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 outreach-message-composergit 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/outreach-message-composer)<a href="https://agentmods.dev/skills/crevideo/crevideo-reach/outreach-message-composer"><img src="https://agentmods.dev/badge/skills/crevideo/crevideo-reach/outreach-message-composer/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/outreach-message-composer"><img src="https://agentmods.dev/badge/skills/crevideo/crevideo-reach/outreach-message-composer.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 | $0.00110 | $0.01336 |
| Opus 5 | $0.00055 | $0.00668 |
| Sonnet 5 | $0.00022 | $0.00267 |
| Haiku 4.5 | $0.00011 | $0.00134 |
Grade A, and why
outreach-message-composer 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 3d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outreach Message Composer · 多渠道触达文案
Role: produce ready-to-use outreach copy (DM / Target Collaboration / email). Only writes copy + channel/param suggestions; fit, tier, and commission compliance go to creator-fit-scoring / creator-tier-resolver / offer-policy-checker.
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 (e.g.
send_email,create_dm_automation) stay identical in both languages. If unsure which market, ask once before producing output.
When to use / not use
- Use: write a cold DM, a Target Collaboration invite, an email, a follow-up.
- Don't use: only scoring / tier judgment / data lookup.
Inputs (ask if missing)
- Target creator tier + channel (DM / TC / email / combo).
- Product (name/category/price; must be ACTIVATE).
- Scenario: cold / follow-up / negotiation reply.
- Optional: proposed commission (if the copy must mention it).
Steps (in order)
- Read brand voice (project
Knowledge/brand-voice; default "warm but professional, no emoji" if absent) and the current hero product + angle (sku-catalog-snapshot, if present); before contacting, compare againstKnowledge/do-not-contactand drop matches (before ranking). - Pick the channel (per the Cheat Sheet's outreach waterfall): warm / existing / customer-type → prefer Target Collaboration; cold T2/T3 → DM first, asking permission for "a quick chat"; cold VIP/T1, or DM with no reply → email (consider enrichment only for high value).
- Set tone & length by tier: higher tier = more personalized, more creative latitude; lower tier = concise, one clear value point. Do not drop a commission number early in a cold DM (hold it until they reply — acceptance is higher).
- Draft 3 versions (1 primary + 2 alternates, differentiated tone); email must carry the value prop + compliance requirements (#ad / branded-content).
- Force brand-safety-compliance: any version that hits a block is rewritten, not output, with the violated rule noted.
- If commission is mentioned → run offer-policy-checker; if over the cap, flag a red warning at the top of the copy.
- Attach anti-spam params (per the Cheat Sheet): when building a DM/combo automation, include stop_on_reply + skip_creators_with_prior_replies + skip_messaged_within_days; don't re-contact within the cross-channel cooldown.
- Naming suggestion: if the copy lands in an automation name, give a short English/alphanumeric name (per current naming rules); if non-ASCII is present, give a deterministic fallback (pinyin / short slug, then truncate) — never let Chinese end up in a name.
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.
- 7d ago Changed · +2 lines 53b69eceb6ea
- 12d ago First seen · 72 lines · 110 tokens per session scan A 86d4a9b20d9e
outreach-message-composer is a skill published in the GitHub repository crevideo/crevideo-reach (7 stars, last pushed 3d ago), licensed MIT. It adds 110 tokens to every session and 1,336 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.