portfolio-mcp: Instructions file for Codex

AGENTS.md

portfolio-mcp AGENTS.md is an instructions file for Codex, OpenCode from saagpatel/portfolio-mcp. It costs 382 tokens per session, scanned A, original, MIT.

Repository instructions that explain the portfolio-mcp project, its current state, technology stack, risks, and local commands. They give an agent background before it changes the code.

In plain words
What is it for?
Use them when maintaining or extending portfolio-mcp, especially when checking its MCP tools, TypeScript setup, tests, packaging, or deployment tasks.
Why use it?
They reduce guesswork and help the agent follow the project's known verification steps, approval gates, and unfinished work.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is saagpatel/portfolio-mcp's own configuration. It tells Codex and OpenCode how to work on portfolio-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 portfolio-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to saagpatel/portfolio-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/saagpatel/portfolio-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/saagpatel/portfolio-mcp

Made for: Codex, OpenCode.

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 portfolio-mcp AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/saagpatel/portfolio-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/saagpatel/portfolio-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 382 This file is loaded in full into every session.
When invoked 382 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 $0.00382 $0.00382
Opus 5.5 $0.00153 $0.00153
Sonnet 5.5 $0.00076 $0.00076
Haiku 4.5 $0.00038 $0.00038

Measured 23d ago against content hash 8edc47bfa0a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

portfolio-mcp AGENTS.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 23d 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.

AGENTS.md · 54 lines

What it actually says

Purpose

portfolio-mcp provides read-only MCP access to the public portfolio corpus over HTTP and stdio.

Layout

  • src/server.ts: shared tools, resources, and prompts.
  • src/index.ts and src/stdio.ts: HTTP Worker and stdio transports.
  • src/corpus.generated.ts: checked-in, generated public-safe corpus.
  • scripts/build-corpus.mjs: builds the corpus from public index artifacts.
  • test/: unit, protocol, corpus-builder, and stdio tests.

Setup

Use the versions pinned in .node-version and package.json.

npm ci

Checks

Run the complete local gate:

make check

The check includes lint, formatting, typecheck, tests, both transports, smoke, parity, and package contents.

Boundaries

  • Use only the checked-in public-safe corpus for normal work. Do not import private portfolio data or sibling-repository content.
  • Do not publish packages, deploy Workers, or sign manifests as part of code changes.
  • Never copy signing keys, Wrangler credentials, or local environment files.
  • Keep runtime access read-only and stateless.

Delivery

Keep changes focused. Run the relevant checks and report their real results. Publishing, deployment, signing, and registry release work require separate operator authorization.

Pinned dependency notes:

  • vite stays at 6.4.3, the currently tested Vite 6 release used with Vitest 5.0.3. Major upgrades are outside the current scope.
  • The undici override holds Wrangler's Miniflare dependency to the v7 API line while Miniflare declares 7.29.1; the lockfile resolves the compatible v7 release without moving to a new major.
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. 23d ago Changed · -4 lines · -71 tokens per session 8edc47bfa0a9
  2. 1mo ago Changed · +7 tokens per session a65d01435a0e
  3. 1mo ago Changed · +20 lines · +122 tokens per session 309ef12c24b5
  4. 2mo ago First seen · 38 lines · 324 tokens per session scan A 9f00c980809a

Subscribe to this mod's changes

portfolio-mcp AGENTS.md is an instructions file published in the GitHub repository saagpatel/portfolio-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 382 tokens to every session, about $0.0015 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 2026-08-31.

Related

portfolio-mcp AGENTS.md compared with instructions from other repositories

portfolio-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
portfolio-mcp AGENTS.mdsaagpatel/portfolio-mcpInstructions file03d agoMITA382Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode