A research workflow for systematic literature reviews, which collect and assess published studies on a defined topic. It searches several academic databases, downloads open-access papers, and builds a searchable local collection.

Use it to gather papers for a thesis or related-work section, search across academic services, download available PDFs, explore citations, and produce a cited report.

It reduces the manual work of finding related papers, following citations, and keeping sources and citations verifiable.

ultrasearch — Skill for Claude Code by zevtos/agentpipe

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 zevtos/agentpipe --skill ultrasearch

Clone the repo

git clone --depth 1 https://github.com/zevtos/agentpipe

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zevtos/agentpipe/ultrasearch/github.svg)](https://agentmods.dev/skills/zevtos/agentpipe/ultrasearch)

Your own site

<a href="https://agentmods.dev/skills/zevtos/agentpipe/ultrasearch"><img src="https://agentmods.dev/badge/skills/zevtos/agentpipe/ultrasearch/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/zevtos/agentpipe/ultrasearch"><img src="https://agentmods.dev/badge/skills/zevtos/agentpipe/ultrasearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 183 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,403 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.

Model	Per session	Once invoked
Fable 5.1	$0.00183	$0.05403
Opus 5.5	$0.00073	$0.02161
Sonnet 5.5	$0.00037	$0.01081
Haiku 4.5	$0.00018	$0.00540

Measured 2mo ago against content hash 6a8f752a1fd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ultrasearch 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 2mo ago.

The scan reads SKILL.md. This mod also ships 35 executable files (scripts/_common.py, scripts/_profile.py, scripts/classifier.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/ultrasearch/SKILL.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ultrasearch — thesis-level literature research

⛔ Rules that override everything else

NEVER fabricate DOIs or citations. Every DOI in the final report MUST exist in papers.doi of corpus.db. A regex-validated check is in the Checklist section; run it before delivering output.
NEVER skip the env-var pre-flight. OPENALEX_API_KEY and UNPAYWALL_EMAIL are not optional. Failing fast on missing env vars is correct behavior, not a bug.
NEVER bypass the venv. Every script is invoked through ensure_env.py, which resolves the skill's venv (a global state dir outside the code — ADR-008). Calling extract/index scripts with system python3 will fail — sentence-transformers, pymupdf4llm, and sqlite-vec live only in that venv.
NEVER deliver a report whose paragraphs lack [Sn] citation markers. synthesize.validate_report() returns the offenders — fix or remove them.
NEVER delete corpus.db. It is user content (ADR-008), stored in a global state dir outside the code; reinstall never touches it. If the user explicitly asks to reset, resolve the path as in Persistent corpus and rm "$DB"*.

Required environment variables

export OPENALEX_API_KEY="..."    # free key — https://openalex.org/account
export OPENALEX_EMAIL="[email protected]"   # polite-pool identifier
export UNPAYWALL_EMAIL="[email protected]"  # mandatory for Tier 2 fetch
export S2_API_KEY="..."           # optional — dedicated 1 RPS pool
# Stage 2 additions:
export CORE_API_KEY="..."         # optional — enables CORE source (5 of 6 work without)
export ZOTERO_API_KEY="..."       # optional — enables --export-zotero remote push
export ZOTERO_USER_ID="..."       # required if ZOTERO_API_KEY set

Var	Required?	What breaks without it
`OPENALEX_API_KEY`	YES (post 13 Feb 2026)	OpenAlex returns 401 for new users
`OPENALEX_EMAIL`	Recommended	drops to anonymous quota
`UNPAYWALL_EMAIL`	YES	Tier 2 (Unpaywall PDF lookup) skipped; cascade loses ~30% recall
`S2_API_KEY`	Optional	shares anonymous 5000/5min bucket; traversal hits it harder
`CORE_API_KEY`	Optional (Stage 2)	CORE source disabled; other 5 sources cover
`ZOTERO_API_KEY`	Optional (Stage 2)	`--export-zotero` writes `.bib` only, no remote push
`ZOTERO_USER_ID`	Required if ZOTERO_API_KEY set	API push fails fast

Read the full file on GitHub · 327 lines

Files

What ships with it

59 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.

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.

2mo ago First seen · 327 lines · 183 tokens per session scan A 6a8f752a1fd7

Subscribe to this mod's changes

ultrasearch is a skill published in the GitHub repository zevtos/agentpipe (10 stars, last pushed 3d ago), licensed MIT. It adds 183 tokens to every session and 5,403 once invoked, about $0.0007 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 2026-08-30.

Research Scientific

ultrasearch next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ultrasearchzevtos/agentpipe	Skill	10	3d ago	MIT	A	183	Claude Code
instrument-data-to-allotropeanthropics/knowledge-work-plugins	Skill	35k	2d ago	Apache-2.0	A	123	Claude Code
exploratory-data-analysisK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	83	Claude Code
matlabK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	44	Claude Code
phylogeneticsK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	71	Claude Code, Codex
research-engineerdavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	43	Claude Code, Codex
mapping-to-snomedmaziyarpanahi/openmed	Skill	5.8k	yesterday	Apache-2.0	A	205	Claude Code