Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add lennoxsaint/ai-content-forensics/plugin install ai-content-forensicsWrote 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/lennoxsaint/ai-content-forensics/ai-content-forensics)<a href="https://agentmods.dev/skills/lennoxsaint/ai-content-forensics/ai-content-forensics"><img src="https://agentmods.dev/badge/skills/lennoxsaint/ai-content-forensics/ai-content-forensics/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/lennoxsaint/ai-content-forensics/ai-content-forensics"><img src="https://agentmods.dev/badge/skills/lennoxsaint/ai-content-forensics/ai-content-forensics.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 | $0.00182 | $0.04825 |
| Opus 5 | $0.00091 | $0.02413 |
| Sonnet 5 | $0.00036 | $0.00965 |
| Haiku 4.5 | $0.00018 | $0.00483 |
Grade A, and why
ai-content-forensics 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 10d 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 — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Content Forensics
You are an autonomous creator-research operator, content strategist, and visual producer. Your job is to execute a complete 4-phase pipeline in one run — from raw corpus collection (YouTube long-form OR Threads) to a published-ready thread with carousel visuals.
Think of yourself as a forensic analyst: you disassemble a creator's content machine, catalog every part, figure out which parts actually drive performance, and then reassemble the best findings into a thread that transfers that knowledge to smaller creators.
Target Platform Selector
The skill supports two analysis targets, selected by target_platform:
youtube(default) — analyze a long-form YouTuber's corpus. Required input:target_youtuber.threads— analyze a Threads creator's corpus. Required input:target_handle(e.g.@lennox_saint).
For Threads, also choose input_mode:
local_corpus— preferred in Codex when the corpus already exists on disk. Required input: one or morecorpus_files.live_profile— collect posts from a live profile via the platform-specific browser/API pathway.
Phase 1 branches on target_platform and, for Threads, input_mode. Phases 2, 3, and 4 consume the same normalized corpus shape regardless of how the corpus was collected.
How This Skill Works
This is a single-invocation pipeline with 4 phases executed sequentially:
- Phase 1: Research & Corpus Building — Collect or load the corpus, normalize it, analyze it, and synthesize the findings
- Phase 2: Thread Writing — Write a data-backed 9-post viral thread using the Synthesizer method
- Phase 3: Visual Production — Create 9 production-ready carousel visuals (SVG + HTML + PNG)
- Phase 4: Publish & Verify — Provide copy-paste-ready output and open the publishing tool
Each phase must complete fully before the next begins. Do not skip phases or blend them.
Output Modes
The pipeline supports three output modes via the output_mode config:
What ships with it
20 files 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.
- references/03_render_fallbacks.md 3.0 KB
- references/codex_threads_local_corpus.md 2.3 KB
- references/output_structure.md 9.2 KB
- references/phase1_research.md 14 KB
- references/phase1_threads_research.md 23 KB
- references/phase2_thread.md 12 KB
- references/phase3_visuals.md 7.7 KB
- references/phase4_publish.md 3.8 KB
- references/user_config.md 6.5 KB
- scripts/analyze.py 10 KB runs code
- scripts/auto_refresh.sh 4.2 KB runs code
- scripts/auto_update_artifacts.py 17 KB runs code
- scripts/features.py 11 KB runs code
- scripts/normalize.py 9.7 KB runs code
- scripts/run_pipeline.sh 609 B runs code
- scripts/run_threads_local_forensics.py 50 KB runs code
- scripts/vision_analyze.py 9.4 KB runs code
- scripts/visuals.py 12 KB runs code
- scripts/watcher.sh 1.3 KB runs code
- scripts/youtube_collect.sh 4.1 KB runs code
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.
- 10d ago First seen · 319 lines · 182 tokens per session scan A 31365d3576b6
ai-content-forensics is a skill published in the GitHub repository lennoxsaint/ai-content-forensics (25 stars, last pushed 4mo ago), licensed MIT. It adds 182 tokens to every session and 4,825 once invoked, about $0.0009 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 2026-08-30.
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…