What is tripsage-ai AGENTS.md?

A project instruction file for coding agents working on TripSage AI, a travel application. It describes the application's technology, external services, coding behavior, planning, research, and output rules.

Use it when developing TripSage's travel features, interface, data handling, payments, email, external travel APIs, or agent workflows.

It gives agents a shared description of the system and constraints, reducing incorrect changes and inconsistent decisions.

How BjornMelin/tripsage-ai configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to BjornMelin/tripsage-ai. 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/BjornMelin/tripsage-ai/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/BjornMelin/tripsage-ai

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/bjornmelin/tripsage-ai/agents-md/github.svg)](https://agentmods.dev/instructions/bjornmelin/tripsage-ai/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/bjornmelin/tripsage-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/bjornmelin/tripsage-ai/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/bjornmelin/tripsage-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/bjornmelin/tripsage-ai/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 7,575 This file is loaded in full into every session.

When invoked 7,575 The same file — it is already loaded in full.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.07575	$0.07575
Opus 5.5	$0.03030	$0.03030
Sonnet 5.5	$0.01515	$0.01515
Haiku 4.5	$0.00758	$0.00758

Measured 2mo ago against content hash 8b836702aef4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

tripsage-ai AGENTS.md scanned grade C with 1 finding 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 2mo 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Safety:** No destructive commands (`rm -rf`, `git reset --hard`) unless requested. Never commit secrets. Delete obsolete files as part of replacements.

AGENTS.md · 324 lines

How it starts

The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md – TripSage AI Contract

This file defines required rules for all AI coding agents in this repo. If anything conflicts, AGENTS.md wins.

0. Architecture and Stack

Frontend-first: All features at repository root. Next.js 16, React 19, TypeScript 6.
Data/State: Zod v4, Zustand v5, React Query v5, React Hook Form.
Backend: Supabase SSR, Upstash (Redis/Ratelimit/QStash), OpenTelemetry.
UI: Radix UI primitives, Tailwind CSS + CVA + clsx, Lucide icons.
External APIs: Amadeus (travel), Stripe (payments), Resend (email).

1. Agent Persona and Global Behavior

Tone: Precise, technical, concise. No buzzwords/emojis.
Correctness first: Never sacrifice for brevity. Include trade‑offs for complex tasks; mark unknowns as UNVERIFIED.
Autonomy: Use tools without asking. Maintain TODO list via update_plan.
Safety: No destructive commands (rm -rf, git reset --hard) unless requested. Never commit secrets. Delete obsolete files as part of replacements.
Evidence: Prefer primary docs (AGENTS.md, official docs, docs/) over blogs. Cite web research; mark inferences.
Output: Plain text with bullets/inline code by default; JSON only when requested/tool-required; reference file paths instead of code blocks.

2. Planning, Tools, and Research

2.1 Planning and investigation

For any non‑trivial or multi‑step change, use zen.planner plus update_plan (with exactly one in_progress step).
For design trade‑offs, use zen.consensus with weights: Solution Leverage 35%, Application Value 30%, Maintenance 25%, Adaptability 10%.

2.2 Search and documentation tools

Code and API questions: Use context7(resolve-library-id → get-library-docs),then exa.get_code_context_exa.
Research/web search: Use exa.web_search_exa.
Scraping/Crawling: Use exa.crawling_exa.

3. Project Layout and Responsibilities

Primary app (root): Next.js 16 workspace at repo root. Core AI in src/app/api/** route handlers. Shared schemas/types in src/domain/schemas (reuse server/client). Structure: src/app, src/components, src/lib, src/hooks, src/stores, src/domain, src/ai, src/prompts, src/styles, src/test, src/test-utils, src/__tests__.
Infrastructure: Scripts in scripts/; containers in docker/; tests in src/**/__tests__; docs in docs/; e2e tests in e2e/.

Read the full file on GitHub · 324 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.

2mo ago First seen · 324 lines · 7,575 tokens per session scan C 8b836702aef4

Subscribe to this mod's changes

tripsage-ai AGENTS.md is an instructions file published in the GitHub repository BjornMelin/tripsage-ai (40 stars, last pushed 25d ago), licensed MIT. It adds 7,575 tokens to every session, about $0.0303 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ai-agents budget-optimization flight-search itinerary-generator multi-agent-system supabase

tripsage-ai AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tripsage-ai AGENTS.mdBjornMelin/tripsage-ai	Instructions file	40	25d ago	MIT	C	7,575	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

tripsage-ai: Instructions file for Codex