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 Meteora0720/Deepseek-Research-Harness --skill dsrh-paper-readergit clone --depth 1 https://github.com/Meteora0720/Deepseek-Research-HarnessWrote 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/meteora0720/deepseek-research-harness/dsrh-paper-reader)<a href="https://agentmods.dev/skills/meteora0720/deepseek-research-harness/dsrh-paper-reader"><img src="https://agentmods.dev/badge/skills/meteora0720/deepseek-research-harness/dsrh-paper-reader/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/meteora0720/deepseek-research-harness/dsrh-paper-reader"><img src="https://agentmods.dev/badge/skills/meteora0720/deepseek-research-harness/dsrh-paper-reader.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 | $0.00000 | $0.00341 |
| Opus 5 | $0.00000 | $0.00170 |
| Sonnet 5 | $0.00000 | $0.00068 |
| Haiku 4.5 | $0.00000 | $0.00034 |
Grade A, and why
dsrh-paper-reader 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 12d 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
DSRH PaperReader
Use this skill to analyze a born-digital research paper. Keep every important technical statement traceable to evidence returned by the DSRH paper tools.
Procedure
- Ingest the PDF with
mcp__dsrh-science__dsrh_paper_ingest. Do not claim success if the result reports degraded or metadata-only mode. - Inspect metadata and the section tree before reading. Read abstract, introduction, methods, experiments, ablations, results, limitations, and references when present.
- Search for the method name, datasets, baselines, metrics, training details, and limitation language. Retrieve exact evidence records for material claims.
- Inspect extracted figure and table metadata. Explain only what captions and nearby evidence support; do not infer unseen visual content.
- Build an evidence map before synthesis. Distinguish
Reported by authors,Author interpretation, andDSRH inferencein the report. - Report missing, ambiguous, malformed, or scan-only content explicitly. Never invent experiments, datasets, equations, metrics, ablations, or conclusions.
Output
Cover research problem, motivation, contributions, method, architecture, modules, equations, training, datasets, metrics, baselines, results, ablations, figures, limitations, reproducibility, follow-up opportunities, and an evidence map. Omit a section only when the paper lacks the information, and state that absence.
For core facts, cite evidence ids in brackets, for example [paper_ab12cd34:p006:s03:c014]. Use the policy and report schema in references/evidence-policy.md and references/paper-analysis-schema.md.
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.
- 12d ago First seen · 20 lines · 0 tokens per session scan A 557d7f2cf8eb
dsrh-paper-reader is a skill published in the GitHub repository Meteora0720/Deepseek-Research-Harness (3 stars, last pushed 28d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 341 tokens. 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
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
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.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.