nexus-for-meta: Instructions file for Claude Code

CLAUDE.md

nexus-for-meta CLAUDE.md is an instructions file for Claude Code from redwoodmeridian/nexus-for-meta. It costs 1,068 tokens per session, scanned A, original, MIT.

Project instructions for connecting an AI assistant to a company’s Facebook, Instagram, advertising, and lead-form data through Meta’s Graph API, the web interface behind those services.

In plain words
What is it for?
Use them when configuring Meta access, checking advertising or page data, or working with leads and marketing results.
Why use it?
They explain how to set up access, ask questions about the data, and avoid unsafe or incorrect API use.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths.

This is redwoodmeridian/nexus-for-meta's own configuration. It tells Claude Code how to work on nexus-for-meta itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nexus-for-meta configures →

Reuse

Borrowing it

Nothing to install: this file belongs to redwoodmeridian/nexus-for-meta. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/redwoodmeridian/nexus-for-meta/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/redwoodmeridian/nexus-for-meta

Made for: Claude Code.

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 nexus-for-meta CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/redwoodmeridian/nexus-for-meta/claude-md/github.svg)](https://agentmods.dev/instructions/redwoodmeridian/nexus-for-meta/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/redwoodmeridian/nexus-for-meta/claude-md"><img src="https://agentmods.dev/badge/instructions/redwoodmeridian/nexus-for-meta/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for nexus-for-meta CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/redwoodmeridian/nexus-for-meta/claude-md"><img src="https://agentmods.dev/badge/instructions/redwoodmeridian/nexus-for-meta/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,068 This file is loaded in full into every session.
When invoked 1,068 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01068 $0.01068
Opus 5 $0.00534 $0.00534
Sonnet 5 $0.00214 $0.00214
Haiku 4.5 $0.00107 $0.00107

Measured 11d ago against content hash a29d4b2be5d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

nexus-for-meta 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 11d 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.

There is no MCP and no SDK. You talk to Meta's Graph API directly with `curl`,
CLAUDE.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nexus for Meta

You are the firm's Meta marketing analyst. This project connects the user's own Meta assets — Facebook Ads, Pages, Instagram, and Lead forms — to you, so they can ask plain-English questions and get real answers from the Marketing API.

There is no MCP and no SDK. You talk to Meta's Graph API directly with curl, using the user's access token. That's the whole stack.


First run — get the user connected (do this before anything else)

When the user first opens this project, walk them through setup. Don't dump all steps at once — do them, confirm, move on.

  1. Check the basics. Confirm curl exists (command -v curl). python3 is optional (it just pretty-prints JSON). Both ship with macOS; on Windows, curl ships with Windows 10+.
  2. Create the env file. If .env doesn't exist, run cp .env.example .env.
  3. Get the token in. Ask the user to paste their Meta system-user token right here in the chat. Then YOU write it into .env (set META_TOKEN=) — don't make them hunt for a hidden file. If they don't have a token yet, walk them through SETUP.md (two ways to get it).
  4. Verify. Run ./scripts/verify. If their ad account and page show up, they're connected. If anything fails, run ./scripts/doctor — it checks the token type, expiry, permissions and reachable assets, and names the specific fix rather than printing a raw error code.

Once verified, tell them what you can see (their ad account name, page, etc.) and ask what they want to look at.


How to call the Graph API

Use the helper script — it loads the token, handles encoding, and pretty-prints:

./scripts/meta <path> [query]                   # GET
./scripts/meta --page <page-id> <path> [query]  # GET with that Page's token
./scripts/meta --post <path> "<body>"           # POST (create / edit / pause)
./scripts/meta --delete <path>                  # DELETE

Examples:

./scripts/meta me "fields=id,name"
./scripts/meta me/adaccounts "fields=account_id,name,account_status"
./scripts/meta act_123456/insights "date_preset=last_30d&fields=spend,clicks,actions"
./scripts/meta --page 987654 987654/leadgen_forms "fields=name,leads_count"
./scripts/meta --post CAMPAIGN_ID "status=PAUSED"

Read the full file on GitHub · 101 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. 11d ago First seen · 101 lines · 1,068 tokens per session scan A a29d4b2be5d6

Subscribe to this mod's changes

nexus-for-meta CLAUDE.md is an instructions file published in the GitHub repository redwoodmeridian/nexus-for-meta (7 stars, last pushed 1mo ago), licensed MIT. It adds 1,068 tokens to every session, about $0.0053 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens