-in take-rate using the Cheat Sheet's exact formula — do not reconstruct it from memory. (Shape per the Doctrine: platform commission% + effective creator commission [listed ÷ (1 − return rate)] + per-order fulfillment ÷ AOV; landed cost/duty, samples, sales tax, and return-handling costs are NOT in it.) Write N/A for any missing item, do not fabricate. Over the Cheat Sheet's all-in take-rate ceiling → mark "needs intervention" (suggest lower commission / raise AOV·bundle / different product / lower-cost channel); never pass on "high GMV".
- Eligibility check: product must be ACTIVATE; in batch, every creator in the pool must pass (else split the pool).
- Anti-spam param check (outbound): confirm stop_on_reply / skip_creators_with_prior_replies / skip_messaged_within_days per the Cheat Sheet, plus the cross-channel cooldown. Flag any missing.
- Output the verdict + fixes (do not decide acceptance of a counter-offer for the user).
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 · 65 lines · 120 tokens per session scan A 71bb8d4a6699
offer-policy-checker is a skill published in the GitHub repository crevideo/crevideo-reach (7 stars, last pushed yesterday), licensed MIT. It adds 120 tokens to every session and 1,190 once invoked, about $0.0006 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
markifact-overview
Reference — what Markifact is, what the MCP server exposes, and the discover→inspect→run pattern. Always loaded into the performance-marketer agent.
safe-write-operations
Reference — rules for safely executing write/destructive operations against ad accounts. Always loaded into the performance-marketer agent.
dev
Software development planning. Actions - spec (brainstorm product and tech specification), plan (turn the specs into a delivery plan - work packages, dependencies, effort in hours, milestones), feature (decompose specs into numbered feature documents), revise (update specs with new requirements), overview. Planning…
project
Create and manage the project structure - projects, sub-projects, and work packages (WPs). Actions - new project, new subproject, new WP, overview. Hierarchy depth (2 or 3 levels) is fixed at creation. All work happens in WPs; projects and sub-projects are pure structure.
ws
Create and run workstations - permanent areas for routine, repeated work (independent of projects). Actions - new WS, new subWS, new area, new routine, run, from project, list, overview. Hierarchy depth (2 or 3 levels) is fixed at creation.
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.