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.
git clone --depth 1 https://github.com/frankxai/claude-skills-libraryWrote 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/plugins/frankxai/claude-skills-library/starlight-neutron)<a href="https://agentmods.dev/plugins/frankxai/claude-skills-library/starlight-neutron"><img src="https://agentmods.dev/badge/plugins/frankxai/claude-skills-library/starlight-neutron/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/plugins/frankxai/claude-skills-library/starlight-neutron"><img src="https://agentmods.dev/badge/plugins/frankxai/claude-skills-library/starlight-neutron.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
starlight-neutron 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 yesterday.
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
{
"name": "starlight-neutron",
"version": "0.2.0",
"description": "Spend fewer tokens without lowering the ceiling: a router skill, a measurement protocol, a doctor/bench CLI and a fail-open RTK hook for shell output.",
"author": { "name": "FrankX", "url": "https://github.com/frankxai" },
"homepage": "https://github.com/frankxai/claude-skills-library/tree/main/packs/starlight-neutron",
"license": "MIT",
"keywords": ["tokens", "cost", "context", "rtk", "headroom", "orchestration"]
}
What it installs
The manifest is a name and a version. 2 skills, 1 hook travel with it, and installing the plugin installs all of them — 166 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- yesterday First seen · 10 lines scan A 413c1686315c
starlight-neutron is a plugin published in the GitHub repository frankxai/claude-skills-library (47 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-15.
Other plugins, from other repositories
prompt-refiner
Hybrid prompt linter — deterministic Node detector for 18 of 20 rules plus an LLM model layer for PR003, PR009, and semantic cases of PR002, PR005, and PR010. Lint, don't rewrite. Markdown or JSON output, suppression comments, baseline mode, conformance corpus (25 cases), CI recipes. Never imposes a framework, never…
pr-provenance-stamp
Embeds a reviewer-facing provenance receipt into your PR body when Claude runs gh pr create (or glab mr create). A PostToolUse hook (async, zero added latency) records a per-session ledger: tool calls, agent-authored lines, and every test/typecheck command with its real exit code; a PreToolUse (Bash) hook then rewr.
memory-kit
Persistent memory for Claude Code agents: a hot cache injected every session and held under three size caps, per-session handoffs, and agent-audited promotion into knowledge articles and rules. Carries the builder's layers too — executor/recon/idea-validator agents, session review, second opinion, agent QA and a…
rust-tools
SOTA Rust tooling - refactoring, profiling, benchmarking, testing, SIMD, dependency audit.
context-optimization
Techniques for extending effective context capacity through compaction, observation masking, KV-cache optimization, and context partitioning. Double or triple effective context without larger models.
config-server
Generate centralized config management.