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 agentmods add instructions/modellix/modellix-plugin/agents-mdgit clone --depth 1 https://github.com/Modellix/modellix-pluginWhat 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 | $0.05164 | $0.05164 |
| Opus 5 | $0.02582 | $0.02582 |
| Sonnet 5 | $0.01033 | $0.01033 |
| Haiku 4.5 | $0.00516 | $0.00516 |
Grade A, and why
modellix-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.
How it starts
The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for coding agents that maintain this Modellix plugin package. Human install and product overview live in README.md.
Project overview
This repository conforms to Agent Plugins 1.0.0: the git repository root is the plugin root, root plugin.json is the portable manifest, skills/modellix/ is the fixed Agent Skill location, and root mcp.json declares the read-only Docs MCP. Cursor, Claude Code, Codex, legacy Open Plugins, OpenClaw/ClawHub, OpenCode, Pi, and Hermes adapters add host capabilities such as rules, hooks, and seven slash commands without changing the portable core.
There is no application runtime. The product is manifests + skill markdown + thin stdlib Python helpers, covered by repository regression tests.
modellix-plugin/ ← plugin root (= repo root)
├── plugin.json ← Agent Plugins 1.0.0 portable manifest (edit first)
├── mcp.json ← Agent Plugins Docs MCP (streamable-http)
├── .plugin/plugin.json ← legacy Open Plugins host adapter
├── .cursor-plugin/ ← Cursor plugin.json + single-repo marketplace.json
├── .claude-plugin/ ← Claude Code plugin.json + marketplace.json
├── .codex-plugin/plugin.json
├── .agents/plugins/marketplace.json
├── assets/logo.svg
├── skills/modellix/ ← Agent Plugins fixed skills/ discovery
│ ├── SKILL.md
│ ├── skill.json
│ ├── references/ ← cli / rest / capability playbooks
│ ├── scripts/ ← CLI update/preflight + execution helpers (stdlib Python)
│ ├── assets/
│ └── evals/
├── openclaw.plugin.json ← ClawHub bundle-plugin (skills only; no extensions)
├── .mcp.json ← Cursor/legacy Docs MCP adapter (`type: http`)
├── commands/ ← slash commands (thin prompts routing to the CLI flow)
├── rules/ ← host-specific always-on .mdc guardrails
├── hooks/ ← hooks.json (legacy/Claude) + cursor-hooks.json (Cursor)
├── scripts/ ← plugin-level hook scripts + cross-platform Node launcher
├── package.json ← npm + ClawHub + Pi (`bin`, `pi-package`, pi.skills)
├── .opencode/skills/modellix → ../../skills/modellix
├── .pi/skills/modellix → ../../skills/modellix
└── .github/workflows/skill_update.yml
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.
- 2d ago First seen · 292 lines · 5,164 tokens per session scan A 837ef24859e8
modellix-plugin AGENTS.md is an instructions file published in the GitHub repository Modellix/modellix-plugin (1 stars, last pushed 21d ago), licensed MIT. It adds 5,164 tokens to every session, about $0.0258 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.
Other instructions, from other repositories
pixellab-pip GEMINI.md
Instructions for Shilo/pixellab-pip: Use PixelLab Pip when the user asks about PixelLab asset generation, editing, animation, MCP setup, REST v2 integration, website/editor workflows, Aseprite, Pixelorama, legacy v1, bearer-token auth, endpoint choice, SDK coverage, or PixelLab docs.
pixellab-pip AGENTS.md
Instructions for Shilo/pixellab-pip: PixelLab Pip is an unofficial, agent-agnostic PixelLab workflow router shipped as a portable Agent Skill. It teaches coding agents to choose between documented PixelLab MCP tools, REST v2 endpoints, website/editor fallback, Aseprite, Pixelorama, and local asset assembly. The…
pixellab-pip CLAUDE.md
Instructions for Shilo/pixellab-pip, a project described as: Meet PixelLab Pip: a tiny pup who fetches the right PixelLab workflow. He follows human commands to create, edit, and animate pixel assets, then sniffs out a bigger prompt, scouts for a useful tool, and carries back what happened.
supergraph AGENTS.md
Instructions for datit309/supergraph, covering supergraph — mandatory workflows, skills, auto language detection, tiered workflow — pick the right tier first and full pipeline (tier 3).
project-legibility AGENTS.md
Instructions for perhapsspy/project-legibility, covering agents.md and 검증.
LifeHack-2026 CLAUDE.md
Instructions for Ducksss/LifeHack-2026: Before changing this repository, read AGENTS.md in full and follow its canonical context order, product invariants, worktree rules, and definition of done. Then read docs/HANDOVER.md for the latest product and repository state.