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/darellchua2/opencode-config-templatenpx agentmods add skills/darellchua2/opencode-config-template/docling-mcp-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/skills/darellchua2/opencode-config-template/docling-mcp-skill)<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/docling-mcp-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/docling-mcp-skill/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/darellchua2/opencode-config-template/docling-mcp-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/docling-mcp-skill.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 | $0.00054 | $0.01395 |
| Opus 5.5 | $0.00022 | $0.00558 |
| Sonnet 5.5 | $0.00011 | $0.00279 |
| Haiku 4.5 | $0.00005 | $0.00139 |
Grade A, and why
docling-mcp-skill 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What this skill does
- Documents docling as a Tier 2 escalation engine for the AGENTS.md → Office Document Extraction Routing rule
- Provides the CLI-on-demand recipe (primary path — codegraph-init analog): detect, ask consent, install, convert, read
- Documents the optional persistent MCP tier via
--enable-pack docling - States the trust-boundary honestly: unlike markitdown (zero phone-home), docling downloads ML models from huggingface.co on first use
- Prescribes the consent policy: primary asks; headless/subagent soft-fails; never auto-install ~3-4 GB
Reference: docling on PyPI · docling-mcp on PyPI
When to use docling (Tier 2)
Follow the AGENTS.md → Office Document Extraction Routing rule — this skill does NOT re-derive the full markitdown/pdf-specialist tree. Docling is the escalation target when:
- markitdown returns empty/garbage (scanned PDFs, image-only)
- markitdown mangles complex tables (multi-column, merged cells, nested headers)
- markitdown drops layout that matters (multi-column text flow, footnotes, sidebars)
- The PDF needs OCR (docling's OCR pipeline handles scanned docs markitdown cannot)
Do NOT use docling for: plain text dumps of clean born-digital docs (markitdown is faster, lighter), visual understanding (image-analyzer-subagent), or structured form-field extraction (pdf-specialist-skill).
CLI-on-demand recipe (primary path)
This is the codegraph-init analog — docling is not installed by default (~3-4 GB with models). The agent detects absence, asks consent, installs, converts — all within the session, no restart.
1. DETECT: command -v docling >/dev/null 2>&1
2. ABSENT → ASK CONSENT (primary session only — see Consent Policy below)
3. INSTALL: pip install --user docling
4. CONVERT: docling convert <file> --to md -o <output-dir>
5. READ: Read the generated <output-dir>/<file>.md
Consent Policy
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 a54fb41bf14c
- 1mo ago Changed 14137dbb4ebd
- 1mo ago Changed 78e8cea887fd
- 2mo ago First seen · 101 lines · 54 tokens per session scan A 103d63df5cc5
docling-mcp-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,395 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 2026-09-03.
docling-mcp-skill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| docling-mcp-skilldarellchua2/opencode-config-template | Skill | 6 | 1mo ago | Apache-2.0 | A | 54 | Claude Code, Codex |
| processing-pdfstelagod/code-abyss | Skill | 244 | 3mo ago | MIT | A | 57 | Claude Code |
| rtl-persian-pdfmamahoos/dot-files | Skill | 5 | 3d ago | MIT | A | 60 | Claude Code, Cursor |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 48 | Claude Code |
| foundry-hosted-agent-validationmicrosoft/agent-framework | Skill | 15k | yesterday | MIT | A | 82 | Claude Code, Codex |
| skill-doc-deliverynyldn/claude-octopus | Skill | 4.4k | yesterday | MIT | A | 29 | Claude Code |
| meta-web-to-pdf-briefingopensquilla/opensquilla | Skill | 7.1k | 6d ago | Apache-2.0 | A | 45 | Claude Code, Codex |