teksersek

teksersek is a skill for Claude Code from urimtal/factcheck-plugin. It costs 147 tokens per session (3,162 once invoked), scanned A, original, MIT.

A fact-checking workflow for journalists and editors reviewing news articles or other reported text. It examines whether claims are supported and how reliable the sources are.

In plain words
What is it for?
Use it to review pasted articles or article URLs, assess source quality, and verify factual claims in Kazakh or English journalism.
Why use it?
It helps reveal unsupported statements, weak sources, and missing verification before publication. It also provides a required process for checking that fetched articles are complete.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the factcheck plugin — 1 skill shipped together

Good fit Use it to review pasted articles or article URLs, assess source quality, and verify factual claims in Kazakh or English journalism.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/urimtal/factcheck-plugin/teksersek
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 urimtal/factcheck-plugin --skill teksersek
Clone the repo
git clone --depth 1 https://github.com/urimtal/factcheck-plugin

Made for: Claude Code.

Or install factcheck, the plugin that ships this one along with the rest of its 1 skill.

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 teksersek

README.md
[![agentmods](https://agentmods.dev/badge/skills/urimtal/factcheck-plugin/teksersek.svg)](https://agentmods.dev/skills/urimtal/factcheck-plugin/teksersek)
Your own site
<a href="https://agentmods.dev/skills/urimtal/factcheck-plugin/teksersek"><img src="https://agentmods.dev/badge/skills/urimtal/factcheck-plugin/teksersek.svg" alt="Measured on agentmods" height="20"></a>
Per session 147 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,162 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 $0.00147 $0.03162
Opus 5 $0.00073 $0.01581
Sonnet 5 $0.00029 $0.00632
Haiku 4.5 $0.00015 $0.00316

Measured 7d ago against content hash 84133a1ec696, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

teksersek 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 7d 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/teksersek/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Teksersek — Journalistic Fact-Checking Skill (v7)

You are a fact-checking assistant for journalists. When this skill is invoked, perform a thorough source quality analysis of the journalistic text provided.

Step 1 — Receive input and acquire full text

The user will provide either:

  • A URL to an article
  • Pasted text

If URL is provided — MANDATORY VERIFICATION PROTOCOL

Web fetch on news sites is unreliable. Articles may appear "complete" but silently drop paragraphs containing named experts in the middle of the body. Follow this procedure WITHOUT EXCEPTION:

  1. First fetch with default parameters

  2. Second fetch with a different extraction method for maximum completeness (e.g. raw HTML download + paragraph extraction, or higher token limit / markdown extraction if the fetch tool supports it)

  3. Compare the two fetches. Look specifically for:

    • Named persons (any capitalized full name) that appear in one fetch but not the other
    • Sections referenced in headings/intro that are missing from the body
    • Abrupt transitions or topic jumps that suggest a missing paragraph
  4. Even if both fetches look complete, you MUST warn the user before proceeding:

    "Мақаланы жүктедім. Бірақ кейбір қазақстандық сайттарда (inform.kz, kazinform т.б.) мақала ортасындағы абзацтар автоматты жүктеу кезінде түсіп қалуы мүмкін. Сенімді талдау үшін мақала мәтінін осы чатқа толық көшіріп жіберуіңізді сұраймын. Әлде сіз жүктелген нұсқамен талдауды жалғастыруды қалайсыз ба?"

  5. Wait for the user's choice. Only proceed without pasted text if the user explicitly confirms.

If pasted text is provided

Use it directly. This is the most reliable input mode.

If input is neither

Ask the user to provide a URL or paste the article text.

Step 2 — Detect language

  • Kazakh text → use AQTAQTA methodology, respond in Kazakh
  • English text → use IMVAIN methodology, respond in English
  • Other → respond: "Бұл MVP нұсқа тек қазақ және ағылшын тілдеріндегі мәтіндерді қолдайды."

Read the full file on GitHub · 200 lines

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. 7d ago First seen · 200 lines · 147 tokens per session scan A 84133a1ec696

Subscribe to this mod's changes

teksersek is a skill published in the GitHub repository urimtal/factcheck-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 147 tokens to every session and 3,162 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

fact-check-prompt

Generates a systematic fact-checking checklist from a draft article, categorizing every verifiable claim by type and priority, with the specific verification question, recommended source type, and appropriate verification strategy for each — across six distinct claim categories with tailored methodologies.

ur-grue/autopunk-media-skills · 55 tokens

source-verification

Walks through structured verification of sources, claims, images, video, and documents across five verification modes — visual media, documents, anonymous sources, expert credentials, and social media content — using the SIFT framework, forensic metadata inspection, deepfake indicators, C2PA Content Credentials, and…

ur-grue/autopunk-media-skills · 82 tokens

ethics-review-checklist

Generate a story-specific editorial ethics checklist: consent verification, harm assessment, source protection, vulnerable-subject protocols, conflict-of-interest flags, and public interest justification — tailored to the story's specific risks.

ur-grue/autopunk-media-skills · 46 tokens

source-credibility-brief

Assesses the credibility of a source whose claims appear in a draft — expertise, track record, conflicts of interest, and the corroboration needed before publication.

ur-grue/autopunk-media-skills · 38 tokens

statistics-fact-checker

Analyzes statistics used in a draft article and flags any that are misrepresented, lack context, use misleading framing, or require additional sourcing before publication.

ur-grue/autopunk-media-skills · 36 tokens

claim-verification-checklist

Generates a point-by-point checklist of every verifiable claim in a draft article, categorized by claim type and accompanied by the specific evidence needed to confirm each one.

ur-grue/autopunk-media-skills · 39 tokens