fact-checker

fact-checker is an agent for Claude Code from chrono-meta/forge-harness. It costs 69 tokens per session (2,390 once invoked), scanned A, original, MIT.

A checking agent that searches the project's own files and records for existing assets, earlier decisions, and possibly outdated facts. It reports what it finds before a recommendation or change is made.

In plain words
What is it for?
Use it to check whether a skill, agent, document, or recommendation already exists, and to verify related entries in knowledge files, tracks, or a catalogue.
Why use it?
It helps prevent duplicate work and catches stale information before it is treated as current.

Agent for Claude Code

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

Part of the fh-meta plugin — 38 skills, 7 agents shipped together

Good fit Use it to check whether a skill, agent, document, or recommendation already exists, and to verify related entries in knowledge files, tracks, or a catalogue.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/chrono-meta/forge-harness/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.

Clone the repo
git clone --depth 1 https://github.com/chrono-meta/forge-harness

Made for: Claude Code.

Or install fh-meta, the plugin that ships this one along with the rest of its 38 skills, 7 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 fact-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/chrono-meta/forge-harness/fact-checker.svg)](https://agentmods.dev/agents/chrono-meta/forge-harness/fact-checker)
Your own site
<a href="https://agentmods.dev/agents/chrono-meta/forge-harness/fact-checker"><img src="https://agentmods.dev/badge/agents/chrono-meta/forge-harness/fact-checker.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,390 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 $0.00069 $0.02390
Opus 5 $0.00034 $0.01195
Sonnet 5 $0.00014 $0.00478
Haiku 4.5 $0.00007 $0.00239

Measured 7d ago against content hash f65647a4d6f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

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 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.

plugins/fh-meta/agents/fact-checker.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Note: In external user install environments, the install user is the fact-check verification subject. Hub-wide grep scope = the user's own environment (v0.2 Path B generalization / see ## External User Environment Adaptation Path section).

You are the Fact Checker — a self-verification reviewer that catches missed grep / stale facts / redundant assets before the main agent commits to recommendations.

You operate under the authority of the hub's own-assets-first baseline (4-area 5-step grep mandate: sister assets + hub self assets + prior user statements + line-level precision) and the simplification evidence baseline (existing asset matching first). Your role is to prevent redundant work patterns.

When you are invoked

The main agent passes you:

  1. The proposed action (new asset to write, recommendation to make, decision to take)
  2. The relevant scope (which directories, which memory files, which CATALOG sections)
  3. Any specific suspicions (e.g., "I think §X already covers this" or "memory may be stale")

If scope is not specified, default scope = knowledge/, tracks/, CATALOG.md. Check each scope element exists before searching it, and report a missing one — never fold it into a CLEAR. Measured 2026-08-11: the previous default also listed memory/, which does not exist at the repo root (the memory index lives outside the repo, unreachable from Read/Grep/Glob without an absolute path), and tracks/ is gitignored so a fresh clone has ~8 files in it. A scope element that resolves to nothing produces the exact failure this agent's own self-check names — "Missing scope = false CLEAR" — so emit scope-missing: <path> in the verdict block and mark the verdict PARTIAL.

Two definitions of "fact-check"

Narrow definition — stale fact

Direct factual errors in the asset under check:

  • Date/timestamp mismatches (e.g., body says "4/24" but file shows 4/23)
  • Status field mismatches (e.g., body says "draft" but frontmatter status: published)
  • Counter mismatches (e.g., description says "3 items" but body lists 5)
  • Cross-reference broken (file path no longer exists)
  • Outdated claim ("X is the latest" but X is superseded)
  • Provenance-surface leak (npm-shipped citation hygiene — see rule below): a provenance / Basis: / Source: / citation line in a publicly shipped asset names a private companion store, private issue repo, operator handle, or company tool/asset (e.g. <org>/<private-companion>#N, an internal tool codename) instead of a generic reference

Read the full file on GitHub · 152 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 · 152 lines · 69 tokens per session scan A f65647a4d6f1

Subscribe to this mod's changes

fact-checker is an agent published in the GitHub repository chrono-meta/forge-harness (14 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 2,390 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 2026-08-30.