Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add wenhaochai/claude-plugins/plugin install writingWrote 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/skills/wenhaochai/claude-plugins/preflight)<a href="https://agentmods.dev/skills/wenhaochai/claude-plugins/preflight"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/preflight/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/skills/wenhaochai/claude-plugins/preflight"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/preflight.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 | $0.00111 | $0.00634 |
| Opus 5.5 | $0.00044 | $0.00254 |
| Sonnet 5.5 | $0.00022 | $0.00127 |
| Haiku 4.5 | $0.00011 | $0.00063 |
Grade A, and why
preflight scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Preflight
Six checks a model gets wrong and a script gets right. Run it before the paper goes anywhere.
python3 "${CLAUDE_PLUGIN_ROOT}/skills/preflight/preflight.py" <paper-dir> --venue iclr
Flags: --venue picks the page cap (neurips icml iclr cvpr iccv eccv acl emnlp colm aaai tmlr arxiv,
default arxiv), --main names the root file (default main.tex), --no-compile skips the build
when latexmk is unavailable or the PDF is already current.
| Check | What it catches |
|---|---|
| 0.1 compile | latexmk exit status. A failure stops the run: reviewing un-compilable source produces unreliable output. |
| 0.2 page count | Total pages against the venue cap. The cap counts body pages, so a pass still needs your eyes on where the references start. |
| 0.3 build log | Undefined citations and references fail. Overfull hboxes over 5pt fail; smaller ones and underfull boxes warn. |
| 0.4 placeholders | TODO, XXX, FIXME, TBD, [CITATION], lorem, and leftover \textcolor{red} from the previous review round. Commented-out lines are skipped. |
| 0.5 correspondence | Density of , which and respectively per file, the two constructions that force a reader to hold a long-range correspondence. Ranked, so you fix the worst file first. |
| 0.6 bib hygiene | Entries missing author, title, year, or venue; a year in the future, which usually means a hallucinated reference; an arXiv id parked in the title field. |
Exit status is 1 when any check fails, so it chains into a larger gate.
Reading the output
Report the checklist verbatim at the top of whatever you write next: each line is already
[PASS] / [WARN] / [FAIL] with the detail attached. Fix every FAIL before drafting prose about
the paper. A WARN is a judgment call: a file with twelve respectively is worth a rewrite pass, a
file with one is not.
The script reads the tree and the build products. It never edits the paper.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 38 lines · 111 tokens per session scan A cc81aed51b71
preflight is a skill published in the GitHub repository wenhaochai/claude-plugins (17 stars, last pushed 2d ago), licensed MIT. It adds 111 tokens to every session and 634 once invoked, about $0.0004 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 2026-09-17.
Other skills, from other repositories
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
meta-web-to-pdf-briefing
Render a topic into a distributable PDF briefing in three steps: web search → bullet summary → styled PDF. Trigger when the user asks for a PDF briefing on a single topic.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
paper-reader
A reading assistant for computer-vision and deep-learning research papers. It can work with PDF files, arXiv papers, and papers stored in Zotero, a reference-management app.