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/taboola/realize-claude-plugin/claude-mdgit clone --depth 1 https://github.com/taboola/realize-claude-pluginWrote 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/instructions/taboola/realize-claude-plugin/claude-md)<a href="https://agentmods.dev/instructions/taboola/realize-claude-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/taboola/realize-claude-plugin/claude-md.svg" alt="Measured on agentmods" 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 | $0.04253 | $0.04253 |
| Opus 5 | $0.02126 | $0.02126 |
| Sonnet 5 | $0.00851 | $0.00851 |
| Haiku 4.5 | $0.00425 | $0.00425 |
Grade A, and why
realize-claude-plugin CLAUDE.md scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Taboola's developer documentation is deliberately excluded**, and the exclusion is reasoned, not an oversight: its API reference covers the same API the MCP already wraps (and *No direct curl / no API client code* belo How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Contributor Notes
Internal implementation notes for anyone (human or agent) editing this plugin. Not user-facing — the user-facing docs are in README.md.
Architecture at a glance
This is a thin Claude Code plugin that wraps the Realize remote MCP. The MCP does all the heavy lifting (auth, HTTP, response shaping); the plugin's job is to teach the model how to use the MCP well.
┌─────────────────────┐
│ User (Claude Code) │
└──────────┬──────────┘
│ natural language
▼
┌─────────────────────┐
│ realize-analyst │ orchestrator agent (agents/realize-analyst.md)
│ agent │ routes intent → right skill/tool
└──────────┬──────────┘
│
├──► accounts skill → search_accounts
├──► campaigns skill → list_campaigns, get_campaign, list_items, get_item
├──► discovery skill → search_geos, search_techno, search_audiences,
│ search_lookalike_audiences, search_contextual_segments,
│ search_publishers, search_conversion_rules,
│ list_time_zones, list_cta_types
├──► reports skill → 4 report tools (CSV output)
├──► optimize-campaign skill → diagnoses underperformance; hands write
│ prescriptions to manage-campaigns
├──► manage-campaigns skill → 6 write tools: create_campaign, update_campaign,
│ create_native_item, update_native_item,
│ create_display_item, update_display_item.
│ Tiered preview-then-confirm with mandatory
│ ▶ WRITE TARGET account header.
│ UI fallback for delete/duplicate/bulk ops.
│
├──► support skill → NO MCP tools. Reads the local Claude Code
│ session transcript and renders one Markdown
│ file the user emails to [email protected].
│ Preview-then-confirm; writes locally only,
│ transmits nothing. Entry point: /support.
│
└──► web-fallback skill → NO MCP tools. WebSearch + WebFetch against
realize.com/help/ only. Last tier of the
sourcing ladder: fires only on a real
per-question miss, never supplements, and
loses silently to knowledge/ on conflict.
│
▼
┌────────────────────────────────────────┐
│ Realize MCP (https://mcp.realize.com) │
│ OAuth 2.1, 19 read + 6 write tools │
│ wired here. Writes routed exclusively │
│ through the manage-campaigns skill. │
└────────────────────────────────────────┘
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.
- 3d ago First seen · 196 lines · 4,253 tokens per session scan A 4b758079116d
realize-claude-plugin CLAUDE.md is an instructions file published in the GitHub repository taboola/realize-claude-plugin (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 4,253 tokens to every session, about $0.0213 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.