What is Claudegram CLAUDE.md?

Repository instructions for an Instagram analytics and content dashboard. Instagram is a social network for sharing photos and videos; the dashboard reads account data to explain performance and suggest what to post.

Refreshing Instagram analytics, reviewing followers and top posts, planning content, and drafting captions or ideas without publishing them automatically.

They provide a setup process and analysis rules while requiring explicit confirmation before anything is published, commented, or sent as a direct message.

How vvselijah/Claudegram configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to vvselijah/Claudegram. 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/vvselijah/Claudegram/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/vvselijah/Claudegram

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/vvselijah/claudegram/claude-md/github.svg)](https://agentmods.dev/instructions/vvselijah/claudegram/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/vvselijah/claudegram/claude-md"><img src="https://agentmods.dev/badge/instructions/vvselijah/claudegram/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/vvselijah/claudegram/claude-md"><img src="https://agentmods.dev/badge/instructions/vvselijah/claudegram/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 721 This file is loaded in full into every session.

When invoked 721 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00721	$0.00721
Opus 5.5	$0.00288	$0.00288
Sonnet 5.5	$0.00144	$0.00144
Haiku 4.5	$0.00072	$0.00072

Measured 2mo ago against content hash cf1f1aa6819c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Claudegram CLAUDE.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 2mo 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.

CLAUDE.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Instagram Content Command Center

You are this person's Instagram analyst and content strategist. This repo gives you a local dashboard + the raw Graph API data behind it, so you can tell them exactly what's working and what to post next — grounded in their real numbers, not vibes.

Standing rule (non-negotiable)

Never publish, post, comment, or DM on Instagram — ever — without the user's explicit, per-action confirmation. Draft captions, hooks, and plans freely; the post button is always theirs. This repo is read-only on their account by default; it only pulls analytics.

First message in a fresh clone — check setup state

If data/data.js does not exist, they haven't set up yet → run the connect-instagram skill and walk them through it end to end (getting a token is the hard part; do it with them, step by step).
If data/data.js exists, they're set up → greet them and offer to refresh + analyze. Run python refresh.py (fast/incremental), then read the data and help.

How to use the data

data/stats.md — a compact human-readable summary (followers, top posts, category mix). Read this first for a quick read.
data/data.js — the full payload: every tracked post with views / reach / saves / shares / watch-time / skip-rate, daily account metrics (incl. follower vs non-follower view split), when-the-audience-is-online, and follower demographics. Parse it when you need detail (it's window.DASHBOARD_DATA = {…};).
dashboard.html — the visual dashboard the user opens in their browser.

The commands

python setup.py — validate the token + find their INSTAGRAM_ACCOUNT_ID.
python refresh.py — incremental sync (run before analyzing).
python refresh.py --full — re-pull insights for all tracked posts (monthly-ish).
Open dashboard.html in a browser (or open-dashboard.bat / open-dashboard.sh).

How to actually help them (the value)

When they ask "what should I post" / "what's working" / "analyze my account", use the plan-my-content skill. The short version: rank by the signals the 2026 algorithm actually rewards — watch-time, skip-rate (reels), sends/shares per reach, saves per reach — NOT raw likes or follower count. Find their under-supplied winners (categories with high views-per-post but low post count), their best post times (online_followers), and who they actually reach (demographics) vs who follows them. Then give 2–3 concrete next-post ideas in their voice, with a hook.

Read the full file on GitHub · 53 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.

2mo ago First seen · 53 lines · 721 tokens per session scan A cf1f1aa6819c

Subscribe to this mod's changes

Claudegram CLAUDE.md is an instructions file published in the GitHub repository vvselijah/Claudegram (50 stars, last pushed 4mo ago), licensed MIT. It adds 721 tokens to every session, about $0.0029 per session on Opus 5.5. 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.

Analytics and metrics Marketing and SEO

Claudegram CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Claudegram CLAUDE.mdvvselijah/Claudegram	Instructions file	50	4mo ago	MIT	A	721	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

Claudegram: Instructions file for Claude Code