githits-plugin-maintenance

githits-plugin-maintenance is a skill for Claude Code, Codex from githits-com/githits-cli. It costs 70 tokens per session (912 once invoked), scanned A, original, Apache-2.0.

An internal guide for maintaining GitHits plugins and agent-skill integrations in the GitHits CLI repository.

In plain words
What is it for?
Use it when changing GitHits skills, plugin manifests, marketplace data, MCP transport details, host integrations, release metadata, or their tests.
Why use it?
It helps keep source files, generated plugin files, marketplace metadata, and MCP instructions consistent when the repository changes.

Skill for Claude CodeCodex

Part of the githits plugin — 6 skills, 1 MCP server shipped together

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/githits-com/githits-cli/githits-plugin-maintenance
Any agent
npx skills add githits-com/githits-cli --skill githits-plugin-maintenance
Clone the repo
git clone --depth 1 https://github.com/githits-com/githits-cli

Made for: Claude Code, Codex.

Or install githits, the plugin that ships this one along with the rest of its 6 skills, 1 MCP server.

Wrote 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.

agentmods badge for githits-plugin-maintenance

README.md
[![agentmods](https://agentmods.dev/badge/skills/githits-com/githits-cli/githits-plugin-maintenance.svg)](https://agentmods.dev/skills/githits-com/githits-cli/githits-plugin-maintenance)
Your own site
<a href="https://agentmods.dev/skills/githits-com/githits-cli/githits-plugin-maintenance"><img src="https://agentmods.dev/badge/skills/githits-com/githits-cli/githits-plugin-maintenance.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 912 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 $0.00070 $0.00912
Opus 5 $0.00035 $0.00456
Sonnet 5 $0.00014 $0.00182
Haiku 4.5 $0.00007 $0.00091

Measured today against content hash 1aa179eb15fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

githits-plugin-maintenance 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 today.

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.

.agents/skills/githits-plugin-maintenance/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Maintain GitHits Plugin Surfaces

This is an internal, repository-only skill. Do not publish or package it with the public skills under skills/.

Keep root skills and shared metadata canonical. Treat generated manifests and host MCP files as reviewable build artifacts, not authoring locations.

Workflow

  1. Identify the canonical input that owns the requested behavior.
  2. Read docs/implementation/plugin-packaging.md before changing packaging or transport behavior.
  3. Edit canonical inputs only.
  4. For the stable MCP quick-start guide, keep packages/mcp/src/mcp/instructions.ts buildMcpQuickStart() and the terminal ## Quick-start guide section in skills/githits-mcp/SKILL.md byte-for-byte aligned in the same PR. src/skills-packaging.test.ts is the exact-parity contract; exclude buildLocalMcpQuickStart() runtime appendices from the public copy. Route behavior-dependent guide changes through the public Agent Skill lifecycle.
  5. Run bun run plugins:generate.
  6. Inspect every generated diff and confirm it follows from the canonical change.
  7. Run bun run plugins:check.
  8. Run targeted tests, then the required smoke or agent evaluations for the affected surface.

Canonical Ownership

  • Author public skill content only under skills/.
  • Author shared agent guidance in AGENTS.md; keep CLAUDE.md and GEMINI.md as symlinks to it.
  • packages/mcp/src/mcp/instructions.ts owns the stable quick-start builder; the terminal guide in skills/githits-mcp/SKILL.md is its exact public copy.
  • Use package.json for root version, identity, and shared package metadata.
  • Use server.json for registry transports and the hosted MCP endpoint.
  • Use scripts/generate-plugin-assets.ts for host rendering and validation.

Transport Contract

  • Every plugin and extension package uses https://mcp.githits.com. Claude, Codex, Cursor, and VS Code/GitHub Copilot OpenPlugin share generated .mcp.json; Gemini uses gemini-extension.json with httpUrl; and Antigravity uses mcp_config.json with serverUrl.
  • The hosted server lives in the separate remote-mcp repository and consumes released @githits/mcp for tool registration, descriptors, quick_start, and tool logic. Keep transport, request-scoped service composition, auth/session handling, deployment, and observability in remote-mcp; never reimplement package-owned MCP behavior there. Hosted descriptor changes take effect only after the package release is adopted and deployed by remote-mcp.
  • Direct githits init configuration retains stdio except for Cursor, which is remote-only. Claude and Gemini CLI setup remove legacy plugin or extension state before installing the user-scoped stdio server.
  • server.json advertises both remote and version-pinned npm stdio transports.

Read the full file on GitHub · 94 lines

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. today Changed · +7 lines 1aa179eb15fa
  2. 3d ago First seen · 87 lines · 70 tokens per session scan A f19ddcab7efd

Subscribe to this mod's changes

githits-plugin-maintenance is a skill published in the GitHub repository githits-com/githits-cli (93 stars, last pushed today), licensed Apache-2.0. It adds 70 tokens to every session and 912 once invoked, about $0.0003 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 2026-08-30.