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 pantheon-org/tekhne --skill google-scholar-searchgit clone --depth 1 https://github.com/pantheon-org/tekhneWrote 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/pantheon-org/tekhne/google-scholar-search)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/google-scholar-search"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/google-scholar-search/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/pantheon-org/tekhne/google-scholar-search"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/google-scholar-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, 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 Excessive Agency · line 32 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 120 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 128 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00073 | $0.01382 |
| Opus 5 | $0.00036 | $0.00691 |
| Sonnet 5 | $0.00015 | $0.00276 |
| Haiku 4.5 | $0.00007 | $0.00138 |
Grade A, and why
google-scholar-search 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 9d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Scholar Search
Search Google Scholar for academic papers and author profiles to build a candidate list before triaging.
When to Use
- Discovering papers on a topic before running
triage-paper - Finding papers by a specific author, optionally filtered by year range
- Scoping a research area and exporting a candidate list to JSON for batch review
When Not to Use
- The paper is already known (arxiv ID, DOI, URL) — go straight to
triage-paper - The
semantic-scholarMCP is configured — optionally prefer it; it returns structured data with no rate-limit risk - The search is for biomedical literature — use PubMed or a domain-specific source
- A candidate JSON already exists at
/tmp/<topic>-candidates.json— reuse it rather than re-running
Mindset
Search is discovery, not triage. The goal is a candidate list, not a finished reference.
- Return candidates, not conclusions: hand the list to the user; let them choose what to triage.
- Scraping is fragile: a gotcha is that a blank result may be a silent CAPTCHA redirect, not an empty query. Always verify by checking the raw response length before reporting "no results".
- MCP first: a common pitfall is invoking the script without checking whether a
semantic-scholarorgoogle-scholarMCP is available. MCPs are faster, structured, and avoid rate-limit risk.
Workflow
1. Check MCP availability
Consider the semantic-scholar or google-scholar MCP server first. If either is configured and reachable, prefer it over this script.
2. Set up the environment (first run only)
See setup-and-troubleshooting.md for venv creation and dependency installation.
3. Run the search
Activate the venv, then choose the appropriate subcommand:
# Basic keyword search
./scripts/google-scholar-search.py search --query "retrieval-augmented generation" --results 10
# Advanced: filter by author and year range
./scripts/google-scholar-search.py advanced \
--query "LLM reasoning" --author "Yann LeCun" \
--year-start 2020 --year-end 2024 --results 10
What ships with it
12 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.
- .audits/2026-04-09/analysis.md 1.2 KB
- .audits/2026-04-09/audit.json 507 B
- .audits/2026-04-09/remediation-plan.md 3.0 KB
- .audits/latest 10 B
- evals/instructions.json 575 B
- evals/scenario-01.md 2.2 KB
- evals/scenario-02.md 1.9 KB
- evals/scenario-03.md 2.3 KB
- evals/summary.json 69 B
- references/setup-and-troubleshooting.md 1.8 KB
- requirements.txt 57 B
- scripts/google-scholar-search.py 13 KB runs code
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.
- 9d ago First seen · 141 lines · 73 tokens per session scan A 014a43612de5
google-scholar-search is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 1,382 once invoked, about $0.0004 per session on Opus 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 2026-09-03.
Other skills, from other repositories
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
atlas-obscura
Search Atlas Obscura for weird, wonderful, and hidden gem places near any destination. Find the interesting stuff, not boring plaques. Search by coordinates, get full details with descriptions and images.
agent-code-generator
Generates Agent definitions (.md files) based on user intent and standard templates.
cf-validate
A validator for 1C configuration source files. It checks the XML structure and the files and objects that make up a 1C business-application configuration.