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 alivirgo/Major-AI-Skills --skill ai-citation-verificationgit clone --depth 1 https://github.com/alivirgo/Major-AI-SkillsWrote 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/alivirgo/major-ai-skills/ai-citation-verification)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/ai-citation-verification"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/ai-citation-verification/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/alivirgo/major-ai-skills/ai-citation-verification"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/ai-citation-verification.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 | $0.00053 | $0.04001 |
| Opus 5.5 | $0.00021 | $0.01600 |
| Sonnet 5.5 | $0.00011 | $0.00800 |
| Haiku 4.5 | $0.00005 | $0.00400 |
Grade A, and why
ai-citation-verification 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 21d 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 — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Citation Verification AI Skill Guide (Claude)
Overview & Engine Architecture
A citation is not a vibe and not a footnote aesthetic. Groundedness (answer consistent with some retrieved text) ≠ citation correctness (the cited span supports the claim) ≠ citation faithfulness (the model actually relied on that span rather than post-rationalizing from parametric memory). Shipping “looks cited” without these checks is the hallucinated-citations anti-pattern.
Claude operates as a Principal Evidence Auditor, specializing in three-rubric citation eval, retrieval-registry binding, claim→span entailment, quote/offset checks, scope/qualifier fidelity, and safe handling of inaccessible sources.
┌─────────────────────────────────────────────────────────────┐
│ Citation Verification Stack │
│ │
│ Bind (generation-time) │
│ ├── Retrieval registry: chunk_id → text, loc, hash, ACL │
│ ├── Model emits markers / structured claims+ids only │
│ └── Reject ids absent from this turn's registry │
│ │
│ Rubric 1 — Structural │
│ └── Schema/markers valid (@llm-json-contract-check) │
│ │
│ Rubric 2 — Resolvability │
│ ├── chunk_id ∈ registry | URL/DOI live | PDF page exists │
│ └── Cited id was retrieved this turn (not corpus-wide) │
│ │
│ Rubric 3 — Semantic (per claim × cited span) │
│ ├── supported | partial | contradicted | neutral/irrelevant│
│ ├── quote_verbatim? offsets? qualifier match? │
│ └── correctness ≠ faithfulness (post-rationalization risk) │
│ │
│ Deliverable │
│ └── claim table + corrected wording + unresolved gaps │
└─────────────────────────────────────────────────────────────┘
What ships with it
2 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.
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.
- 21d ago Changed · +370 lines · +26 tokens per session 04f4d1d3c760
- 1mo ago First seen · 35 lines · 27 tokens per session scan A 1f10b26b5a9a
ai-citation-verification is a skill published in the GitHub repository alivirgo/Major-AI-Skills (2 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 4,001 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-12.
Other skills, from other repositories
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
ai-pipeline-orchestration
Orchestrate AI/ML pipelines for data ingestion, model training, batch inference, and RAG indexing using Prefect, Airflow, or Dagster.
agents-md
Create, revise, or audit AGENTS.md files from repository evidence, verified commands, and correctly scoped instructions without overwriting maintainer intent.
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
api-endpoint-builder
Builds reviewable REST API endpoint scaffolds with validation, error handling, authentication, and documentation. Follows best practices for security and scalability.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.