Borrowing it
Nothing to install: this file belongs to selvin-paul-raj/Instagram-Alpic-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/selvin-paul-raj/Instagram-Alpic-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/selvin-paul-raj/Instagram-Alpic-mcpWrote 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/selvin-paul-raj/instagram-alpic-mcp/claude-md)<a href="https://agentmods.dev/instructions/selvin-paul-raj/instagram-alpic-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/selvin-paul-raj/instagram-alpic-mcp/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.
<a href="https://agentmods.dev/instructions/selvin-paul-raj/instagram-alpic-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/selvin-paul-raj/instagram-alpic-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00788 | $0.00788 |
| Opus 5 | $0.00394 | $0.00394 |
| Sonnet 5 | $0.00158 | $0.00158 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
Instagram-Alpic-mcp 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 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.
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code when working in this repo. See README.md for full user-facing docs.
What this is
A single-user MCP server exposing Instagram actions via the Composio SDK, deployed on Alpic.
Entry point: src/server.py (FastMCP, streamable-HTTP transport). Sibling project to
D:\Personal\Linkedin-alpic-mcp — same architecture, same production fixes, different toolkit.
Commands
uv run python -m src.server # run locally
uv run pytest # run tests
uv run ruff check . # lint
Required environment
Both are mandatory — the server raises KeyError at startup if either is missing:
COMPOSIO_API_KEY— must be a project-scoped Composio API key, not a playground key. Playground keys are hard-locked server-side to one bound user; any otheruser_idgets a 403 (user_id does not match the user this playground API key is locked to) that no client-side code can work around.COMPOSIO_USER_ID— the Composio account's actual user id.
Gotchas (all discovered the hard way on the LinkedIn sibling project, apply here too)
.env/.env.exampleare write-protected by a local security hook (secret-file path guard). Edits to those files must be pasted in manually by the user, not written by the agent.- Alpic's managed Python runtime does not use this repo's
Dockerfile— it builds directly frompyproject.tomlwith its own buildpack (uv sync-style), running the process out of/var/taskwith a read-only$HOME. Don't assume a DockerfileENVchange takes effect on Alpic; env vars need to be set viaalpic environment-variable add(or the dashboard) too. - Composio's SDK creates a cache dir at
$HOME/.composioat import time — crashes immediately on any read-only-home sandbox unlessCOMPOSIO_CACHE_DIRpoints somewhere writable (/tmpworks). This is a Composio/platform issue, not toolkit-specific. logger.py's file handler andstats.py's_save()are both wrapped intry/except OSErrorfor the same reason — don't remove that, a read-only filesystem must degrade gracefully (stdout-only logging, in-memory-only stats), never crash the server.ENABLED_INSTAGRAM_TOOLSincomposio_client.pyis a curated list, not "every Instagram action Composio supports" — it reflects what's actually enabled for this account's auth config. Both session creation (_get_session) and discovery (list_instagram_tools) are scoped to it.ComposioClient._get_session()is lazily created and cached per instance — one Composio session per server process, not per request.execute()deliberately has no automatic retry (unlikecheck_connection/list_instagram_tools) because retrying an ambiguous write (e.g. creating a post, sending a DM) can duplicate it.- The README's "Available Instagram Tools" parameter list is best-effort (inferred from action
names, not live-fetched schemas) until the Composio connection for this account is completed —
call
instagram_mcp_list_toolsonce connected and update the README with the real schemas, the way the LinkedIn project's README was built from a livelist_linkedin_tools()call.
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.
- 11d ago First seen · 54 lines · 788 tokens per session scan A 931fd53add9b
Instagram-Alpic-mcp CLAUDE.md is an instructions file published in the GitHub repository selvin-paul-raj/Instagram-Alpic-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 788 tokens to every session, about $0.0039 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
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.
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.
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.
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).