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 san-npm/skills-ws --skill influencer-marketinggit clone --depth 1 https://github.com/san-npm/skills-wsWrote 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/san-npm/skills-ws/influencer-marketing)<a href="https://agentmods.dev/skills/san-npm/skills-ws/influencer-marketing"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/influencer-marketing/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/san-npm/skills-ws/influencer-marketing"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/influencer-marketing.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 | $0.00077 | $0.06035 |
| Opus 5.5 | $0.00031 | $0.02414 |
| Sonnet 5.5 | $0.00015 | $0.01207 |
| Haiku 4.5 | $0.00008 | $0.00604 |
Grade A, and why
influencer-marketing 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 2mo 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 — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Influencer Marketing
Influencer Tiers
Engagement bands below are typical ranges, not guarantees — they vary by platform, niche, and post format (Reels/Shorts usually out-engage static posts). Do not treat these as cost data; price with the budgeting model in the next section, not a flat per-tier rate.
| Tier | Followers | Typical ER (IG/TikTok) | Best For |
|---|---|---|---|
| Nano | 1K-10K | 3-8% | Niche communities, authenticity, gifting/seeding |
| Micro | 10K-100K | 1.5-5% | Targeted reach, high trust, volume programs |
| Mid | 100K-500K | 1-3% | Scale + engagement balance |
| Macro | 500K-1M | 0.8-2% | Brand awareness campaigns |
| Mega/Celebrity | 1M+ | 0.5-1.5% | Mass reach, cultural moments |
Why smaller tiers often win on efficiency: engagement rate tends to decline as follower count rises (audience-fatigue + broader, less-aligned audiences), so micro/nano creators frequently produce a lower cost-per-engagement and more relatable content. Treat this as a hypothesis to validate per campaign, not a fixed benchmark — compute actual CPE/CPV per creator (formulas below) and let your own data decide the mix. Avoid quoting a universal "X% better" figure to stakeholders; it rarely survives contact with real category/geo data.
2026 Budgeting Model (build the rate, don't look it up)
Flat per-tier rate cards are stale on arrival and ignore the variables that actually drive cost. Build each quote from a base fee plus multipliers:
Quote = BaseFee(format, platform, tier)
× UsageRightsMultiplier
× ExclusivityMultiplier
× WhitelistingMultiplier
× ProductionMultiplier
+ PerformanceBonus(optional, paid on verified KPI)
| Lever | Direction & rough effect | Notes |
|---|---|---|
| Base fee | Set by deliverable, platform, tier | Anchor to the creator's own quote + comparable creators; longer-form (YT integration) costs more than a Story frame |
| Usage / paid media rights | +20-100%+ over organic-only | Biggest hidden cost. Price by where (organic repost vs. paid ads vs. OOH/CTV), channels, and duration. "Perpetual / all media" can multiply the base several times — buy only the term you need (e.g., 3-6 months) |
| Whitelisting / partnership ads (Meta Partnership Ads, TikTok Spark Ads) | +25-50% on top of usage | You run ads from the creator's handle; add ad spend separately (this is media budget, not talent fee) |
| Exclusivity | +10-50% per category, scaled by length | A 6-month category lockout costs far more than 30 days; never ask for exclusivity you won't use |
| Production complexity | +0-100%+ | Studio shoots, multi-location, talent/props, scripted edits, raw-file delivery, agency/manager fees |
| Category / geography | Varies widely | Finance, beauty, B2B/dev, and large-market creators (US/UK/DACH) command premiums; emerging markets lower |
| Performance bonus | Add-on, paid on verified results | Tie to attributable outcomes (code redemptions, qualified leads), not vanity reach |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 354 lines · 77 tokens per session scan A c7d28a89cb23
influencer-marketing is a skill published in the GitHub repository san-npm/skills-ws (4 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 6,035 once invoked, about $0.0003 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.
influencer-marketing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| influencer-marketingsan-npm/skills-ws | Skill | 4 | 1mo ago | MIT | A | 77 | Codex |
| fto-triageanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 81 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| specification-writingwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 49 | Claude Code |
| terms-of-servicegenspark-ai/genoffice | Skill | 12k | 2d ago | Apache-2.0 | A | 32 | Claude Code, Codex |
| x-scorecardx-cmd/x-cmd | Skill | 4.7k | 7d ago | Apache-2.0 | A | 57 | Claude Code, Codex |
| gesellschaftsrechtliche-satzungen-agbKlotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | yesterday | Apache-2.0 | A | 69 | Claude Code |