Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/cheenu1092-oss/netmcpnpx agentmods add skills/cheenu1092-oss/netmcp/threegpp-specsWrote 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/cheenu1092-oss/netmcp/threegpp-specs)<a href="https://agentmods.dev/skills/cheenu1092-oss/netmcp/threegpp-specs"><img src="https://agentmods.dev/badge/skills/cheenu1092-oss/netmcp/threegpp-specs/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/cheenu1092-oss/netmcp/threegpp-specs"><img src="https://agentmods.dev/badge/skills/cheenu1092-oss/netmcp/threegpp-specs.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 | $0.00080 | $0.00684 |
| Opus 5.5 | $0.00032 | $0.00274 |
| Sonnet 5.5 | $0.00016 | $0.00137 |
| Haiku 4.5 | $0.00008 | $0.00068 |
Grade A, and why
threegpp-specs 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.
What it actually says
3GPP Specs — 5G/LTE Standards Search
CLI Usage (Quick & Easy)
Simple bash wrapper scripts for direct command-line use:
cd ./skills/threegpp-specs/scripts
# Get specific spec details
./get.sh 23.501
# Search specs by keyword
./search.sh "5G" 5
# List specs by release
./releases.sh 18
MCP Server Setup
cd SKILL_DIR/../../packages/threegpp-specs
npm install && node src/index.js
# Or install into Claude Code config
./scripts/install-mcp.sh
Tools Available
spec_search — Search specifications
Input: Spec number or keyword (e.g. "23.501", "5G security", "NR physical layer") Returns: Matching specs with title, responsible group, releases, archive link
spec_get — Get details for a specific spec
Input: Spec number (e.g. "TS 23.501", "38.300") Returns: Full spec details including release history
spec_releases — List specs by release
Input: Release number (15, 16, 17, 18) Returns: Release info and all curated specs in that release
Key Releases
- Release 15 (2018): 5G Phase 1 — NSA + SA
- Release 16 (2020): 5G Phase 2 — URLLC, V2X, NPN
- Release 17 (2022): 5G-Advanced prep — NTN, RedCap, XR
- Release 18 (2024): 5G-Advanced — AI/ML, Ambient IoT
Key Specs to Know
- TS 23.501: 5G System Architecture (the "bible" of 5G)
- TS 38.300: NR Overall Description (5G radio overview)
- TS 38.331: NR RRC (Radio Resource Control)
- TS 33.501: 5G Security Architecture
- TS 29.500: 5G Service-Based Architecture
Data Source
3GPP FTP Archive: www.3gpp.org/ftp/Specs/archive/ — Public, no auth. Curated database of 40+ key specs plus live FTP directory scraping.
Examples
- "What's in TS 23.501?" →
spec_getwith "23.501" - "Find 5G security specs" →
spec_searchwith "security" - "What's new in Release 18?" →
spec_releaseswith release 18 - "Show me NR physical layer specs" →
spec_searchwith "NR physical"
What ships with it
4 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 · 74 lines · 80 tokens per session scan A 3fb226d4a548
threegpp-specs is a skill published in the GitHub repository cheenu1092-oss/netmcp (0 stars, last pushed 18d ago), licensed MIT. It adds 80 tokens to every session and 684 once invoked, about $0.0003 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.
threegpp-specs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| threegpp-specscheenu1092-oss/netmcp | Skill | 0 | 18d ago | MIT | A | 80 | Claude Code, Codex |
| orca-emulator-androidstablyai/orca | Skill | 117k | yesterday | MIT | A | 102 | Claude Code, Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| android-tombstone-symbolicationdotnet/skills | Skill | 5.8k | yesterday | MIT | A | 176 | Claude Code |
| dogfoodcallstack/agent-device | Skill | 5.3k | yesterday | MIT | A | 55 | Claude Code |
| winapp-mauimicrosoft/winappCli | Skill | 1.4k | yesterday | MIT | A | 68 | Claude Code |
| app_remixrome-os/rome | Skill | 889 | yesterday | MIT | A | 50 | Claude Code, Codex |