me-han-hu-revise

me-han-hu-revise is a command for Claude Code from hanhuark/mechanical-engineering-research-skill. It costs 26 tokens per session (386 once invoked), scanned A, original, MIT.

A revision workflow for an existing technical manuscript in Han Hu manuscript mode. It preserves scientific evidence, figures, values, citations, equations, and the boundaries of the claims while addressing deeper writing and reasoning problems.

In plain words
What is it for?
Reviewing manuscript text, figures, tables, equations, data, citations, and reviewer comments; diagnosing structure and claims; revising the manuscript; and reporting changes, unresolved issues, and evidence limits.
Why use it?
It helps improve a research paper without accidentally changing its results, evidence, definitions, or level of support.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the thermal-fluid-research-workflow plugin — 9 skills, 17 commands shipped together

Good fit Reviewing manuscript text, figures, tables, equations, data, citations, and reviewer comments; diagnosing structure and claims; revising the manuscript; and reporting changes, unresolved issues, and evidence limits.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/hanhuark/mechanical-engineering-research-skill/me-han-hu-revise
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.

Clone the repo
git clone --depth 1 https://github.com/hanhuark/mechanical-engineering-research-skill

Made for: Claude Code.

Or install thermal-fluid-research-workflow, the plugin that ships this one along with the rest of its 9 skills, 17 commands.

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 me-han-hu-revise

README.md
[![agentmods](https://agentmods.dev/badge/commands/hanhuark/mechanical-engineering-research-skill/me-han-hu-revise/github.svg)](https://agentmods.dev/commands/hanhuark/mechanical-engineering-research-skill/me-han-hu-revise)
Your own site
<a href="https://agentmods.dev/commands/hanhuark/mechanical-engineering-research-skill/me-han-hu-revise"><img src="https://agentmods.dev/badge/commands/hanhuark/mechanical-engineering-research-skill/me-han-hu-revise/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 me-han-hu-revise

Your own site · 80×15
<a href="https://agentmods.dev/commands/hanhuark/mechanical-engineering-research-skill/me-han-hu-revise"><img src="https://agentmods.dev/badge/commands/hanhuark/mechanical-engineering-research-skill/me-han-hu-revise.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 386 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00386
Opus 5 $0.00013 $0.00193
Sonnet 5 $0.00005 $0.00077
Haiku 4.5 $0.00003 $0.00039

Measured today against content hash 3df68cbaafb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

me-han-hu-revise 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 today.

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.

commands/me-han-hu-revise.md · 25 lines

What it actually says

Han Hu Manuscript Revision

Use mechanical-engineering-research in Han Hu manuscript mode.

  1. Inspect the current manuscript source, figures and captions, tables, equations, cited evidence, reviewer comments, and available data before editing.
  2. Read han-hu-research-style.md, paper-writing-style.md, manuscript-revision-submission.md, and han-hu-style-calibration-protocol.md.
  3. Retrieve two to four private corpus excerpts matched to the section’s genre and rhetorical function. Prefer accepted or author-approved after-text; preserve each exemplar’s evidence status.
  4. Diagnose paragraph logic, physical framing, figure roles, claim strength, definitions, conditions, evidence boundaries, redundancy, and reader clarity before sentence-level polishing.
  5. For abstracts, introductions, and conclusions, check that the narrative separates the existing gap from the work's actual contribution. State the consequence of the gap, what the work does with its data or model, what it finds, and how the finding should be used. Do not let a known limitation become the manuscript's main conclusion.
  6. Correct substantive problems through analysis, evidence, definitions, or explicit limitations where required. Do not merely weaken prose to hide a validity gap.
  7. Preserve values, units, equations, citations, sample sizes, uncertainty statements, definitions, and evidence class. Flag any proposed change that would alter them.
  8. Return the revised text, a change log separating substantive corrections from style edits, unresolved blockers, and a style-deviation audit.

Expected output:

  • revised manuscript text
  • substantive-versus-style change log
  • unresolved technical or evidence blockers
  • reader-clarity and narrative audit for abstracts, introductions, or conclusions
  • style-deviation audit
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. today Changed · +2 lines 3df68cbaafb8
  2. 12d ago First seen · 23 lines · 26 tokens per session scan A c9b1ef7e5d13

Subscribe to this mod's changes

me-han-hu-revise is a command published in the GitHub repository hanhuark/mechanical-engineering-research-skill (16 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 386 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.