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 artivilla/agents-config --skill paper-mcpgit clone --depth 1 https://github.com/artivilla/agents-configWrote 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/artivilla/agents-config/paper-mcp)<a href="https://agentmods.dev/skills/artivilla/agents-config/paper-mcp"><img src="https://agentmods.dev/badge/skills/artivilla/agents-config/paper-mcp/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/artivilla/agents-config/paper-mcp"><img src="https://agentmods.dev/badge/skills/artivilla/agents-config/paper-mcp.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 | $0.00072 | $0.00547 |
| Opus 5 | $0.00036 | $0.00273 |
| Sonnet 5 | $0.00014 | $0.00109 |
| Haiku 4.5 | $0.00007 | $0.00055 |
Grade A, and why
paper-mcp 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 10d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper MCP
Use the Paper MCP server for paper-driven research and implementation tasks. For setup and debugging details (env vars, config, verification), see references/paper-mcp-config.md.
Paper MCP integration rules
These rules define how to translate paper inputs into reliable outputs and must be followed for every paper-driven change.
Required flow (do not skip)
- Resolve the paper first (URL/DOI/arXiv/PMID) and fetch high-level metadata before requesting full text.
- If the full response is large or truncated, fetch section-level context and work section-by-section.
- Fetch a stable citation list before drafting any claims that depend on references.
- If figures/tables are relevant, fetch those assets and capture captions prior to synthesis.
- Only after metadata plus content context are collected, generate the user output (summary/table/notes/code-facing plan).
- Validate all key claims against source excerpts before marking complete.
Tool mapping rule
- Paper MCP deployments may expose different tool names.
- Start by listing available paper MCP tools, then map this workflow to equivalent tools in the current server.
- If a required capability is missing (for example, no section fetch or no citation endpoint), note the limitation and continue with the best available fallback.
Implementation rules
- Treat paper MCP responses as source context, not final prose.
- Keep outputs traceable: tie each important claim to a section, figure, or citation.
- Distinguish evidence from inference clearly.
- Preserve units, metrics, and dataset/task names exactly as written in source context.
- Prefer concise structured output (tables/checklists) when comparing multiple papers.
- For code-facing tasks, extract actionable constraints (input shapes, evaluation metrics, baseline numbers, reproducibility requirements).
Quality rules
- Do not invent citations, metrics, or section names.
- Call out uncertainty when context is partial, truncated, or conflicting.
- If two sources disagree, present both with scope and date/context differences.
- Keep quoted text short and use paraphrasing for long passages.
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.
- 10d ago First seen · 43 lines · 72 tokens per session scan A 2fba7ec1459d
paper-mcp is a skill published in the GitHub repository artivilla/agents-config (0 stars, last pushed 3mo ago), licensed MIT. It adds 72 tokens to every session and 547 once invoked, about $0.0004 per session on Opus 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
astro-dso-doc
Generates a complete, polished HTML documentation page, a processing checklist, an AstroBin post JSON, a PixInsight process icon set (XPSM), AND a ready-to-paste PixInsight project Description field for a deep-sky object (DSO) astrophotography project. Use this skill whenever the user mentions astrophotography, a DSO…
collect-preserve-specimens
Collect and preserve insect specimens following museum-grade standards including legal compliance, collection methods, humane dispatch, dry pinning, wet preservation, labeling, storage, and curation. Covers permit requirements, protected species regulations, sweep nets, beating trays, pitfall traps, light traps…
analyze-diffusion-dynamics
Analyze the dynamics of diffusion processes using stochastic differential equations, Fokker-Planck equations, first-passage time distributions, and parameter sensitivity analysis. Use when deriving probability density evolution for a continuous-time diffusion process, computing mean first-passage times for bounded…
analyze-tensegrity-system
Analyze a tensegrity system by identifying compression struts and tension cables, classifying type (class 1/2, biological/architectural), computing prestress equilibrium, verifying stability via Maxwell's rigidity criterion, and mapping biological tensegrity (microtubules, actin, intermediate filaments). Use when…
assess-holistic-health
Conduct temperament-based health assessment from Hildegard von Bingen's Causae et Curae. Evaluates the four temperaments (sanguine, choleric, melancholic, phlegmatic), elemental correspondences (air, fire, earth, water), and provides dietary and lifestyle recommendations for rebalancing. Use when understanding…
consult-natural-history
Reference Hildegard von Bingen's Physica natural history knowledge. Covers classification of plants, stones, animals, fish, birds, elements, and trees with their medicinal, symbolic, and practical properties. Enables cross- referencing between categories and application guidance. Use when exploring a specific plant…