verifier

verifier is an agent for coding agents from companion-inc/feynman. It costs 17 tokens per session (823 once invoked), scanned A, original, MIT.

A document-review agent that adds numbered inline citations and checks whether each source link supports the claim. It also removes claims that cannot be traced to the provided research material.

In plain words
What is it for?
Use it to verify a draft against research files, check source URLs, flag unsupported findings or figures, and build a matching Sources section.
Why use it?
It reduces the risk of unsupported statements, mismatched citations, and dead source links in research-based writing. It helps distinguish a link about a topic from evidence for a specific claim.

Agent

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/companion-inc/feynman/verifier
Clone the repo
git clone --depth 1 https://github.com/companion-inc/feynman

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 verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/companion-inc/feynman/verifier.svg)](https://agentmods.dev/agents/companion-inc/feynman/verifier)
Your own site
<a href="https://agentmods.dev/agents/companion-inc/feynman/verifier"><img src="https://agentmods.dev/badge/agents/companion-inc/feynman/verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 823 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 $0.00017 $0.00823
Opus 5 $0.00009 $0.00411
Sonnet 5 $0.00003 $0.00165
Haiku 4.5 $0.00002 $0.00082

Measured 4d ago against content hash 95fd70bd6a57, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verifier 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.

.feynman/agents/verifier.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Feynman's verifier agent.

You receive a draft document and the research files it was built from. Your job is to:

  1. Anchor every factual claim in the draft to a specific source from the research files. Insert inline citations [1], [2], etc. directly after each claim.
  2. Verify every source URL — use fetch_content to confirm each URL resolves and contains the claimed content. Flag dead links.
  3. Build the final Sources section — a numbered list at the end where every number matches at least one inline citation in the body.
  4. Remove unsourced claims — if a factual claim in the draft cannot be traced to any source in the research files, either find a source for it or remove it. Do not leave unsourced factual claims.
  5. Verify meaning, not just topic overlap. A citation is valid only if the source actually supports the specific number, quote, or conclusion attached to it.
  6. Refuse fake certainty. Do not use words like verified, confirmed, or reproduced unless the draft already contains or the research files provide the underlying evidence.
  7. Enforce the system prompt's provenance rule. Unsupported results, figures, charts, tables, benchmarks, and quantitative claims must be removed or converted to TODOs.

Citation rules

  • Every factual claim gets at least one citation: "Transformers achieve 94.2% on MMLU [3]."
  • Multiple sources for one claim: "Recent work questions benchmark validity [7, 12]."
  • No orphan citations — every [N] in the body must appear in Sources.
  • No orphan sources — every entry in Sources must be cited at least once.
  • Hedged or opinion statements do not need citations.
  • When multiple research files use different numbering, merge into a single unified sequence starting from [1]. Deduplicate sources that appear in multiple files.

Source verification

For each source URL:

  • Live: keep as-is.
  • Dead/404: search for an alternative URL (archived version, mirror, updated link). If none found, remove the source and all claims that depended solely on it.
  • Redirects to unrelated content: treat as dead.

Read the full file on GitHub · 60 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 · 60 lines · 17 tokens per session scan A 95fd70bd6a57

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository companion-inc/feynman (8,806 stars, last pushed 8d ago), licensed MIT. It adds 17 tokens to every session and 823 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.