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/a554b554/reactant/citenpx skills add a554b554/Reactant --skill citegit clone --depth 1 https://github.com/a554b554/ReactantWhat 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 | $0.00015 | $0.00480 |
| Opus 5 | $0.00008 | $0.00240 |
| Sonnet 5 | $0.00003 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
cite 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.
What it actually says
Cite
Find relevant references to support a statement or claim, and insert a citation.
Input
- File path: the file being processed.
- Surrounding text: the paragraph or block where the
<@cite: ...>tag appears. - Prompt: where/how to find references. May include a source hint, an explicit reference, or a search instruction.
Workflow
- Read the surrounding text to understand the claim or statement that needs a citation.
- Determine the citation source from the prompt: user may specify a
.bibor.mdfile, anarxivsearch, a web search, or another file containing references. - Determine the output format: look at the existing citations and file format to determine the output, e.g., in LaTeX it should be \cite{key}, and in Markdown it should be [number] or [@key]. Check out the existing citation style in the document and follow it.
Context References
The prompt may contain context references wrapped in double backticks ( ``). These point to external resources.
- As source (most common): The reference points to a citation source — a
.bibfile,arxiv, a URL, or another file containing references. E.g.,<@cite: ``refs.bib``>— searchrefs.bibfor a matching entry. - Resolve file references relative to the source file's directory unless an absolute path is given.
- Remove the
Rules
- Only insert citations — do not modify the surrounding text.
- The
<@cite: ...>tag and all - When searching online or on arXiv, prefer peer-reviewed or well-cited sources.
- If no credible source can be found, replace the tag with a placeholder comment (e.g.,
[citation needed]) and warn the user. - In latex doc, when cite a new paper found online, add it to the main
.bibfile. When adding to a.bibfile, do not duplicate existing entries. - Match the citation style already used in the document.
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 · 39 lines · 15 tokens per session scan A b783ee7e27b8
cite is a skill published in the GitHub repository a554b554/Reactant (54 stars, last pushed 29d ago), licensed MIT. It adds 15 tokens to every session and 480 once invoked, about $0.0001 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
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…