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 patleeman/neon-pilot --skill agent-plugin-installationgit clone --depth 1 https://github.com/patleeman/neon-pilotWrote 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/patleeman/neon-pilot/agent-plugin-installation)<a href="https://agentmods.dev/skills/patleeman/neon-pilot/agent-plugin-installation"><img src="https://agentmods.dev/badge/skills/patleeman/neon-pilot/agent-plugin-installation/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/patleeman/neon-pilot/agent-plugin-installation"><img src="https://agentmods.dev/badge/skills/patleeman/neon-pilot/agent-plugin-installation.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 | $0.00025 | $0.00479 |
| Opus 5.5 | $0.00010 | $0.00192 |
| Sonnet 5.5 | $0.00005 | $0.00096 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
agent-plugin-installation 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
Agent Plugin Installation
Use this skill when the user asks to install, add, inspect, update, enable, disable, remove, or explain a Codex or Claude Code style agent plugin.
Mental model
- Agent plugins are external Codex or Claude Code style repositories or folders.
- They can contain skills, instruction files, docs, MCP server definitions, hooks, and related files.
- Neon Pilot imports compatible pieces through an extension wrapper so agents can use them.
- Installed agent plugins are turned on by default. Treat turning a plugin off as an explicit user choice, not a normal installation step.
Install workflow
- Use
neon-pilot agent-plugins list --jsonif you need to check whether the requested plugin is already installed. - Use
neon-pilot agent-plugins install <git-url> --jsonwhen the user supplies or clearly approves a Git repository URL. - Use
neon-pilot agent-plugins install <folder> --local --jsonwhen the user supplies or clearly approves a local folder path. - After install, summarize the imported capabilities:
- skills
- instructions/docs
- MCP server definitions
- ignored hooks or compatibility warnings
- Tell the user if the plugin installed but produced no supported capabilities.
Source safety
- Only install from a source the user supplied or explicitly approved.
- Do not invent a plugin repository URL.
- If the source is ambiguous, ask for the exact Git URL or local folder.
- If a plugin reports compatibility warnings or ignored hooks, surface them plainly.
Useful UI
Users can manage installed plugins in Settings > Agent plugins. The same operations are available through:
neon-pilot agent-plugins listneon-pilot agent-plugins installneon-pilot agent-plugins enableneon-pilot agent-plugins disableneon-pilot agent-plugins check-updatesneon-pilot agent-plugins updateneon-pilot agent-plugins remove
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 · 51 lines · 25 tokens per session scan A 85fc037165f1
agent-plugin-installation is a skill published in the GitHub repository patleeman/neon-pilot (23 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 479 once invoked, about $0.0001 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.
agent-plugin-installation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agent-plugin-installationpatleeman/neon-pilot | Skill | 23 | 3mo ago | MIT | A | 25 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |