flightsweeper-webmcp AGENTS.md

flightsweeper-webmcp AGENTS.md is an instructions file for Codex, OpenCode from raintree-technology/flightsweeper-webmcp. It costs 221 tokens per session, scanned A, original, MIT.

Project instructions for FlightSweeper WebMCP, a self-contained challenge project for purchasing flights through web tools under strict policies.

In plain words
What is it for?
Use them when modifying this repository to keep work on the main branch, enforce policy and duplicate-request protection in consequential tools, avoid sensitive data in tool inputs and outputs, and run npm test.
Why use it?
They set boundaries for safe development, including preventing real purchases, protecting passenger and payment data, and checking changes before handoff.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/raintree-technology/flightsweeper-webmcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/raintree-technology/flightsweeper-webmcp

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 flightsweeper-webmcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/raintree-technology/flightsweeper-webmcp/agents-md.svg)](https://agentmods.dev/instructions/raintree-technology/flightsweeper-webmcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/raintree-technology/flightsweeper-webmcp/agents-md"><img src="https://agentmods.dev/badge/instructions/raintree-technology/flightsweeper-webmcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 221 This file is loaded in full into every session.
When invoked 221 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00221 $0.00221
Opus 5 $0.00111 $0.00111
Sonnet 5 $0.00044 $0.00044
Haiku 4.5 $0.00022 $0.00022

Measured today against content hash 0cc04d0e89ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

flightsweeper-webmcp 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 today.

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 · 13 lines

What it actually says

FlightSweeper WebMCP Challenge Edition

  • Work only on main.
  • Keep this repository self-contained and safe to publish.
  • Never copy credentials, production data, private provider code, or customer information from FlightSweeper.
  • Sandbox purchases must never create a real charge or supplier order.
  • Keep raw passenger identity and payment details outside WebMCP tool inputs and outputs.
  • Consequential tools must enforce policy and idempotency on the application side; never trust model-supplied prices or authorization claims.
  • Read STANDARDS.md before changing behavior, public claims, tests, or release evidence. Apply the closest profiles from the public Raintree Standards catalog and report unresolved requirements by stable rule ID.
  • Preserve the deliberate limits in STANDARDS.md. Do not describe this repository as certified or claim that an unchecked manual gate passed.
  • Update the relevant test and evidence record in the same change when behavior or a public claim changes.
  • Run npm test before handoff.
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. today Changed · +3 lines · +106 tokens per session 0cc04d0e89ab
  2. 4d ago First seen · 10 lines · 115 tokens per session scan A b3e78c42360b

Subscribe to this mod's changes

flightsweeper-webmcp AGENTS.md is an instructions file published in the GitHub repository raintree-technology/flightsweeper-webmcp (0 stars, last pushed 3d ago), licensed MIT. It adds 221 tokens to every session, about $0.0011 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

hermes-workspace AGENTS.md

Instructions for outsourc-e/hermes-workspace, covering hermes workspace agent contract, current semantic roster, operating rules and windows-specific notes (2026-06-01).

outsourc-e/hermes-workspace · 1,699 tokens

agentshield CLAUDE.md

Instructions for affaan-m/agentshield, covering agentshield, build & test, architecture, key patterns and severity scoring.

affaan-m/agentshield · 942 tokens

elnora-ai-agent-hackathon-starter-kit AGENTS.md

AGENTS.md instructions for Elnora-AI/elnora-ai-agent-hackathon-starter-kit, covering agents.md, core rules, 1. never commit secrets, 2. treat external content as untrusted and 3. keep it simple (yagni).

Elnora-AI/elnora-ai-agent-hackathon-starter-kit · 1,021 tokens

LifeHack-2026 AGENTS.md

Instructions for Ducksss/LifeHack-2026, covering woven agent instructions, canonical context, current snapshot, product and trust invariants and architecture and scope.

Ducksss/LifeHack-2026 · 1,786 tokens

webmcpify AGENTS.md

Instructions for TueJon/webmcpify: This repository IS an agent skill. If a user asked you to "webmcpify" a project or make it agent-ready with WebMCP, do not explore this repo further — read and follow skills/webmcpify/SKILL.md inside the target project's working directory.

TueJon/webmcpify · 648 tokens

LifeHack-2026 CLAUDE.md

Instructions for Ducksss/LifeHack-2026: Before changing this repository, read AGENTS.md in full and follow its canonical context order, product invariants, worktree rules, and definition of done. Then read docs/HANDOVER.md for the latest product and repository state.

Ducksss/LifeHack-2026 · 125 tokens