scientific-validator

scientific-validator is an agent for coding agents from indranilbanerjee/contentforge. It costs 47 tokens per session (4,884 once invoked), scanned A, original, MIT.

An agent that checks any draft against verified research and citations to find invented claims, factual errors, unsupported statements, and reasoning problems.

In plain words
What is it for?
Use it to validate drafts against research notes, source records, statistics checks, visual references, and earlier content phases.
Why use it?
It catches accuracy and citation issues before articles, FAQs, reports, or other content are published.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the contentforge plugin — 22 skills, 9 commands, 13 agents shipped together

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.

agentmods
npx agentmods add agents/indranilbanerjee/contentforge/04-scientific-validator
Clone the repo
git clone --depth 1 https://github.com/indranilbanerjee/contentforge

Or install contentforge, the plugin that ships this one along with the rest of its 22 skills, 9 commands, 13 agents.

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 scientific-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/indranilbanerjee/contentforge/04-scientific-validator.svg)](https://agentmods.dev/agents/indranilbanerjee/contentforge/04-scientific-validator)
Your own site
<a href="https://agentmods.dev/agents/indranilbanerjee/contentforge/04-scientific-validator"><img src="https://agentmods.dev/badge/agents/indranilbanerjee/contentforge/04-scientific-validator.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,884 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00047 $0.04884
Opus 5 $0.00023 $0.02442
Sonnet 5 $0.00009 $0.00977
Haiku 4.5 $0.00005 $0.00488

Measured 4d ago against content hash ff9dda970d71, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scientific-validator 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 4d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

agents/04-scientific-validator.md · 328 lines

How it starts

The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scientific Validator Agent — ContentForge Phase 4

Role: Re-verify the drafted content to catch hallucinations, unsourced claims, logical errors, and factual inaccuracies before content proceeds to polishing phases. This audit runs on EVERY content type — blogs, articles, whitepapers, FAQs, and research papers alike.

INPUTS

The orchestrator passes you {brand-slug} and {run_id}. Read prior artifacts with the Read tool — do not expect them inlined in your prompt.

Read from:

  • ~/.claude-marketing/{brand-slug}/runs/{run_id}/phase-3.5-visuals.md — Annotated Draft v1.5 (visual markers + chart references) + Visual Asset Report
  • ~/.claude-marketing/{brand-slug}/runs/{run_id}/phase-3.5-visual-manifest.json — JSON manifest of all visual assets
  • ~/.claude-marketing/{brand-slug}/runs/{run_id}/phase-3-draft.md — Draft Metadata block (word count, citation analysis, section coverage)
  • ~/.claude-marketing/{brand-slug}/runs/{run_id}/phase-2-factcheck.md — Verified Research Brief: verified claims, resolved Citation Library, Statistics Verification Report
  • ~/.claude-marketing/{brand-slug}/runs/{run_id}/phase-1-research.md — the Verified Outline, required by Step 6.1. It was missing from this list while Step 6.1 asked you to cross-reference against it, which left the completeness check with no input. If the file is genuinely absent, record outline adherence as NOT VERIFIABLE with the reason — do not infer the outline from the draft, which would make the draft its own outline and the check vacuous

Do NOT call pipeline-tracker. Phase timing is handled exclusively by the orchestrator.

FENCE — do NOT re-fetch URLs or re-verify sources. Phase 2's verified ledger is authoritative; its URL verification and cross-referencing are already done. Your job is draft-vs-ledger diffing: check that every claim in the draft matches what the ledger verified. No web_fetch, no web_search — if a claim isn't in the ledger, it is a hallucination candidate; you do not go hunting for a new source to save it.

Read the full file on GitHub · 328 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. 4d ago First seen · 328 lines · 47 tokens per session scan A ff9dda970d71

Subscribe to this mod's changes

scientific-validator is an agent published in the GitHub repository indranilbanerjee/contentforge (26 stars, last pushed 18d ago), licensed MIT. It adds 47 tokens to every session and 4,884 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

content-creator

Invoke when the user needs any form of marketing content created or refined — blog posts, ad copy, email campaigns, social media posts, landing page copy, press releases, video scripts, product descriptions, or newsletter content. Triggers on requests to write, draft, rewrite, or improve marketing copy.

indranilbanerjee/digital-marketing-pro · 64 tokens

execution-coordinator

Invoke when the user wants to publish, send, launch, schedule, or execute any marketing action on an external platform. Triggers on requests to publish blog posts, send emails, launch ads, schedule social posts, deliver reports, sync CRM data, or send SMS/notifications. Manages the approval workflow and ensures every…

indranilbanerjee/digital-marketing-pro · 72 tokens

competitive-intel

Invoke for any competitor work — one-off competitive teardowns (content, SEO, paid ads, social, AI visibility, pricing, positioning) OR ongoing competitive monitoring (change detection, share of voice, ad/price monitoring, win/loss, narrative mapping, competitor launch and M&A tracking). Triggers on requests…

indranilbanerjee/digital-marketing-pro · 87 tokens

email-specialist

Invoke when the user needs help with email marketing — campaign strategy, automation flows, deliverability optimization, A/B testing methodology, list segmentation, lifecycle sequences, re-engagement campaigns, win-back flows, transactional email optimization, or newsletter strategy. Triggers on requests involving…

indranilbanerjee/digital-marketing-pro · 74 tokens

intelligence-curator

Use when the task requires interpreting, synthesizing, or distributing marketing learnings across agents — compound intelligence, pattern recognition, confidence scoring, playbook generation, conflict resolution, or institutional knowledge management. This is the sole intake/interpretation hub; durable…

indranilbanerjee/digital-marketing-pro · 67 tokens

social-media-manager

Invoke when the user needs help with social media management — community management, content calendar planning, algorithm optimization, trend response, engagement strategy, UGC curation, social commerce, crisis monitoring, platform-specific strategy, or social listening insights. Triggers on requests involving social…

indranilbanerjee/digital-marketing-pro · 73 tokens