papers

A workflow for downloading every cited paper, report, article, or book and saving a PDF plus a structured summary in the project's references/papers/ folder. Each summary includes a link to the original online source.

In plain words
What is it for?
Use it to collect research sources, record their main findings and takeaways, add tags, and maintain a traceable reference library for design documents, experiments, hypotheses, and research notes.
Why use it?
It prevents citations from pointing to sources that were never saved or explained. Online links keep the references usable when files move or another machine opens the project.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/stellarshenson/claude-code-plugins/papers
Any agent
npx skills add stellarshenson/claude-code-plugins --skill papers
Clone the repo
git clone --depth 1 https://github.com/stellarshenson/claude-code-plugins

Made for: Claude Code, Codex.

Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,760 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00129 $0.01760
Opus 5 $0.00064 $0.00880
Sonnet 5 $0.00026 $0.00352
Haiku 4.5 $0.00013 $0.00176

Measured 2d ago against content hash 257a361e50e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

papers 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 2d 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.

plugins/datascience/skills/papers/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Papers - reference and digest workflow

Every source cited in a project document (design docs, experiment registrations, hypothesis groundings, research notes) gets TWO artifacts in the project's references/papers/ directory. A cited source that is not downloaded and digested is a defect - no citation without both.

  • [paper] <short name>, <year>.pdf - the downloaded PDF
  • [paper digest] <short name>.md - the structured digest

<short name> is a compact human-readable title (not the arXiv id), identical between the two files - e.g. [paper] automem memory as cognitive skill, 2026.pdf and [paper digest] automem memory as cognitive skill.md.

The digest's **Source** section carries the online provenance link: the actual downloadable or access URL for the original. Never a local filename, never a path.

  • A digest outlives its PDF - it is read, quoted, and grounded against on other machines, in other repos, after the local file has moved or gone. A local path resolves for exactly one reader; a URL resolves for every reader
  • Durability order: DOI URL (https://doi.org/<doi>) > arXiv abs page > publisher OA / PMC / OpenReview / ACL Anthology landing page > direct PDF URL. Prefer the landing page over a CDN link that rots
  • Verify the URL resolves before writing it - a fabricated or dead DOI is worse than no link
  • Paywalled - link the DOI anyway and add one line: - Access: paywalled; digest written from abstract and published summaries
  • Books - link the publisher page, DOI, or a stable catalogue record (worldcat, openlibrary); an ISBN alone is not a link
  • The PDF is still downloaded under the naming rule above; it simply never appears inside the digest

Getting the source

  • Prefer arXiv - https://arxiv.org/pdf/<id> serves the PDF directly; for other venues use the open-access PDF (OpenReview, ACL Anthology, PMLR, PMC, publisher OA)
  • Verify the download is a real PDF - check the %PDF magic header or file output, never trust the extension; an HTML error page saved as .pdf is a recurring failure
  • Paywalled with no open version - write the digest anyway from the abstract / public material and mark the access caveat; the digest is still mandatory
  • A research agent recommending a source returns a verified PDF URL plus digest-ready content in the format below, so the main session only downloads and saves

Read the full file on GitHub · 126 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 126 lines · 129 tokens per session scan A 257a361e50e7

Subscribe to this mod's changes

papers is a skill published in the GitHub repository stellarshenson/claude-code-plugins (3 stars, last pushed 2d ago), licensed MIT. It adds 129 tokens to every session and 1,760 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens