webmcp-sdk: Instructions file for Codex

AGENTS.md

webmcp-sdk AGENTS.md is an instructions file for Codex, OpenCode from up2itnow0822/webmcp-sdk. It costs 510 tokens per session, scanned A, original, MIT.

Repository instructions for maintaining a secure browser-tool software development kit and a reference studio. They define ownership, safety limits, supported APIs, and required regression coverage.

In plain words
What is it for?
Use them when working on the webmcp-sdk repository, especially for browser tools, payments, security behavior, ownership boundaries, or regression tests.
Why use it?
They give coding agents project-specific rules before they edit files. This helps prevent unsafe payment handling, unsupported security claims, and changes without tests.

Instructions file for CodexOpenCode

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

This is up2itnow0822/webmcp-sdk's own configuration. It tells Codex and OpenCode how to work on webmcp-sdk 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 webmcp-sdk configures →

Reuse

Borrowing it

Nothing to install: this file belongs to up2itnow0822/webmcp-sdk. 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/up2itnow0822/webmcp-sdk/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/up2itnow0822/webmcp-sdk

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 webmcp-sdk AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/up2itnow0822/webmcp-sdk/agents-md/github.svg)](https://agentmods.dev/instructions/up2itnow0822/webmcp-sdk/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/up2itnow0822/webmcp-sdk/agents-md"><img src="https://agentmods.dev/badge/instructions/up2itnow0822/webmcp-sdk/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 webmcp-sdk AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/up2itnow0822/webmcp-sdk/agents-md"><img src="https://agentmods.dev/badge/instructions/up2itnow0822/webmcp-sdk/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 510 This file is loaded in full into every session.
When invoked 510 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 $0.00510 $0.00510
Opus 5.5 $0.00204 $0.00204
Sonnet 5.5 $0.00102 $0.00102
Haiku 4.5 $0.00051 $0.00051

Measured 25d ago against content hash 8430fb183d0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

webmcp-sdk 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 25d 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 · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Maintain a secure browser-tool SDK and non-custodial reference studio. Never claim absolute security or fabricate payment outcomes.

Ownership

Coordinator alone owns package/lock files, dependency installs, source exports, root integration/docs, staging, commits and GitHub updates. Workers own the domains assigned by coordinator; no spawning, stages or commits.

Contracts

  • Read owning instructions before edits; update DOX after meaningful changes.
  • Explicit user review and wallet authorization precede financial execution; no key/seed entry, custody, automatic agent signing or real funds in tests.
  • Fail closed on absent confirmation, unsafe input, unsupported payment route, stale account/chain/policy and unverified settlement. Immutable intents; ambiguous submitted transactions stay pending.
  • Bound input, admission/queue/deadlines and retain leases until underlying work actually quiesces; cancellation is cooperative. Redacted complete security audit needs a real sink.
  • Modern native API uses document.modelContext/execute/async readiness/registration AbortSignals; legacy is explicit.
  • Every changed behavior requires RED/GREEN regression coverage. Source repairs must survive a full release gate and independent review.
  • User explicitly authorized merging the reviewed security PR into main on 2026-10-15 UTC after all report fixes and complete PR Automerge gates pass. This supersedes the prior merge-only approval gate. No registry publication, production deployment or funded transactions are authorized.

Recovery

Scratch maintenance removed unpushed repairs. Fresh baseline restored from GitHub blobs and SHA verified; tree matches 4881c2fbe372e05a733c7117a413c4ab587c3069. Prior test counts are historical until reconstructed work is freshly verified. Push verified progress frequently to prevent loss.

Verification

Coordinator restores verify:release: SDK/app typechecks/tests/builds, packed consumers, actual native/CSP/browser/accessibility flows, Python tests and npm audit. Workers report commands and evidence, not completion guarantees.

Read the full file on GitHub · 30 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. 25d ago First seen · 30 lines · 510 tokens per session scan A 8430fb183d0e

Subscribe to this mod's changes

webmcp-sdk AGENTS.md is an instructions file published in the GitHub repository up2itnow0822/webmcp-sdk (3 stars, last pushed today), licensed MIT. It adds 510 tokens to every session, about $0.0020 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 2026-10-15.

Related

webmcp-sdk AGENTS.md compared with instructions from other repositories

webmcp-sdk AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
webmcp-sdk AGENTS.mdup2itnow0822/webmcp-sdkInstructions file3todayMITA510Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot