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.
git clone --depth 1 https://github.com/hanhuark/mechanical-engineering-research-skillWrote 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.
[](https://agentmods.dev/commands/hanhuark/mechanical-engineering-research-skill/me-han-hu-revise)<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.
<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>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 | $0.00026 | $0.00386 |
| Opus 5 | $0.00013 | $0.00193 |
| Sonnet 5 | $0.00005 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00039 |
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.
What it actually says
Han Hu Manuscript Revision
Use mechanical-engineering-research in Han Hu manuscript mode.
- Inspect the current manuscript source, figures and captions, tables, equations, cited evidence, reviewer comments, and available data before editing.
- Read
han-hu-research-style.md,paper-writing-style.md,manuscript-revision-submission.md, andhan-hu-style-calibration-protocol.md. - 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.
- Diagnose paragraph logic, physical framing, figure roles, claim strength, definitions, conditions, evidence boundaries, redundancy, and reader clarity before sentence-level polishing.
- 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.
- Correct substantive problems through analysis, evidence, definitions, or explicit limitations where required. Do not merely weaken prose to hide a validity gap.
- Preserve values, units, equations, citations, sample sizes, uncertainty statements, definitions, and evidence class. Flag any proposed change that would alter them.
- 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
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.
- today Changed · +2 lines 3df68cbaafb8
- 12d ago First seen · 23 lines · 26 tokens per session scan A c9b1ef7e5d13
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.
Other commands, from other repositories
research
Start or resume an academic research project — idea through literature, methodology, writing, feedback, and publishing.
openehr-explain
One-stop router that explains or looks up any openEHR thing — auto-detects an archetype, a template, an RM/AM/BASE type, an RM structural concept, an ADL idiom, an AQL query or keyword, or a terminology code (replaces /archetype-explain, /template-explain, /type-spec, /rm-structure, /adl-idiom, /terminology).
gpd:write-paper
Structure and write a physics paper from project research results or a bounded external-authoring intake.
gpd:derive-equation
Perform a rigorous physics derivation with systematic verification at each step.
gpd:limiting-cases
Systematically identify and verify all relevant limiting cases for a result or phase.
external-review
Run a single external code review via an external LLM API on the full branch diff vs main. Standalone usage — no aggregation with internal review.