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 anhnguyen0905/codex-mcp --skill influencer-strategygit clone --depth 1 https://github.com/anhnguyen0905/codex-mcpWrote 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/anhnguyen0905/codex-mcp/influencer-strategy)<a href="https://agentmods.dev/skills/anhnguyen0905/codex-mcp/influencer-strategy"><img src="https://agentmods.dev/badge/skills/anhnguyen0905/codex-mcp/influencer-strategy/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/anhnguyen0905/codex-mcp/influencer-strategy"><img src="https://agentmods.dev/badge/skills/anhnguyen0905/codex-mcp/influencer-strategy.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 | $0.00067 | $0.01550 |
| Opus 5 | $0.00034 | $0.00775 |
| Sonnet 5 | $0.00013 | $0.00310 |
| Haiku 4.5 | $0.00007 | $0.00155 |
Grade A, and why
influencer-strategy 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 11d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Influencer Strategy (creator selection, contracting, measurement)
Tiers are roles, not sizes
nano (~1k-10k) cheapest per post, high comment intimacy; local/niche proof and cheap volume
testing of angles. Most ops overhead per unit of reach.
micro (~10k-100k) workhorse: real topical authority, negotiable, enough volume to A/B creators.
mid (~100k-500k) meaningful single-post reach with retained community trust; anchors a wave.
macro/celebrity reach, credibility transfer, PR value. Priced like media, not word of mouth;
low CPE, weaker comment-level trust, key-person risk.
Bands differ by platform and market — re-cut them from your own data; the tier's job is the point. Portfolios beat single tiers: macro/mid for reach and legitimacy, micro/nano for coverage, repeatability and cheap creative learning.
Select on fit, not follower count
Rank on audience overlap with the target (geo, language, age, interest — from the creator's own audience export, not a guess) · topical authenticity (do they use the category unpaid?) · comment substance and sentiment · brand-deal density, since back-to-back sponsorships convert poorly · brand-safety history. Follower count only sets the price band; an audience 70% outside your market is expensive at any CPM.
CPM / CPE as planning inputs
CPM = fee / (expected impressions / 1000)
CPE = fee / expected engagements ← define engagement: likes+comments+shares+saves
CPV = fee / expected views ← state the platform's view definition; they differ
expected impressions ≈ MEDIAN views of the creator's last N comparable organic posts
Use recent medians, never peaks and never follower count. Sanity-check the resulting CPM against your paid CPM for the same placement. These are estimates: pay on deliverables and terms, and negotiate a make-good clause if delivered reach lands far below the stated median.
Brief, creative freedom, and contract terms
Give only the non-negotiables — single message, mandatory and prohibited claims, hook window, CTA and link/code, delivery spec. The creator owns format, voice, script and edit; that native voice is what you are buying, and word-for-word scripting reads as an ad and loses the trust you paid for. Approve a concept or outline instead of line-editing. The contract must then fix:
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.
- 11d ago First seen · 117 lines · 67 tokens per session scan A 09411f1fc23e
influencer-strategy is a skill published in the GitHub repository anhnguyen0905/codex-mcp (3 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 1,550 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…