maintain-agent-plugins

A maintenance workflow for agent-plugin repositories that keeps plugin definitions aligned and checks or applies the complete plugin set with two standard commands.

In plain words
What is it for?
It is for installing the managed maintenance runtime, checking plugin definitions with `just plugins-check`, and applying updates with `just plugins-apply`.
Why use it?
It reduces inconsistent metadata, one-off maintenance commands, and manual synchronization across plugin manifests and marketplace entries.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/gaelic-ghost/socket/maintain-agent-plugins
Any agent
npx skills add gaelic-ghost/socket --skill maintain-agent-plugins
Clone the repo
git clone --depth 1 https://github.com/gaelic-ghost/socket

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 954 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00036 $0.00954
Opus 5 $0.00018 $0.00477
Sonnet 5 $0.00007 $0.00191
Haiku 4.5 $0.00004 $0.00095

Measured 2d ago against content hash df0b193786a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

maintain-agent-plugins 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 2d 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.

plugins/agent-plugin-skills/skills/maintain-agent-plugins/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Maintain Agent Plugins

Purpose

Create and maintain Codex plugin source without reintroducing hand-maintained metadata, per-plugin commands, Python automation, or customizable scaffolding. Use current official OpenAI plugin documentation for host schema facts, then apply the fixed Socket repository policy through the managed runtime.

Required Interface

Plugin maintenance has exactly two public commands. Each processes every plugin manifest and marketplace entry owned by the repository:

just plugins-check
just plugins-apply

Do not add per-plugin, per-manifest, scaffold, sync, bootstrap, or alternate mode recipes. plugins-check is read-only. plugins-apply performs the complete deterministic reconciliation and then checks its result.

Installation

  1. Confirm the target is a Git repository root.
  2. Run scripts/maintain-agent-plugins.fsx --repo-root <path> --operation install from this skill once to copy the managed runtime and Just import.
  3. The installer also adds ordered repository-maintenance hooks when the target already uses the canonical scripts/repo-maintenance/ runtime.
  4. Run just plugins-apply, then just repo-validate when repository-skills is present.

Use --operation refresh to replace managed files from this skill and --operation report-only for a read-only drift report. These installer modes are skill internals, not additional Just tasks.

Fixed Policy

  • Publisher: Gale, [email protected], https://github.com/gaelic-ghost.
  • License: Apache-2.0.
  • Plugin names: stable kebab case matching their directory.
  • Manifest: .codex-plugin/plugin.json; bundled skills: ./skills/.
  • Default plugin repository URL: https://github.com/gaelic-ghost/<plugin-name>.
  • Local marketplace policy: AVAILABLE and ON_INSTALL.
  • Default category: Developer Tools unless the plugin already has an intentional product category.
  • Default-discovered hook files stay at hooks/hooks.json; do not duplicate that default path in the manifest.
  • interface.defaultPrompt is an array of at most three concise prompts.

Read the full file on GitHub · 104 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 104 lines · 36 tokens per session scan A df0b193786a8

Subscribe to this mod's changes

maintain-agent-plugins is a skill published in the GitHub repository gaelic-ghost/socket (6 stars, last pushed 6d ago), licensed Apache-2.0. It adds 36 tokens to every session and 954 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

xcode-disk-cleanup

Audit and safely clean Xcode-related developer storage on macOS. Use whenever a developer mentions low disk space, Xcode storage, DerivedData, simulator devices or runtimes, stale beta platforms in Xcode Settings, DeviceSupport, archives, dSYMs, CocoaPods caches, simulator dyld caches, project .build folders…

AvdLee/Xcode-Disk-Cleanup-Agent-Skill · 147 tokens

storescreens

Set up and run storescreens-cli to automate App Store screenshot capture for iOS apps: render captioned/framed App Store-ready screenshots with device bezels, markdown captions, and panoramic backgrounds; upload screenshots + per-locale metadata (name, subtitle, description, keywords, what's new, promotional text) to…

ciscoriordan/storescreens-skill · 331 tokens

poll-github-work

Poll and rank open GitHub issues, RFCs, and pull requests for maintainer work, or start one explicitly selected item. Use when a user asks what to work on, requests backlog priorities, says "poll work," wants actionable issues or pull requests, or says "start.

trycua/cua · 61 tokens

test

Run tests. Use after code changes to validate. Arguments: unit (default, no GPU), e2e (with models), filter name, or all.

soniqo/speech-swift · 34 tokens

baocut

BaoCut-only operator for the installed bcut CLI and .bcut projects. Implicitly trigger only when the request explicitly names BaoCut or bcut, targets a .bcut project or BaoCut Subtitle Studio, or continues a BaoCut workflow already established in the conversation. Do not trigger solely for generic audio or video…

JimLiu/baocut · 160 tokens

release

Build, sign, notarize, and publish a new DroidProxy release. Use when the user wants to cut a release, merge a PR and ship it, or asks to build/notarize/publish. Covers the full pipeline: PR merge, version bump, swift build, code signing, Apple notarization, Sparkle appcast update, and GitHub release creation.

nikships/droidproxy · 80 tokens