agentmods.dev

lacuna-code-to-paper

lacuna-code-to-paper is a skill for Claude Code, Codex from tiptreesystems/lacuna-research-mcp. It costs 53 tokens per session (441 once invoked), scanned A, original, MIT.

A research lookup workflow that links a machine-learning code repository, dataset, or model to its associated research papers. It checks the resource's identity and recorded relationship before attributing a paper.

In plain words
What is it for?
Use it to find which papers an implementation comes from, understand how code relates to a paper, or decide what research to read before changing it.
Why use it?
It helps avoid citing the wrong paper based only on a README mention, a similar name, or an old repository address. It also distinguishes recorded evidence from unsupported assumptions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 57repo +15 yesterday A scan 53 tokens original MIT

Good fit Use it to find which papers an implementation comes from, understand how code relates to a paper, or decide what research to read before changing it.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tiptreesystems/lacuna-research-mcp/lacuna-code-to-paper
View source ↗ tiptreesystems/lacuna-research-mcp lacuna.tiptreesystems.com
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.

Any agent
npx skills add tiptreesystems/lacuna-research-mcp --skill lacuna-code-to-paper
Clone the repo
git clone --depth 1 https://github.com/tiptreesystems/lacuna-research-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for lacuna-code-to-paper

README.md
[![agentmods](https://agentmods.dev/badge/skills/tiptreesystems/lacuna-research-mcp/lacuna-code-to-paper/github.svg)](https://agentmods.dev/skills/tiptreesystems/lacuna-research-mcp/lacuna-code-to-paper)
Your own site
<a href="https://agentmods.dev/skills/tiptreesystems/lacuna-research-mcp/lacuna-code-to-paper"><img src="https://agentmods.dev/badge/skills/tiptreesystems/lacuna-research-mcp/lacuna-code-to-paper/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.

agentmods 80×15 button for lacuna-code-to-paper

Your own site · 80×15
<a href="https://agentmods.dev/skills/tiptreesystems/lacuna-research-mcp/lacuna-code-to-paper"><img src="https://agentmods.dev/badge/skills/tiptreesystems/lacuna-research-mcp/lacuna-code-to-paper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 441 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00053 $0.00441
Opus 5.5 $0.00021 $0.00176
Sonnet 5.5 $0.00011 $0.00088
Haiku 4.5 $0.00005 $0.00044

Measured 3d ago against content hash 1707e5daddd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lacuna-code-to-paper 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 3d 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.

skills/lacuna-code-to-paper/SKILL.md · 36 lines

What it actually says

Trace code to papers

If Lacuna tools are unavailable, point to the setup instructions and stop the Lacuna lookup.

  1. Identify the resource from the user's URL or local README and dependency metadata. Query public resource names only; do not send private code or URLs.
  2. Use search_lacuna with search_type="resource" and the matching resource_kind: "codebase" for repositories, "dataset" for datasets, or "model" for models. Match the returned provider, key, title, and URL to the intended resource; rank and stars do not establish identity. Renames can leave old provider keys, so verify aliases against recorded URLs or the original repository. If no candidate matches, retry once without resource_kind, keeping search_type="resource" and the same identity checks. If no match is established or several remain plausible, show the candidates and stop before attributing papers.
  3. Use get_resource to inspect publications, relationship labels, evidence_url, any recorded basis, and the collection timestamp. A README mention is not a recorded official_code_for relationship; other labels may describe different connections.
  4. Follow relevant paper_id values with get_paper. Check original sources before making implementation claims, and distinguish the original paper from follow-ups.

Return the resource, relevant papers, relationship labels, recorded basis, and evidence links. Distinguish recorded relationships from independently verified connections or inferences. If no publication link is recorded, say so; separate paper-search results are candidates until verified. Search counts and detail collections can differ; neither establishes complete coverage.

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. 3d ago First seen · 36 lines · 53 tokens per session scan A 1707e5daddd3

Subscribe to this mod's changes

lacuna-code-to-paper is a skill published in the GitHub repository tiptreesystems/lacuna-research-mcp (57 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 441 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 2026-11-03.

ResearchScientificai-agentsknowledge-graphliterature-searchmachine-learningmcpmcp-server
Related

lacuna-code-to-paper compared with skills from other repositories

lacuna-code-to-paper next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
lacuna-code-to-papertiptreesystems/lacuna-research-mcpSkill57yesterdayMITA53Claude Code, Codex
prismdbcls/togomcpSkill212d agoMITA209Claude Code, Codex
disease-analysisdbcls/togomcpSkill212d agoMITA149Claude Code, Codex
research-article-analysisdbcls/togomcpSkill212d agoMITA147Claude Code, Codex
query-provenancedbcls/togomcpSkill212d agoMITA188Claude Code, Codex
ml_inference_optimizationLeeroo-AI/leeroopedia-mcpSkill141mo agoMITA0Claude Code, Codex
leeroopedia-mcpLeeroo-AI/leeroopedia-mcpSkill141mo agoMITA42Claude Code, Codex