Foresight-MCP: Instructions file for Claude Code

CLAUDE.md

Foresight-MCP CLAUDE.md is an instructions file for Claude Code from KKSurendran06/Foresight-MCP. It costs 6,970 tokens per session, scanned A, original, MIT.

A project blueprint for Foresight, an MCP server that tracks supply-chain disruptions, links them to purchase orders, finds screened alternatives, and drafts purchasing memos.

In plain words
What is it for?
Use it when implementing or maintaining the disruption-detection, exposure-analysis, alternate-supplier, and memo-drafting parts of Foresight.
Why use it?
It records the agreed project scope, architecture, deadlines, working rules, and decisions so the implementation stays within the planned boundaries.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; positional $N argument.

This is KKSurendran06/Foresight-MCP's own configuration. It tells Claude Code how to work on Foresight-MCP 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 Foresight-MCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to KKSurendran06/Foresight-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.

Copy the file
curl -O https://raw.githubusercontent.com/KKSurendran06/Foresight-MCP/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/KKSurendran06/Foresight-MCP

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 Foresight-MCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kksurendran06/foresight-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/kksurendran06/foresight-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kksurendran06/foresight-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kksurendran06/foresight-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.

agentmods 80×15 button for Foresight-MCP CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kksurendran06/foresight-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kksurendran06/foresight-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,970 This file is loaded in full into every session.
When invoked 6,970 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.06970 $0.06970
Opus 5 $0.03485 $0.03485
Sonnet 5 $0.01394 $0.01394
Haiku 4.5 $0.00697 $0.00697

Measured 8d ago against content hash b056253619f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Foresight-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 8d 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 · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Foresight — Project Blueprint

MCP Hackathon 2026, Amrita University · Manufacturing & Industry 4.0 track Hard deadline: 18 July 2026, 12:00 PM IST. No extensions. Server must stay live through automated reachability checks at 6:01 PM IST.

This file is the settled architecture and scope. It was signed off by the team on 17 Jul 2026 ~15:00 IST. Do not add features not listed here without team agreement. Keep PROGRESS.md updated after every milestone (see "Working rules" at the bottom). also use decisions.md to log all your decisions takens, and justify why you took that decisions in that file.


1. What Foresight is

One MCP server that closes the loop from disruption detected to decision drafted:

detect (live hazard feeds vs. supplier map) → exposure (which POs, how many dollars, how many days) → alternates (tier-ranked, compliance-screened against real sanctions/exclusion lists) → memo (drafted for purchasing to approve).

Pitch line (closes every pitch, never say "ChatGPT for procurement"): "Supply chains don't fail because disruptions happen — they fail because nobody finds out fast enough to still have options. We built the system that finds out first."

Positioning vs. the crowd: "Supply chain disruption monitor" is a printed example idea on our track sheet — other teams will build monitors. Commercial products (Resilinc, Everstream, Interos) cost six figures and stop at the alert. We never claim category novelty. We claim the loop: "they stop at the alert; we deliver the decision, as a tool call any agent can compose."

Honesty rules baked into the pitch:

  • The hazard feeds and the compliance lists are REAL. The supplier/order data is synthetic and presented as the deliberate ERP integration seam: "this table is where your SAP plugs in — you wouldn't hand us yours in 24 hours."
  • MCP is pull-based. We do NOT claim background monitoring. Framing: "every morning your agent reads the world against your supplier map before you've had coffee. We made the pull cheap, diffable, and schedulable — point any scheduler at it."
  • Humans approve the switch. The memo is FOR purchasing. Never "negotiates with" or "onboards" suppliers.

Read the full file on GitHub · 276 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. 8d ago First seen · 276 lines · 6,970 tokens per session scan A b056253619f5

Subscribe to this mod's changes

Foresight-MCP CLAUDE.md is an instructions file published in the GitHub repository KKSurendran06/Foresight-MCP (1 stars, last pushed 1mo ago), licensed MIT. It adds 6,970 tokens to every session, about $0.0348 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.

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

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

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

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