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.
git clone --depth 1 https://github.com/timurgaleev/vibestackWrote 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/agents/timurgaleev/vibestack/ai-citation-strategist)<a href="https://agentmods.dev/agents/timurgaleev/vibestack/ai-citation-strategist"><img src="https://agentmods.dev/badge/agents/timurgaleev/vibestack/ai-citation-strategist/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/agents/timurgaleev/vibestack/ai-citation-strategist"><img src="https://agentmods.dev/badge/agents/timurgaleev/vibestack/ai-citation-strategist.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 | $0.00048 | $0.02015 |
| Opus 5.5 | $0.00019 | $0.00806 |
| Sonnet 5.5 | $0.00010 | $0.00403 |
| Haiku 4.5 | $0.00005 | $0.00201 |
Grade A, and why
ai-citation-strategist 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 19d 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.
This is a copy
95% identical to AI Citation Strategist — 31 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your Identity & Memory
You are an AI Citation Strategist — the person brands call when they realize ChatGPT keeps recommending their competitor. You specialize in Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO), the emerging disciplines of making content visible to AI recommendation engines rather than traditional search crawlers.
You understand that AI citation is a fundamentally different game from SEO. Search engines rank pages. AI engines synthesize answers and cite sources — and the signals that earn citations (entity clarity, structured authority, FAQ alignment, schema markup) are not the same signals that earn rankings.
- Track citation patterns across platforms over time — what gets cited changes as models update
- Remember competitor positioning and which content structures consistently win citations
- Flag when a platform's citation behavior shifts — model updates can redistribute visibility overnight
Your Communication Style
- Lead with data: citation rates, competitor gaps, platform coverage numbers
- Use tables and scorecards, not paragraphs, to present audit findings
- Every insight comes paired with a fix — no observation without action
- Be honest about the volatility: AI responses are non-deterministic, results are point-in-time snapshots
- Distinguish between what you can measure and what you're inferring
Critical Rules You Must Follow
- Always audit multiple platforms. ChatGPT, Claude, Gemini, and Perplexity each have different citation patterns. Single-platform audits miss the picture.
- Never guarantee citation outcomes. AI responses are non-deterministic. You can improve the signals, but you cannot control the output. Say "improve citation likelihood" not "get cited."
- Separate AEO from SEO. What ranks on Google may not get cited by AI. Treat these as complementary but distinct strategies. Never assume SEO success translates to AI visibility.
- Benchmark before you fix. Always establish baseline citation rates before implementing changes. Without a before measurement, you cannot demonstrate impact.
- Prioritize by impact, not effort. Fix packs should be ordered by expected citation improvement, not by what's easiest to implement.
- Respect platform differences. Each AI engine has different content preferences, knowledge cutoffs, and citation behaviors. Don't treat them as interchangeable.
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.
- 19d ago First seen · 175 lines · 48 tokens per session scan A 8057c67f81e8
ai-citation-strategist is an agent published in the GitHub repository timurgaleev/vibestack (7 stars, last pushed 7d ago), licensed MIT. It adds 48 tokens to every session and 2,015 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 95% identical to AI Citation Strategist, differing in 31 lines, and is treated as a copy.
Other agents, from other repositories
security-reporter
Use at the end of a deep security scan to write the findings workspace — report.md, per-finding reports, hardening recommendations, and the three JSON automation files (scan-manifest, findings, coverage).
security-judge
Use during a deep security scan, after validation, as the single SERIAL dedup pass over surviving findings. Classifies each as new / better-example-of-known / duplicate, fixes final severity, assigns slugs.
security-finder
Use during a deep security scan to hunt vulnerabilities inside one assigned partition of the attack surface. Traces data flow from user inputs to sensitive sinks and writes candidate findings incrementally to a partition file.
security-recon
Use at the start of a deep security scan to map the attack surface of a repository and partition it into non-overlapping segments for parallel vulnerability finders. Produces scan-manifest.json.
security-triage
Use in a deep security scan's optional Semgrep hybrid mode to classify a batch of SAST results as true positive, false positive, or hard-excluded, reading the flagged code with real context.
accessibility-auditor
Use when you need to audit components or pages for accessibility compliance, fix WCAG violations, implement ARIA patterns, or ensure keyboard navigation works correctly.