What is technical-paragraph-rewrite?

A review workflow that checks whether a paper paragraph accurately describes related software, then suggests revised wording. It does not change the text unless you approve it.

Use it to compare a manuscript paragraph with source files, examples, or architecture notes and receive several reviewed rewrite options.

It helps catch incorrect descriptions of functions, interfaces, data structures, or system behavior before publication. It is useful when the paper has an associated software implementation.

technical-paragraph-rewrite — Skill 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 technical-paragraph-rewrite

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/technical-paragraph-rewrite/github.svg)](https://agentmods.dev/skills/rezenders/scientific_writing_agent/technical-paragraph-rewrite)

Your own site

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

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 484 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	$0.00038	$0.00484
Opus 5.5	$0.00015	$0.00194
Sonnet 5.5	$0.00008	$0.00097
Haiku 4.5	$0.00004	$0.00048

Measured 1mo ago against content hash 4548a0e3d92b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

technical-paragraph-rewrite 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/technical-paragraph-rewrite/SKILL.md · 28 lines

How it starts

The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Paragraph Rewrite

Follow AGENTS.md. Use this workflow when a paragraph describes implementation behavior and technical verification must precede rewriting.

Workflow

Read context. Inspect the target paragraph, its neighbors, related manuscript claims, and canonical macros.
Verify implementation. Invoke .agents/agents/paper-implementation-checker.md with the paragraph and relevant implementation files. Require CONSISTENT, DIVERGES, or CANNOT_VERIFY with evidence.
Handle uncertainty. Stop before drafting on DIVERGES. On CANNOT_VERIFY, record the limit and prohibit wording that assumes the unverified fact.
Create the contract. Use .agents/context/passage-contract.md to record the verified content, rhetorical function, prohibited implications, and LaTeX that must remain unchanged. Ask the author only about material ambiguity.
Draft once. Invoke .agents/agents/writer.md for one conservative rewrite. Generate alternatives only for a specific author-identified technical or rhetorical choice.
Diagnose. Invoke .agents/agents/scientific-paper-reviewer.md for evidential fidelity and .agents/agents/consistency-auditor.md for manuscript alignment. Use .agents/agents/prose-reviewer.md only when expression remains a material risk. Critics report defects and do not rewrite.
Obtain author decisions. Present the draft and deduplicated findings. Ask the author to accept, reject, or modify each material finding before revision or editing.
Revise once if needed. Give writer only the accepted findings and original evidence. Show a semantic diff, audit against the contract, and stop. Start another cycle only for a specific unresolved defect identified by the author.

Constraints

Treat implementation repositories as read-only ground truth.
Do not invent details or normalize away manuscript-code disagreement.
Do not run automatic rewrite loops or generate routine stylistic alternatives.
Preserve macros, labels, references, citations, math, and technical scope.
Follow the propose-first and validation rules in AGENTS.md.

Read the full file on GitHub · 28 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 · -89 lines · -16 tokens per session 4548a0e3d92b
2mo ago First seen · 117 lines · 54 tokens per session scan A 7d64c2203616

Subscribe to this mod's changes

technical-paragraph-rewrite is a skill published in the GitHub repository Rezenders/scientific_writing_agent (14 stars, last pushed 17d ago), licensed Apache-2.0. It adds 38 tokens to every session and 484 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

technical-paragraph-rewrite next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
technical-paragraph-rewriteRezenders/scientific_writing_agent	Skill	14	17d ago	Apache-2.0	A	38	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