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 agentmods add skills/bemoshiur/omnirank/linkedin-postnpx skills add bemoshiur/OmniRank --skill linkedin-postgit clone --depth 1 https://github.com/bemoshiur/OmniRankWhat 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 | $0.00063 | $0.01013 |
| Opus 5 | $0.00032 | $0.00507 |
| Sonnet 5 | $0.00013 | $0.00203 |
| Haiku 4.5 | $0.00006 | $0.00101 |
Grade A, and why
linkedin-post 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 2d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Daily LinkedIn post
Draft one post in Moshiur's voice. He is Director, Business & Operations at TICON System Limited — a practitioner writing about what he actually hit today, not a marketer.
The one rule
A post needs a real thing that happened. If he hasn't given you one, ask for it before drafting. Do not manufacture a scenario, and do not fall back on general SEO advice — that is the failure mode. Generic "5 tips for better SEO" content reads as filler, performs badly, and costs credibility that specific writing earns.
Acceptable raw material: a prospect conversation, an objection he couldn't answer, a measurement that surprised him, something he was wrong about, a tool result, a decision he had to make with incomplete information.
Structure that works
- A hook that is a fact, not a claim. Ideally a number or a short admission. "I ran our own website through a tool I built. 57 pages. Not one had an answer an AI could quote." Never open with "In today's digital landscape".
- The problem, stated concretely — what he actually ran into, in two or three short paragraphs. Short lines. LinkedIn truncates around 200 characters, so the first two lines carry the whole post.
- Evidence. Real numbers, indented as a small block. See below for pulling them.
- What he did or concluded — including the uncomfortable part if there is one.
- One specific question. Not "thoughts?" — something a reader can answer in a sentence from their own experience.
- Link only if it earns its place. github.com/bemoshiur/OmniRank when relevant.
- 4–7 hashtags, lowercase-natural, no keyword stuffing.
Target 1,300–2,000 characters. Longer gets collapsed behind "see more".
Getting real numbers
Never invent a statistic. When a post would benefit from data, measure it:
cd "<repo>" && .venv/bin/python -m omnirank.cli audit https://<site> --out /tmp/post.json
Then read /tmp/post.json for exact per-layer scores and finding counts. Quote what the
tool actually printed. If a number can't be measured, cut the claim rather than soften it.
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.
- 2d ago First seen · 85 lines · 63 tokens per session scan A 5434e1e1532d
linkedin-post is a skill published in the GitHub repository bemoshiur/OmniRank (6 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 1,013 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
ansvisor-aeo-coach-standalone
Standalone (no-MCP) version of the Ansvisor AEO Coach. Use this only when the user's Claude client cannot connect to the Ansvisor MCP server (e.g. claude.ai web without a Connector configured). Fetches live data from the Ansvisor REST API directly with the user's API key via code execution. For clients that support…
ansvisor-aeo-coach
Acts as an Answer Engine Optimization (AEO) analyst for users running Ansvisor. Activates when the user asks how their brand is doing across AI search engines (ChatGPT, Gemini, Perplexity, Claude, Copilot, AI Overview, AI Mode), why visibility changed, or how they compare to competitors. Uses the Ansvisor MCP server…
rank-audit
Full SEO/GEO/AEO/Citability/Content/Performance/Vertical/Security audit with auto-fix. Scans, reports, fixes, and verifies.
rank-aeo
Answer engine optimization. Optimize for featured snippets, voice search, People Also Ask.
rank-geo
AI search optimization audit. Optimize content for ChatGPT, Perplexity, Google AI Overviews.
rank-fix
Auto-fix all SEO/GEO/AEO findings in one command. Scan, fix, verify.