Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mishahanin/heading-osnpx agentmods add skills/mishahanin/heading-os/docparseWrote 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/mishahanin/heading-os/docparse)<a href="https://agentmods.dev/skills/mishahanin/heading-os/docparse"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/docparse/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/mishahanin/heading-os/docparse"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/docparse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 13 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00135 | $0.01836 |
| Opus 5.5 | $0.00054 | $0.00734 |
| Sonnet 5.5 | $0.00027 | $0.00367 |
| Haiku 4.5 | $0.00014 | $0.00184 |
Grade A, and why
docparse 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- docparse — 97% identical, 21 lines differ
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DocParse - Document Parsing with Visual Citations
Parse documents and answer questions with spatially-grounded visual citations. Every cited fact is traced to an exact location on the source page.
Variables
$ARGUMENTS- file path(s) or directory, optional question in quotes- Examples:
/docparse work/deliverable/datastore/corporate/presentations/deck.pdf/docparse inbound/document/datastore/books/ "What are the key principles?"/docparse report.pdf --report
Phase 0 - Setup & Context
-
Run prerequisite check:
python scripts/docparse.py setup --checkIf any check fails, print the install instructions and STOP.
-
Parse
$ARGUMENTS:- Extract file path(s) or directory
- Extract optional question (quoted string)
- Check for
--reportflag or if user explicitly asks for "visual citations" / "visual report" - Check for
--pagesspecification (e.g.,--pages 1-10)
-
If a directory was given, discover supported files:
# Use Glob to find PDFs, DOCX, PPTX, XLSX in the directory -
For documents over 50 pages, ask the user which page range to parse. Never parse 100+ pages without an explicit
--pagesrestriction.
Phase 1 - Parse
Run the parser:
python scripts/docparse.py parse \
--files "<file1>" "<file2>" \
[--pages "1-10"] \
[--dpi 150] \
--output-json /tmp/docparse_parsed.json
Read the output JSON and present a summary:
- Number of files and pages parsed
- Cache hits vs fresh parses
- Total text items extracted
Phase 2 - Analysis
If the user asked a question:
-
Read
/tmp/docparse_parsed.jsonfocusing on each page'stextfield. Do NOT read rawtext_itemsarrays - those are for the bounding box engine only. -
Analyze the text to answer the question. Identify specific passages that support the answer.
-
For each cited passage, extract an exact verbatim quote from the parsed text:
- Character-for-character exact (this is critical for bounding box lookup)
- Prefer short quotes under 60 characters
- Quote evidence (numbers, data values, key phrases), not just labels
- Include 5-15 citations per answer
What ships with it
2 files 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 Changed · +6 lines d9933c8c0678
- 1mo ago Changed 3fd1795d637e
- 1mo ago Changed · +1 lines 03a11e9bf8c9
- 1mo ago Changed · +4 lines 60993ec5ebc5
- 2mo ago First seen · 200 lines · 135 tokens per session scan A 6e598c7f6b0d
docparse is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 135 tokens to every session and 1,836 once invoked, about $0.0005 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 files: create, read, merge, fill, OCR, edit text.
pdf-text-replace
Replace text in fillable PDF forms by updating form field values. This skill should be used when users need to update names, addresses, dates, or other text in PDF form fields.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…
tageszeitung
Creates a personalised daily newspaper from RSS feeds and web sources. Ported from the BACH news system (news.py + newspapergenerator.py). Own SQLite store (no Origin-DB). feedparser optional — XML fallback via stdlib. PDF export via Edge Headless (msedge.exe).
Process PDF files - extract text, create PDFs, merge documents. Use when user asks to read PDF, create PDF, or work with PDF files.
nano-pdf
Edit PDF text/typos/titles via nano-pdf CLI (NL prompts).