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 X-T-E-R/nb-paper-search --skill paper-search-cligit clone --depth 1 https://github.com/X-T-E-R/nb-paper-searchWrote 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/x-t-e-r/nb-paper-search/paper-search-cli)<a href="https://agentmods.dev/skills/x-t-e-r/nb-paper-search/paper-search-cli"><img src="https://agentmods.dev/badge/skills/x-t-e-r/nb-paper-search/paper-search-cli/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/x-t-e-r/nb-paper-search/paper-search-cli"><img src="https://agentmods.dev/badge/skills/x-t-e-r/nb-paper-search/paper-search-cli.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 | $0.00164 | $0.01873 |
| Opus 5.5 | $0.00066 | $0.00749 |
| Sonnet 5.5 | $0.00033 | $0.00375 |
| Haiku 4.5 | $0.00016 | $0.00187 |
Grade A, and why
paper-search-cli 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.
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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NB Paper Search
Use this skill for the local paper-search-cli system, its canonical tools, and
its MCP server. The display name is NB Paper Search; that is not a breaking
rename of the paper-search command, skill slug, configuration keys, canonical
tools, or MCP identity.
Installed entrypoint
Run commands from this skill directory through its launcher:
node scripts/paper-search.mjs --version
node scripts/paper-search.mjs paths --json
node scripts/paper-search.mjs status --json
node scripts/paper-search.mjs tools --json
The installed skill is a Junction or symlink into a retained Paper Search
checkout. The launcher resolves that checkout and starts its verified runtime.
Do not bypass it with repository-relative node dist/cli.js during normal agent
use. The paper-search shim is the equivalent human entrypoint.
Activation boundary
Use this skill when the request concerns Paper Search, its provider packages, search/run history, citation expansion, transparent assessment, workspace/material records, its configured or explicit Zotero projection, its MCP server, or a canonical tool. Paper Search may write its own run record to a nearest-directory standalone or Paperflow context. Paperflow still owns project roles and the research runtime; selected bibliography/evidence records remain a separate project workflow.
The optional web_search tool exists only when the user-owned
external-search.toml grants External Search v1 process authority. Use normal
search/browser routing for general web work. Use a dedicated Zotero skill for
general Zotero library operations; use this skill for Paper Search's mapped
selected-item projection and explicit zotero sink handoff.
Eight capability groups
| Group | Use for |
|---|---|
discover |
Academic and patent search, plus optional External Search v1. |
identify |
DOI/PMID/arXiv/ISBN/URL metadata lookup and patent detail. |
assess |
Checksum-bound observation snapshots, conflicts, provenance, and optional explicit policy traces. |
acquire |
Provider-mediated artifact acquisition or recording, including resource_pdf compatibility. |
extract |
Markdown, structured output, and assets through material extractor providers. |
organize |
Local selected workspace add/list/export and Zotero projection. |
orchestrate |
Durable discovery, citation expansion, batch rows, material ingest, and material status. |
operate |
Paths, status, run inspection/pruning plans, config, provider management, help/tools, and MCP serving. |
What ships with it
5 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.
- 2mo ago First seen · 149 lines · 164 tokens per session scan A aa73be987d47
paper-search-cli is a skill published in the GitHub repository X-T-E-R/nb-paper-search (0 stars, last pushed 2mo ago), licensed MIT. It adds 164 tokens to every session and 1,873 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 2026-08-31.
paper-search-cli compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| paper-search-cliX-T-E-R/nb-paper-search | Skill | 0 | 2mo ago | MIT | A | 164 | Codex |
| browser-relayreliefeai/browser-relay | Skill | 138 | 1mo ago | MIT | A | 52 | Claude Code |
| mediagenCripacx/mediagen | Skill | 50 | 1mo ago | MIT | A | 84 | Claude Code, Codex |
| grok-botadamanz/grok-bot-skill | Skill | 17 | 2d ago | MIT | A | 95 | Claude Code, Codex |
| historyay-bh/chat-history | Skill | 13 | 10d ago | MIT | A | 92 | Claude Code, Codex |
| actualactual-software/actual-skill | Skill | 6 | 2d ago | Apache-2.0 | A | 157 | Claude Code |
| hyalo-skillsractive/hyalo | Skill | 28 | yesterday | MIT | A | 26 | Codex |