What is full-manuscript-audit?

A complete review of a scientific manuscript before submission or after a major revision. It checks open notes, consistency across sections, scientific issues, and optionally whether implementation claims match the software.

Use it to audit terminology, acronyms, claims, comparisons, annotations, and implementation-related descriptions.

It brings separate checks into one report so unresolved problems are easier to find before submission. It can focus on the full manuscript or selected sections.

full-manuscript-audit — Skill for Claude Code and Codex by Rezenders

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 Rezenders/scientific_writing_agent --skill full-manuscript-audit

Clone the repo

git clone --depth 1 https://github.com/Rezenders/scientific_writing_agent

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rezenders/scientific_writing_agent/full-manuscript-audit/github.svg)](https://agentmods.dev/skills/rezenders/scientific_writing_agent/full-manuscript-audit)

Your own site

<a href="https://agentmods.dev/skills/rezenders/scientific_writing_agent/full-manuscript-audit"><img src="https://agentmods.dev/badge/skills/rezenders/scientific_writing_agent/full-manuscript-audit/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rezenders/scientific_writing_agent/full-manuscript-audit"><img src="https://agentmods.dev/badge/skills/rezenders/scientific_writing_agent/full-manuscript-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 570 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.

Model	Per session	Once invoked
Fable 5.1	$0.00049	$0.00570
Opus 5.5	$0.00020	$0.00228
Sonnet 5.5	$0.00010	$0.00114
Haiku 4.5	$0.00005	$0.00057

Measured 1mo ago against content hash cd697978c79d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

full-manuscript-audit 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 1mo 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.

.agents/skills/full-manuscript-audit/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Full Manuscript Audit

Full-manuscript pre-submission audit. Orchestrates all review agents across every section and produces a unified GO / CONDITIONAL GO / NO-GO report. Use before /pre-submission to catch issues early.

Section Map

Use the project-specific section map in .agents/context/paper-model.md. If it still contains placeholders, derive the active section list from <MAIN_TEX> before auditing.

Workflow

Phase 1 — Annotation Inventory

Run /find-annotations to list all open annotation macros documented in AGENTS.md or .agents/context/terminology.md. Report count and location.

Phase 2 — Full Consistency Audit

Use .agents/agents/consistency-auditor.md on the full manuscript. Check:

macro and terminology drift using .agents/context/terminology.md;
acronym consistency (first use, subsequent use);
contribution-statement alignment (introduction vs. body vs. conclusion);
project-specific ambiguous terms and distinctions;
experimental setup descriptions versus reported results;
cross-section contradictions.

Phase 3 — Section-by-Section Scientific Review

Use .agents/agents/scientific-paper-reviewer.md on each section. Flag critical issues only — skip minor style notes for speed.

Phase 4 — Implementation Spot-Check

Use .agents/agents/paper-implementation-checker.md on high-risk implementation-dependent claims listed in .agents/context/claim-ledger.md, .agents/context/evaluation-claims.md, or the target sections. Focus on claims about runtime behavior, interfaces, generated artifacts, experiment scripts, data processing, and quantitative results.

Phase 5 — Unified Report

## Full Manuscript Audit

### Open Annotations
[Count and location summary]

### Critical Issues (block submission)
[Merged findings from Phases 2–4, ordered by section]

### Medium Issues (should fix)
[...]

### Per-Section Verdicts
| Section | Verdict |
|---|---|
| Introduction | READY / NEEDS REVISION / MAJOR ISSUES |
| ... | ... |

### Overall Verdict
GO | CONDITIONAL GO | NO-GO

Read the full file on GitHub · 67 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.

1mo ago Changed · -47 lines · -14 tokens per session cd697978c79d
2mo ago First seen · 114 lines · 63 tokens per session scan A 1e1ad7c6dbe9

Subscribe to this mod's changes

full-manuscript-audit is a skill published in the GitHub repository Rezenders/scientific_writing_agent (14 stars, last pushed 17d ago), licensed Apache-2.0. It adds 49 tokens to every session and 570 once invoked, about $0.0002 per session on Opus 5.5. 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.

Scientific Writing and docs

full-manuscript-audit next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
full-manuscript-auditRezenders/scientific_writing_agent	Skill	14	17d ago	Apache-2.0	A	49	Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-plugins	Skill	35k	2d ago	Apache-2.0	A	123	Claude Code
exploratory-data-analysisK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	83	Claude Code
matlabK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	44	Claude Code
phylogeneticsK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	71	Claude Code, Codex
research-engineerdavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	43	Claude Code, Codex
mapping-to-snomedmaziyarpanahi/openmed	Skill	5.8k	yesterday	Apache-2.0	A	205	Claude Code