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-draft)<a href="https://agentmods.dev/commands/hanhuark/mechanical-engineering-research-skill/me-han-hu-draft"><img src="https://agentmods.dev/badge/commands/hanhuark/mechanical-engineering-research-skill/me-han-hu-draft/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-draft"><img src="https://agentmods.dev/badge/commands/hanhuark/mechanical-engineering-research-skill/me-han-hu-draft.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 | $0.00023 | $0.00271 |
| Opus 5 | $0.00012 | $0.00135 |
| Sonnet 5 | $0.00005 | $0.00054 |
| Haiku 4.5 | $0.00002 | $0.00027 |
Grade A, and why
me-han-hu-draft 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 10d 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.
What it actually says
Han Hu Manuscript Draft
Use mechanical-engineering-research in Han Hu manuscript mode.
- Identify the requested section, manuscript title, journal, audience, supplied source files, figures, data, equations, and citations.
- Read
han-hu-research-style.md,paper-writing-style.md, andhan-hu-style-calibration-protocol.md. - Retrieve two to four private corpus excerpts matched to the requested genre and rhetorical function. Prefer accepted or author-approved after-text; preserve each exemplar’s evidence status.
- Draft from the current project evidence, not from the corpus. Start with the engineering problem and mechanism before AI, software, or data infrastructure.
- Preserve all supplied values, units, definitions, citations, evidence classes, and claim ceilings. Do not invent a result, mechanism, citation, validation, or approval state.
- Return the draft, a claim-boundary note, and a style-deviation audit naming the exemplar IDs, their evidence status, any necessary journal departure, and the smallest unresolved evidence need.
Expected output:
- publication-ready draft text for the requested section
- evidence and claim-boundary note
- 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.
- 10d ago First seen · 21 lines · 23 tokens per session scan A 508f3fa34960
me-han-hu-draft is a command published in the GitHub repository hanhuark/mechanical-engineering-research-skill (16 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 271 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
security-review
Complete a security review of the pending changes on the current branch.
launch-rhinos
Launch N parallel Rhino MCP sessions via the router and fan out one agent per Rhino.
launch-rhino
Launch a single Rhino MCP session via the router.
build
Build a feature using the adversarial review loop. Default tier: parent works end-to-end, zero subagent spawns. --strict tier adds critic + external review.
check-pr
Check the current branch's PR for external review feedback, fix errors and warnings, run a final external review, and push.
snapshot
Capture the current Rhino viewport and describe what's on screen.