agentmods.dev

academic-full-text

academic-full-text is a skill for Claude Code, Codex from agentlas-ai/agentlas-desktop. It costs 35 tokens per session (411 once invoked), scanned A, original, Apache-2.0.

A tool for retrieving the full text of an open-access research article identified by its DOI or PMID. DOI and PMID are standard identifiers for scholarly papers; the article is taken from Europe PMC and parsed into exact, reusable text.

In plain words
What is it for?
Use it after an academic search to fetch a specific article, create a verified text source, and cite exact passages in later research.
Why use it?
It preserves the original retrieval details and exact text so later claims can be checked against a stable source. It also makes clear when an article cannot be verified through the required open-access collection.

Skill for Claude CodeCodex

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

not rated 6repo changed 29d ago A scan 35 tokens original Apache-2.0

Good fit Use it after an academic search to fetch a specific article, create a verified text source, and cite exact passages in later research.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agentlas-ai/agentlas-desktop/full-text
View source ↗ agentlas-ai/agentlas-desktop agentlas.cloud
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 agentlas-ai/agentlas-desktop --skill full-text
Clone the repo
git clone --depth 1 https://github.com/agentlas-ai/agentlas-desktop

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 academic-full-text

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/full-text/github.svg)](https://agentmods.dev/skills/agentlas-ai/agentlas-desktop/full-text)
Your own site
<a href="https://agentmods.dev/skills/agentlas-ai/agentlas-desktop/full-text"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/full-text/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 academic-full-text

Your own site · 80×15
<a href="https://agentmods.dev/skills/agentlas-ai/agentlas-desktop/full-text"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/full-text.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 411 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 $0.00035 $0.00411
Opus 5.5 $0.00014 $0.00164
Sonnet 5.5 $0.00007 $0.00082
Haiku 4.5 $0.00003 $0.00041

Measured 29d ago against content hash 74dafe54aab6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

academic-full-text 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 29d 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/agentlas-academic-search/skills/full-text/SKILL.md · 21 lines

What it actually says

Retrieve Open Access Full Text

  1. Start from an exact sourceId and current sourceVersionId returned by search_academic_literature; do not reconstruct an identity from a title.
  2. First call retrieve_open_access_full_text with those exact IDs when the source is DOI- or PMID-identified and the Europe PMC Open Access route is applicable.
  3. If that route reports not-open-access, or the research already has a lawful public article PDF/HTML URL or a PDF/HTML/text file inside the project folder, call retrieve_source_full_text_from_location with the same exact IDs and exactly one of url or file_path. The URL must be a public HTTPS article location; the file must be inside the project folder. Do not invent a location or bypass an access boundary.
  4. Inspect the route-specific receipt, raw and parsed byte sizes/hashes, and parsed SourceVersion ID. For the Europe PMC route, also inspect PMCID, license, and metadata/full-text response hashes.
  5. Use only the returned parsed SourceVersion for later evidence spans. Cite exact UTF-8 byte ranges and preserve the distinction between retrieved bytes and deterministic parsed text.
  6. If no lawful full-text route succeeds, the identity differs, the source version is stale, or parsing fails, leave the source body unverified. You may promote a persisted abstract only for explicitly abstract-only claims; do not treat it as full text.

Verification

  • evidenceScope must be full-text.
  • The raw XML hash, parsed text hash, ResearchRun outputs, and current SourceVersion hash must agree.
  • The SourceVersion access state must be parsed before staging or recording evidence.
  • A successful replay must perform no new network request and return the same run and SourceVersion.
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. 29d ago Changed · +1 lines · -3 tokens per session 74dafe54aab6
  2. 1mo ago First seen · 20 lines · 38 tokens per session scan A 09a6539e80ae

Subscribe to this mod's changes

academic-full-text is a skill published in the GitHub repository agentlas-ai/agentlas-desktop (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 35 tokens to every session and 411 once invoked, about $0.0001 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 2026-09-04.

ResearchScientificagentlasai-agentselectronmacosmcp
Related

Other skills, from other repositories

tbtools

Use when the user asks about TBtools, TBtools-II, TBtools RPC API, TBtools CLI, or bioinformatics operations available through TBtools such as sequence manipulation, BLAST, GFF/GTF/GXF processing, expression tables, heatmaps, trees, MCScanX, DIAMOND, HMMER, MUSCLE, and IQ-TREE.

xuzhougeng/wispterm · 77 tokens

electron-expert

Expert in Electron framework, desktop app development, IPC, and cross-platform packaging. Use when the user mentions desktop, Node.js, cross platform, Windows, macOS, or Linux, or when the task involves Electron Architecture, Process Types, IPC Communication, or App Lifecycle.

personamanagmentlayer/pcl · 59 tokens

research-orchestrator

Becomes a principal research scientist who orchestrates deep, multi-source research by coordinating evidence gathering, grading source quality, and synthesizing findings with explicit confidence levels. Use when the user needs a comprehensive research report on a complex topic, evidence-based analysis with source…

FerroxLabs/wayland · 109 tokens

autoresearch

Run an auto research / autoresearch loop for measurable improvements. Use when optimizing a skill, agent, prompt, code path, benchmark, or other target with a mechanical metric: baseline, mutate one thing, verify, keep or discard, log, chart progress, and optionally save improved custom skills or agents through Open…

joe-broadhead/open-cowork · 0 tokens

architecture-diagram

How to draw and maintain the architecture diagram Ensemblr keeps for a workspace — ensemblrgetarchitecturediagram to fetch the stored one (it answers with null when nobody has drawn this workspace yet), the IR shape, how to derive it from the codebase, and ensemblrupdatearchitecturediagram to store it. Read this when…

ensemblr-hq/ensemblr · 94 tokens

scaffold-lean-library

Scaffold a Lean 4 library with Mathlib or PFR, Lake tests, and CI. Use for "new Lean project"; to edit Lean, use write-lean-code.

cboone/agent-harness-plugins · 43 tokens