What is write-to-intent?

A workflow for creating or substantially rewriting a manuscript passage to achieve a stated purpose, such as introducing an argument or framing a result. It produces several proposed versions without changing the file until you approve one.

Use it for a new paragraph, subsection introduction, or major rewrite when you can provide the goal, location, and surrounding context.

It helps when the problem is what a passage should accomplish, not just its grammar or wording. The stated goal guides the rewrite.

write-to-intent — 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 write-to-intent

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/write-to-intent/github.svg)](https://agentmods.dev/skills/rezenders/scientific_writing_agent/write-to-intent)

Your own site

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

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 907 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	$0.00041	$0.00907
Opus 5.5	$0.00016	$0.00363
Sonnet 5.5	$0.00008	$0.00181
Haiku 4.5	$0.00004	$0.00091

Measured 17d ago against content hash 3f91edeb7c96, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

write-to-intent 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 17d 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/write-to-intent/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write To Intent

Follow AGENTS.md. Use this workflow for substantive drafting or rewriting toward a rhetorical goal. Use a smaller direct edit for unambiguous wording changes.

Inputs

Build a passage contract from .agents/context/passage-contract.md containing the rhetorical function, required scientific content and evidence, prohibited claims, terminology to preserve, reader state, local connections, and relevant length constraints.

Read the target and neighboring manuscript text. Ask only for missing contract information that would materially change scientific meaning or argument structure. Do not start prose generation while such an ambiguity remains.

Workflow

1. Establish Ground Truth

Search the manuscript for related definitions, claims, terminology, macros, and limitations. Load focused context files as needed: .agents/context/terminology.md, .agents/context/contributions.md, .agents/context/evaluation-claims.md, .agents/context/claim-ledger.md, and .agents/context/do-not-say.md. Invoke .agents/agents/paper-implementation-checker.md only for implementation-dependent claims. Stop and surface any DIVERGES result before drafting; treat CANNOT_VERIFY conservatively.

2. Confirm The Argument

When the structure is not already explicit, use .agents/skills/argument-plan/SKILL.md or produce its equivalent: a claim-level outline only, with no manuscript prose. Show how each required point supports the rhetorical function. Obtain author approval for the outline before drafting.

Skip this gate when the author supplied an explicit, complete structure.

3. Produce One Draft

Invoke .agents/agents/writer.md with the approved contract, relevant context, and verified findings. Request one primary draft. Request alternatives only for a specific unresolved rhetorical choice identified by the author.

4. Run Diagnostic Review

Use read-only critics. Always use:

.agents/agents/scientific-paper-reviewer.md for support, scope, and technical accuracy
.agents/agents/consistency-auditor.md for terminology, macros, notation, and manuscript-wide alignment

Read the full file on GitHub · 75 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.

17d ago Changed · +9 lines 3f91edeb7c96
1mo ago Changed · -95 lines · -11 tokens per session db09ea13fb38
2mo ago First seen · 161 lines · 52 tokens per session scan A bcf956697332

Subscribe to this mod's changes

write-to-intent is a skill published in the GitHub repository Rezenders/scientific_writing_agent (14 stars, last pushed 17d ago), licensed Apache-2.0. It adds 41 tokens to every session and 907 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.

Writing and docs

write-to-intent next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
write-to-intentRezenders/scientific_writing_agent	Skill	14	17d ago	Apache-2.0	A	41	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code