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.
npx skills add flyfish-dev/file-ai --skill ai-document-enginegit clone --depth 1 https://github.com/flyfish-dev/file-aiWrote 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/flyfish-dev/file-ai/ai-document-engine)<a href="https://agentmods.dev/skills/flyfish-dev/file-ai/ai-document-engine"><img src="https://agentmods.dev/badge/skills/flyfish-dev/file-ai/ai-document-engine/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/flyfish-dev/file-ai/ai-document-engine"><img src="https://agentmods.dev/badge/skills/flyfish-dev/file-ai/ai-document-engine.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 | $0.00081 | $0.00624 |
| Opus 5.5 | $0.00032 | $0.00250 |
| Sonnet 5.5 | $0.00016 | $0.00125 |
| Haiku 4.5 | $0.00008 | $0.00062 |
Grade A, and why
ai-document-engine 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.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Document Engine
Use the File AI MCP tools as the source of truth for document content. Do not manually unzip Office files, inspect PDF internals, or infer spreadsheet structure when these tools are available.
File AI format recognition follows the Flyfish File Viewer core registry. Treat profile.format as the authoritative format decision and profile.extraction as the current content-awareness strategy for that format.
Core Workflow
- Call
doc_analyzewith the local file path before answering content questions. - Use
profile.indexIdfor all later calls in the same task. - Use
doc_contextwhen the user asks about a topic, section, page, slide, sheet, or nearby content. - Use
doc_searchfor exact terms, entities, clauses, headings, table labels, filenames inside archives, or attachment names. - Use
doc_readfor a specificanchorId,blockId, orchunkIdreturned by the engine. - Cite or mention the relevant
anchorIdvalues in answers when making document-grounded claims.
Tool Rules
- Prefer
doc_contextover reading all chunks when the user asks a focused question. - Prefer
doc_searchbefore broad summarization if the user provides keywords or entity names. - Use
doc://{indexId}/profile,doc://{indexId}/outline, anddoc://{indexId}/chunksresources only afterdoc_analyzehas cached the document. - Treat warnings in
profile.warningsas part of the evidence, especially scanned PDFs, clipped sheets, unsupported formats, or best-effort fallback text. - Use
doc_list_formatswhen choosing whether a file extension is recognized by File Viewer; do not infer supported formats from extractor names alone. - If
profile.format.knownis true butprofile.extraction.structuredis false, say the file is recognized by File Viewer but File AI only has metadata or best-effort text for that renderer-only format. - For spreadsheets, keep sheet names and row context in the answer when available.
- For presentations, keep slide numbers in the answer when available.
- For PDFs, keep page numbers in the answer when available.
- For archives, report manifest entries and nested paths; do not extract or mutate archive entries unless another explicit tool supports it.
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 · 37 lines · 81 tokens per session scan A e8ca855e8598
ai-document-engine is a skill published in the GitHub repository flyfish-dev/file-ai (3 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 624 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
excel-cli
Discover and launch the Excel CLI for ordinary Excel workbook requests on Windows, including reads, writes, formulas, data refreshes, and workbook automation. Use the installed excel-cli plugin's npx launcher and native help to find commands; report presentation conventions are a separate optional skill.
document-processing
Use when the deliverable is a document's bytes or its literal content — text/tables out of PDFs, AcroForm fill and flatten, page merge/split, PDF/DOCX from templates, OCR of image-only scans. NOT schema-typed fields pulled from text (that is structured-extraction), NOT signature routing (e-signature) or spreadsheet…
excel-cli-report-formatting
Apply optional presentation conventions when the user requests Excel report formatting or a new reader-facing report through excelcli. Use for readable headers, meaningful number formats, financial-model colours, and report layout. Do not load for ordinary reads, raw exports, targeted data updates, Power Query or Data…
excel-mcp-report-formatting
Apply optional presentation conventions when the user requests Excel report formatting or a new reader-facing report through Excel MCP tools. Use for readable headers, meaningful number formats, financial-model colours, and report layout. Do not load for ordinary reads, raw exports, targeted data updates, Power Query…
document-management
Handle ServiceNow attachments from both sides — the six /api/now/attachment tools that move file bytes in and out of the agent, and GlideSysAttachment for copying between records — plus document generation from sysreporttemplate, PDFs, dmsdocument versioning, and attachment access checks.
kernelcad-drawings
Export 2D engineering-drawing sheets (SVG, or a printable PDF on a standard sheet) from any model or assembly — third-angle front/top/left + isometric views with hidden-line removal, overall dimensions, and a title block. Use when the deliverable is a human-readable fabrication or review drawing.