Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/frankxai/affiliate-agent-skillsnpx agentmods add skills/frankxai/affiliate-agent-skills/affiliate-auditWrote 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/frankxai/affiliate-agent-skills/affiliate-audit)<a href="https://agentmods.dev/skills/frankxai/affiliate-agent-skills/affiliate-audit"><img src="https://agentmods.dev/badge/skills/frankxai/affiliate-agent-skills/affiliate-audit/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/frankxai/affiliate-agent-skills/affiliate-audit"><img src="https://agentmods.dev/badge/skills/frankxai/affiliate-agent-skills/affiliate-audit.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 | $0.00045 | $0.00422 |
| Opus 5 | $0.00023 | $0.00211 |
| Sonnet 5 | $0.00009 | $0.00084 |
| Haiku 4.5 | $0.00005 | $0.00042 |
Grade A, and why
affiliate-audit 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- affiliate-audit — 100% identical, 0 lines differ
What it actually says
affiliate-audit
Connect the affiliate catalog to a site's content and surface monetization gaps.
Run
node scripts/affiliate-audit.mjs --content=<site>/content --traffic=<traffic.json> --write
Reads data/programs.json + the content dir + optional traffic → ranks (1) programs to join first, (2) posts to add links to. Writes AUDIT.md.
Strategy rules (apply when recommending or placing links)
- Frontier names rank, adjacents pay. OpenAI/Anthropic/Google/Runway/Luma/Midjourney/Ideogram/FLUX have NO affiliate programs. Capture their traffic; monetize via the recurring payers the post recommends.
- Higgsfield first (you use it — authentic, 15% recurring, highest ticket), then the recurring spine: Systeme.io (60% lifetime) / CapCut (35%) / ElevenLabs (22%/12mo) / Copy.ai (45% yr1).
- Recurring > one-time. Passive income compounds on subscriptions, not flat bounties.
- One disclosure per page. FTC + trust. Use the catalog's
disclosurestring. - Never link a tool you can't vouch for, and never let a link override the honest pick — say what's actually best, then point to the payer you'd actually buy.
- Ignore dead-ends/closed (
statusin catalog): frontier LLMs, Leonardo (closed Apr 2026), Notion (closed to new).
The loop
Audit → join top program → set ourLink in data/programs.json → add link + disclosure to the named posts → re-audit (gap clears).
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 · 30 lines · 45 tokens per session scan A b75f5b89af3c
affiliate-audit is a skill published in the GitHub repository frankxai/affiliate-agent-skills (2 stars, last pushed 4d ago), licensed MIT. It adds 45 tokens to every session and 422 once invoked, about $0.0002 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
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
omh-rust
This is a Hermes-native rust workflow skill.
omh-code-review
This is a Hermes-native code-review workflow skill.
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.
manage-schemas
Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…