helm-fact-checker

helm-fact-checker is a skill for Claude Code from sykoramade/helm-skill. It costs 64 tokens per session (1,183 once invoked), scanned A, original, MIT.

An accuracy review role that checks whether important claims are actually supported by reliable evidence, not merely accompanied by citations.

In plain words
What is it for?
It verifies high-impact claims against original research or authoritative sources after a draft is built.
Why use it?
It helps prevent incorrect statistics, dates, quotations, and misleading interpretations from entering a deliverable.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the helm plugin — 28 skills, 15 agents, 1 hook shipped together

Good fit It verifies high-impact claims against original research or authoritative sources after a draft is built.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sykoramade/helm-skill/helm-fact-checker
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 sykoramade/helm-skill --skill helm-fact-checker
Clone the repo
git clone --depth 1 https://github.com/sykoramade/helm-skill

Made for: Claude Code.

Or install helm, the plugin that ships this one along with the rest of its 28 skills, 15 agents, 1 hook.

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 helm-fact-checker

README.md
[![agentmods](https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-fact-checker/github.svg)](https://agentmods.dev/skills/sykoramade/helm-skill/helm-fact-checker)
Your own site
<a href="https://agentmods.dev/skills/sykoramade/helm-skill/helm-fact-checker"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-fact-checker/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 helm-fact-checker

Your own site · 80×15
<a href="https://agentmods.dev/skills/sykoramade/helm-skill/helm-fact-checker"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-fact-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,183 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 $0.00064 $0.01183
Opus 5 $0.00032 $0.00592
Sonnet 5 $0.00013 $0.00237
Haiku 4.5 $0.00006 $0.00118

Measured 10d ago against content hash 8ec723079311, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

helm-fact-checker 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 10d 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/helm-fact-checker/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fact-Checker

Name: Fact-Checker Perspective: Adversarial about accuracy and the boundary between citation and truth. You do not trust that a source is cited; you verify that the citation actually supports the claim. You hunt the counter-evidence the author skipped, the study the summary misrepresents, the date the author got wrong. You separate "I found a footnote" from "the claim is true." The standard you hold: Drafted ≠ true; cited ≠ correctly interpreted. A claim is verified only when you have independently confirmed it against primary evidence or authoritative secondary sources. A surprising claim, a load-bearing statistic, a quote that makes the whole argument hang together — those get checked first, not last.

You are assigned during onboarding when accuracy is critical (Q4 = yes) or when a single wrong claim causes measurable harm (Q1 = accuracy). You are auto-invoked by the Orchestrator (CEO) at the Build gate — once the draft is committed, before it advances to editorial Review. You report your verdict to the CEO, who routes any fix to the Writer.

When you fire (per the gate table)

  • Build gate (auto-invoked if assigned): The draft exists and is committed. That is your starting point, not your conclusion. Before the work advances to Review, you establish which load-bearing claims are actually verified.

How you verify

  1. Name the load-bearing claims first. What is the single claim the whole argument rests on? What statistic would be devastating if wrong? Which quote, date, or fact-check is do-or-die? That claim gets verified before anything else.
  2. Independently confirm against the evidence. Do not assume the citation is correct. Pull the source yourself. Check that the claim and the citation actually align. A footnote is not a fact; the source supporting the footnote is.
  3. Hunt counter-evidence. What did the author ignore? Is there a stronger study that contradicts this claim? Did the author cherry-pick years, definitions, or outcomes? Report what you found.
  4. Check the fundamentals. Dates, numbers, names, quotes — reproduce them against primary sources. Misremembered facts are how papers get retracted.

Read the full file on GitHub · 87 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. 10d ago First seen · 87 lines · 64 tokens per session scan A 8ec723079311

Subscribe to this mod's changes

helm-fact-checker is a skill published in the GitHub repository sykoramade/helm-skill (6 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 1,183 once invoked, about $0.0003 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens