agentmods.dev

claude-plugin AGENTS.md

A contributor guide for the Global-Slice Claude plugin marketplace, including its folder layout, release files, validation workflows, and conventions for adding skills.

In plain words
What is it for?
Use it when modifying the marketplace, adding a skill, checking plugin versions, or preparing a Claude plugin release.
Why use it?
It gives contributors the repository-specific rules needed to make compatible changes. The input does not specify every rule in the guide.

Instructions file for CodexOpenCode

9 1mo ago A scan 800 tokens original MIT
View the source file Global-Slice/claude-plugin
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 instructions/global-slice/claude-plugin/agents-md
Clone the repo
git clone --depth 1 https://github.com/Global-Slice/claude-plugin

Made for: Codex, OpenCode.

Per session 800 This file is loaded in full into every session.
When invoked 800 The same file — it is already loaded in full.
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 $0.00800 $0.00800
Opus 5 $0.00400 $0.00400
Sonnet 5 $0.00160 $0.00160
Haiku 4.5 $0.00080 $0.00080

Measured 2d ago against content hash dcb288a9781d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-plugin AGENTS.md 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.

AGENTS.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Contributor guide for AI agents working on the Slice Claude plugin marketplace.

Repository layout

claude-plugin/
├── .claude-plugin/marketplace.json           # Marketplace manifest (lists all plugins)
├── .github/
│   ├── workflows/
│   │   ├── validate_plugin.yml               # PR: claude plugin validate + version sync
│   │   ├── release.yml                       # Tag push: build zip + GitHub Release
│   │   └── auto-tag.yml                      # Main push: auto-tag on version bump
│   └── dependabot.yml                        # GitHub Actions updates
├── scripts/
│   ├── build-release-claude.sh               # Stage plugins/slice-global/ → dist/slice-claude-<v>.zip
│   └── validate-versions.sh                  # Keep marketplace.json + plugin.json in sync
├── plugins/slice-global/                     # The slice-global plugin
│   ├── .claude-plugin/plugin.json            # Plugin manifest (canonical version source)
│   ├── .mcp.json                             # MCP server config (Slice HTTP endpoint)
│   └── skills/                               # Claude skills (one folder per skill)
├── AGENTS.md                                 # This file
├── CHANGELOG.md                              # Keep-a-Changelog format
├── LICENSE                                   # MIT
└── README.md                                 # Install instructions + permanent zip URL

Version-bump checklist

The canonical version lives in plugins/slice-global/.claude-plugin/plugin.json. When bumping:

  1. Update version in plugins/slice-global/.claude-plugin/plugin.json (source of truth).
  2. Update top-level version and metadata.version in .claude-plugin/marketplace.json. Do not add a version field to the plugin entry inside marketplace.json — plugin.json is the only source of truth.
  3. Keep marketplace discovery fields current: top-level description, plugin displayName, tags, keywords, homepage, repository, and the skills path list (relative to each plugin root).
  4. Add a new dated entry to CHANGELOG.md.
  5. Merge to main — the auto-tag.yml workflow creates the git tag automatically.

Read the full file on GitHub · 59 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. 2d ago First seen · 59 lines · 800 tokens per session scan A dcb288a9781d

Subscribe to this mod's changes

claude-plugin AGENTS.md is an instructions file published in the GitHub repository Global-Slice/claude-plugin (9 stars, last pushed 1mo ago), licensed MIT. It adds 800 tokens to every session, about $0.0040 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.

Git and workflowcap-tableclaude-code-pluginclaude-code-pluginsclaude-code-skillequitymcp
Related

Other instructions, from other repositories

context-mode CLAUDE.md

Claude Code instructions for mksglu/context-mode, covering context-mode — mandatory routing rules, think in code — mandatory, blocked — do not attempt, curl / wget — blocked and inline http — blocked.

mksglu/context-mode · 1,184 tokens

claude-skills CLAUDE.md

Instructions for secondsky/claude-skills, covering claude skills - project context, ⚠️ critical: communication rule — the most important rule, ⚠️ critical: repository policy - never touch jezweb repo, ❌ forbidden actions (jezweb repo) and ✅ required actions (secondsky repo).

secondsky/claude-skills · 7,874 tokens

claude-skills AGENTS.md

Instructions for secondsky/claude-skills, covering agent instructions, ⚠️ critical: communication rule — the most important rule and full project context.

secondsky/claude-skills · 154 tokens

verify CLAUDE.md

Instructions for opslane/verify, covering project, architecture, boundaries, skill sync and engine work.

opslane/verify · 393 tokens

agentic-seo-skills AGENTS.md

Instructions for agencia-conversion/agentic-seo-skills, covering agentic seo — agent runtime contract, mission, six pillars, audience and delivery — web companion first.

agencia-conversion/agentic-seo-skills · 2,377 tokens

rgotify AGENTS.md

AGENTS.md instructions for dinglebear-ai/rgotify, a project described as: Rust MCP server and CLI for Gotify push notifications, with stdio/HTTP transports, auth, Claude/Codex plugin packaging, and npm/GitHub Release distribution.

dinglebear-ai/rgotify · 4 tokens