template-manuscript-claim-verification

template-manuscript-claim-verification is a skill for Claude Code, Codex from docxology/template. It costs 86 tokens per session (1,222 once invoked), scanned A, original, Apache-2.0.

A three-pass skill for checking every claim in a research manuscript against its code, data, references, and rendered output.

In plain words
What is it for?
Use it before submitting to arXiv or Zenodo, or when verifying claims, citations, figures, methods, and cross-references. It also independently recomputes results and repairs prose when needed.
Why use it?
It finds unsupported statements, mismatched numbers, missing citation support, and differences between the manuscript and its source evidence before submission.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run python scripts/runner/execute_pipeline.py --project <project> --core-only.

Good fit Use it before submitting to arXiv or Zenodo, or when verifying claims, citations, figures, methods, and cross-references. It also independently recomputes results and repairs prose when needed.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/docxology/template
agentmods
npx agentmods add skills/docxology/template/manuscript-claim-verification

Made for: Claude Code, Codex.

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 template-manuscript-claim-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/docxology/template/manuscript-claim-verification/github.svg)](https://agentmods.dev/skills/docxology/template/manuscript-claim-verification)
Your own site
<a href="https://agentmods.dev/skills/docxology/template/manuscript-claim-verification"><img src="https://agentmods.dev/badge/skills/docxology/template/manuscript-claim-verification/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 template-manuscript-claim-verification

Your own site · 80×15
<a href="https://agentmods.dev/skills/docxology/template/manuscript-claim-verification"><img src="https://agentmods.dev/badge/skills/docxology/template/manuscript-claim-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,222 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00086 $0.01222
Opus 5 $0.00043 $0.00611
Sonnet 5 $0.00017 $0.00244
Haiku 4.5 $0.00009 $0.00122

Measured 9d ago against content hash d857b231ed9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

template-manuscript-claim-verification 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 9d 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.

docs/prompts/manuscript-claim-verification/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Manuscript claim verification

Natural invoke

  • "Triple-check every claim in my manuscript before arXiv"
  • "Abstract numbers don't match optimization_results.csv"
  • "Verify citations actually support what the prose says"

Inputs to confirm

Workflow

Build a claim inventory first (numbered, file:line, class: number, comparison, citation, cross-ref, method, figure reading).

Pass 1 — Source traceability: For each claim, locate backing artifact (generated variable, src/ + test, output/ file, bib key, cross-ref key). Tag BACKED / WEAK / UNBACKED. The canonical deterministic check for binding manuscript numbers/citations to registered evidence is infrastructure.validation.cli evidence <project> --fail-on-issues — run it as the machine gate for BACKED claims.

Pass 2 — Independent recomputation: Regenerate from clean; re-run validation CLI. Reconciliation table: stated | recomputed | tolerance | PASS/FAIL. UNREPRODUCIBLE = FAIL.

Pass 3 — Methodological adversary: Independent review axis — overstated claims, citation mismatch, figure/caption issues, abstract not earned by results. Tag OVERSTATED / UNSUPPORTED / MISLEADING.

Pass 4 — Reference existence (anti-hallucination): Resolve every cited reference against Crossref / OpenAlex / arXiv with the deterministic verification gate. Tag each ok / mismatch / fabricated / unverifiable / unchecked / anachronism. fabricated, mismatch, and anachronism are blocking. unchecked (offline + uncached) is an honest non-pass — re-run with --live to resolve, never treat it as clean. Distilled from the ARS hallucination taxonomy; runs fully offline against the SQLite cache once seeded.

Improve (not just report): Tighten claims; use generated-variable mechanism; fix citations/cross-refs; keep renderable format ([@key], @fig: OR [[…]] per project — never raw \cite{}/\ref{}). Update projects/<n>/AGENTS.md and README.md. Never hand-edit output/.

Read the full file on GitHub · 84 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 84 lines · 86 tokens per session scan A d857b231ed9b

Subscribe to this mod's changes

template-manuscript-claim-verification is a skill published in the GitHub repository docxology/template (19 stars, last pushed today), licensed Apache-2.0. It adds 86 tokens to every session and 1,222 once invoked, about $0.0004 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 skills, from other repositories

planning-with-files

Persistent file-based planning for multi-step AI-agent work. Keeps taskplan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and…

mxyhi/ok-skills · 117 tokens

aerospace-engineering-technician

Use when a task needs the judgment of an Aerospace Engineering and Operations Technologist/Technician — verifying an installed fastener's preload against a drawing's torque callout via the T=K·D·F relationship, reducing strain-gauge data from a structural proof-load test into stress and checking it against an…

wonsukchoi/domain-experts · 169 tokens

aviation-inspector

Use when a task needs the judgment of an Aviation Inspector — determining whether an air carrier's fleet is in compliance with an Airworthiness Directive across a maintenance-records sample, deciding where the FAA's compliance-and-enforcement ladder places a finding (compliance action vs. Letter of Correction vs.…

wonsukchoi/domain-experts · 113 tokens

actor

Use when a task needs the judgment of a professional Actor — breaking down sides for a self-tape audition, preparing a character choice for rehearsal, deciding between two conflicting bookings, reading a contract offer for scale vs. scale-plus terms, or diagnosing why callbacks aren't converting to bookings.

wonsukchoi/domain-experts · 58 tokens

advertising-promotions-manager

Use when a task needs the judgment of an Advertising and Promotions Manager — building a media plan backward from an objective and budget, briefing or evaluating creative against a brief, negotiating with agencies/media vendors, sanity-checking vendor-reported attribution, or reading a post-campaign debrief to…

wonsukchoi/domain-experts · 69 tokens

agricultural-equipment-operator

Use when a task needs the judgment of an Agricultural Equipment Operator — calibrating planter seed population and singulation, diagnosing combine header or separator loss, sequencing planting or harvest across fields under a weather-constrained window, sizing machinery capacity in acres/hour against a season's…

wonsukchoi/domain-experts · 77 tokens