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 CodeAlive-AI/ai-driven-development --skill semantic-scholar-deepgit clone --depth 1 https://github.com/CodeAlive-AI/ai-driven-developmentWrote 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/codealive-ai/ai-driven-development/semantic-scholar-deep)<a href="https://agentmods.dev/skills/codealive-ai/ai-driven-development/semantic-scholar-deep"><img src="https://agentmods.dev/badge/skills/codealive-ai/ai-driven-development/semantic-scholar-deep/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/codealive-ai/ai-driven-development/semantic-scholar-deep"><img src="https://agentmods.dev/badge/skills/codealive-ai/ai-driven-development/semantic-scholar-deep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 37 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
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 | $0.00163 | $0.02266 |
| Opus 5.5 | $0.00065 | $0.00906 |
| Sonnet 5.5 | $0.00033 | $0.00453 |
| Haiku 4.5 | $0.00016 | $0.00227 |
Grade A, and why
semantic-scholar-deep 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 1mo 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Scholar — Deep Research
Purpose: fill the gaps that semantic-scholar-lookup (allenai) leaves — references, recommendations, batch, and multi-hop citation-graph traversal.
Contents
- Dispatch Rule — inline vs delegate; model selection
- When to Use — trigger scenarios
- Scripts —
ss_client.py+citation_graph.py - Authentication & Rate Limits
- Progressive Disclosure — deeper references
- Output Hygiene
- Integration — typical pipeline with the subagent
Dispatch Rule (read first)
Two execution modes:
Inline (run the Bash scripts yourself)
Use when the user asks for one specific endpoint:
- "get references of paper X" →
ss_client.py references <id> - "recommendations for paper Y" →
ss_client.py recommendations <id> - "batch-resolve these 30 DOIs" →
ss_client.py batch ... - "find the snippet where X is said" →
ss_client.py snippets "..."
Fast, cheap, no orchestration overhead.
Delegate to deep-paper-researcher subagent
Use when the task is multi-step or would otherwise flood the context:
- Literature review on a topic
- Citation graph / network analysis around a seed paper
- Novelty check for an idea
- State-of-the-art survey
- Anything that requires merging Exa discovery + S2 graph + ranking
Mandatory prompt contents. The subagent runs in isolated context with no access to this conversation's system reminders. Include exactly these two things:
- Today's date — inline as
Today is YYYY-MM-DD.Pull from thecurrentDatesystem-reminder field, or rundate -Ivia Bash before delegating if it's missing. Never rely on training-data intuitions about the current year. - User's request, verbatim — pass the user's original phrasing (topic + any freshness words like "современные / recent / классические / seminal" and any explicit dates like "since 2024"). Translate language if needed but do not paraphrase trigger words into date windows.
What ships with it
6 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.
- 1mo ago First seen · 170 lines · 163 tokens per session scan A 531b8edcd8d5
semantic-scholar-deep is a skill published in the GitHub repository CodeAlive-AI/ai-driven-development (165 stars, last pushed 4d ago), licensed MIT. It adds 163 tokens to every session and 2,266 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.
Other skills, from other repositories
nature-downloader
Use when a user needs lawful academic full text, CNKI institutional access, English OA retrieval, publisher API access, institutional browser fallback, or supporting information downloads.
deep-research
Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 8 modes: full research, quick brief, paper review, lit-review, fact-check, three-way literature scan, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question…
nature-ref-verifier
A reference-checking workflow for academic papers, proposals, and BibTeX files. It compares citation details such as authors, titles, dates, pages, and DOIs across available sources.
nature-experiment-log
A system for turning raw experiment material—images, voice transcripts, or text—into standardised experiment logs with YAML metadata in an Obsidian vault. Obsidian is a note-taking application that stores linked files as plain text.
researchwrite
Proposal-first scientific writing pipeline. Three modes (compose/revise/hybrid) with four-layer QA pipeline. Enforces evidence-before-prose, argument-before-sections, and contracts-before-paragraphs.
nature-reviewer
A reviewer-style assessment guide for Nature submissions. It evaluates a manuscript from a referee's perspective, including originality, importance, technical soundness, and readability for non-specialists.