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 sandbaseai/sandbase-skills --skill document-parsergit clone --depth 1 https://github.com/sandbaseai/sandbase-skillsWrote 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/sandbaseai/sandbase-skills/document-parser)<a href="https://agentmods.dev/skills/sandbaseai/sandbase-skills/document-parser"><img src="https://agentmods.dev/badge/skills/sandbaseai/sandbase-skills/document-parser/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/sandbaseai/sandbase-skills/document-parser"><img src="https://agentmods.dev/badge/skills/sandbaseai/sandbase-skills/document-parser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00041 | $0.00433 |
| Opus 5.5 | $0.00016 | $0.00173 |
| Sonnet 5.5 | $0.00008 | $0.00087 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
document-parser 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 29d 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
Document Parser
Parse and extract structured content from PDFs, Word documents, and other file formats. Converts documents into clean, machine-readable text for analysis, summarization, data extraction, and content processing workflows. Read the API map before selecting a capability.
Call SandBase capabilities
Use the capability identifiers below as discovery hints, not MCP tool names. Find the matching endpoint with sandbase_discover(q: "<provider and capability>"); use its returned name in sandbase_inspect(name: "<returned name>"). Read inputSchema, pricing, and execute_as, then call sandbase_run using execute_as.arguments.name and schema-defined arguments. If a run_id is returned, poll sandbase_run_get(run_id: "<returned run_id>") within the task budget until completed or failed; report pending or failed runs without resubmitting them automatically.
Capability identifiers
agentbody_document_parse
Workflow
- Understand the user's research question, target, and context.
- Resolve each selected capability with
sandbase_discover, then inspect the returnednamewithsandbase_inspectto confirm the schema and pricing. - Follow
execute_aswithsandbase_run; collect async results withsandbase_run_getas described above. - Synthesize findings into a clear, evidence-backed answer.
- Cite sources, note evidence gaps, and separate observations from interpretations.
Guidelines
- Always call
sandbase_inspectbefore using any capability. - Cite sources and preserve attribution (URLs, usernames, dates, metrics).
- Separate factual observations from analysis and recommendations.
- If data is unavailable, note the gap and continue with available evidence.
- Read-only research only. Never take actions on platforms.
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.
- 29d ago Changed 7025f49fd312
- 1mo ago First seen · 33 lines · 41 tokens per session scan A 2ee9da6cb827
document-parser is a skill published in the GitHub repository sandbaseai/sandbase-skills (203 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 433 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
pdf-toolkit
A command-line toolkit for working with local PDF files, which are fixed-layout documents. It can merge files, split or extract pages, read text, and show page information using available tools or Python’s pypdf library.
office-transform
Extract or edit a selection from xlsx, docx, pdf, or pptx into a new file; the source is never modified.
export-book
A preflight and export workflow for a finished manuscript. Preflight checks the book before creating a backup or delivery file such as an EPUB, a common ebook format.
office-export-pdf
Convert an Office document to a requested PDF with LibreOffice Kit.
download-fulltext-pdf
A skill for downloading a research paper's complete PDF using an identifier such as a DOI, title, or BibTeX entry.
write-docs-cn
A guide to writing project documentation, especially README files. It explains how tutorials differ from reference material and where each kind of information belongs.