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 randommonicle/claude-skills --skill verified-citationsgit clone --depth 1 https://github.com/randommonicle/claude-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/randommonicle/claude-skills/verified-citations)<a href="https://agentmods.dev/skills/randommonicle/claude-skills/verified-citations"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/verified-citations/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/randommonicle/claude-skills/verified-citations"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/verified-citations.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 | $0.01860 |
| Opus 5 | $0.00091 | $0.00930 |
| Sonnet 5 | $0.00036 | $0.00372 |
| Haiku 4.5 | $0.00018 | $0.00186 |
Grade A, and why
verified-citations 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.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verified citations
A citation is output you produced, never a reference you recalled. This skill exists because recall is confident and wrong in a narrow, repeatable way, and because the model committing the error reliably reports that it checked.
The measured failure mode
Two independent runs on the same repository, one building a skill library, one authoring an implementation design, both reviewed by a different model:
- 58 of 62 citations exactly right. Trigger names, ERRCODEs, migration numbers, statutory message prefixes, function signatures: all correct. Technical grounding is not the weakness.
- The misses were all about WHERE and WHEN, not WHAT:
- A path invented around a borrowed line number. A spec named a file with no directory and
cited
:47-49. The author reproduced the line numbers correctly and fabricated a plausible directory to complete the reference. The file was real; the path was not. - A line number drifted onto nothing.
:239was cited as a function; 239 was a blank line between two functions. - Ranges that were loose rather than wrong. A cited
:82-118contained the claimed content and also a comment block and a grants preamble, presented as one coherent thing. - Provenance misattributed. "Landed 2026-07-01 under audit C4" when
git log --followshowed 2026-06-15 under C5.
- A path invented around a borrowed line number. A spec named a file with no directory and
cited
- Every run self-reported full verification. The error is invisible from the inside. That is the single most important fact in this file.
The rule that does the work
Every file:line citation carries the quoted text of the line it points at.
This is not a style preference. It is the only rule here that cannot be satisfied by intending to be careful, because you cannot quote a line without having opened the file at that path and looked at that line. It kills the two commonest failures outright: a fabricated path has no line to quote, and a drifted line number quotes a blank string.
It also makes review mechanical. A reviewer runs sed -n 'Np' FILE and compares, instead of
re-deriving your argument to decide whether they believe you.
What ships with it
1 file 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.
- 12d ago First seen · 130 lines · 182 tokens per session scan A a02a25bf408a
verified-citations is a skill published in the GitHub repository randommonicle/claude-skills (23 stars, last pushed 6d ago), licensed Apache-2.0. It adds 182 tokens to every session and 1,860 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 2026-08-31.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…