nonfiction-research

nonfiction-research is a skill for Claude Code, Codex from Ckokoski/AuthorAgent. It costs 17 tokens per session (361 once invoked), scanned A, original, MIT.

A research and fact-checking skill for nonfiction writing. It gathers sources, records citation details, checks factual claims, and organizes research by topic or chapter.

In plain words
What is it for?
Use it to research books and articles, manage interviews and permissions, prepare bibliographies in common citation styles, fact-check statistics, and flag possible legal concerns.
Why use it?
It reduces the work of tracking where claims came from and helps distinguish verified facts, opinions, weak sources, and claims that cannot be confirmed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to research books and articles, manage interviews and permissions, prepare bibliographies in common citation styles, fact-check statistics, and flag possible legal concerns.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ckokoski/authoragent/nonfiction-research
Install

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.

Any agent
npx skills add Ckokoski/AuthorAgent --skill nonfiction-research
Clone the repo
git clone --depth 1 https://github.com/Ckokoski/AuthorAgent

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for nonfiction-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/ckokoski/authoragent/nonfiction-research/github.svg)](https://agentmods.dev/skills/ckokoski/authoragent/nonfiction-research)
Your own site
<a href="https://agentmods.dev/skills/ckokoski/authoragent/nonfiction-research"><img src="https://agentmods.dev/badge/skills/ckokoski/authoragent/nonfiction-research/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.

agentmods 80×15 button for nonfiction-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/ckokoski/authoragent/nonfiction-research"><img src="https://agentmods.dev/badge/skills/ckokoski/authoragent/nonfiction-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 361 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.00361
Opus 5 $0.00009 $0.00180
Sonnet 5 $0.00003 $0.00072
Haiku 4.5 $0.00002 $0.00036

Measured 12d ago against content hash be2d93c9be1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

nonfiction-research 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.

skills/author/nonfiction-research/SKILL.md · 60 lines

What it actually says

Nonfiction Research Skill

Comprehensive research support for nonfiction authors.

Source Management

  • Track all sources with full citation data
  • Organize by chapter/topic
  • Flag primary vs. secondary sources
  • Note source reliability and potential bias

Citation Formats

Support: APA, MLA, Chicago (Notes & Bibliography), Chicago (Author-Date), Harvard Auto-generate bibliography/works cited in the author's preferred format.

Fact-Checking Process

  1. Identify all factual claims in the manuscript
  2. Trace each claim to its source
  3. Verify source reliability
  4. Flag: ✅ verified, ⚠️ needs stronger source, ❌ cannot verify
  5. Note claims that are author opinion vs. established fact

Interview Management

  • Track interview subjects, dates, and key quotes
  • Permission/consent tracking
  • Quote accuracy verification

Data Visualization

  • Help structure data for charts, graphs, and infographics
  • Fact-check statistical claims
  • Suggest better ways to present complex data
  • Flag potential libel concerns
  • Note when something might need legal review
  • Track permissions needed for quoted material
  • Fair use considerations

Output

Save research database to projects/[project]/research/sources.md

Changes

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.

  1. 12d ago First seen · 60 lines · 17 tokens per session scan A be2d93c9be1a

Subscribe to this mod's changes

nonfiction-research is a skill published in the GitHub repository Ckokoski/AuthorAgent (110 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 361 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.