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.
curl -O https://raw.githubusercontent.com/KKSurendran06/Foresight-MCP/main/CLAUDE.mdgit clone --depth 1 https://github.com/KKSurendran06/Foresight-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/kksurendran06/foresight-mcp/claude-md)<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.
<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>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 | $0.06970 | $0.06970 |
| Opus 5 | $0.03485 | $0.03485 |
| Sonnet 5 | $0.01394 | $0.01394 |
| Haiku 4.5 | $0.00697 | $0.00697 |
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.
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.
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.
- 8d ago First seen · 276 lines · 6,970 tokens per session scan A b056253619f5
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.
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).
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).
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.
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.