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.
npx agentmods add instructions/affromero/flight-finder/agents-mdgit clone --depth 1 https://github.com/affromero/flight-finderWrote 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/affromero/flight-finder/agents-md)<a href="https://agentmods.dev/instructions/affromero/flight-finder/agents-md"><img src="https://agentmods.dev/badge/instructions/affromero/flight-finder/agents-md.svg" alt="Measured on agentmods" 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 | $0.01022 | $0.01022 |
| Opus 5 | $0.00511 | $0.00511 |
| Sonnet 5 | $0.00204 | $0.00204 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
flight-finder 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 6d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working on Flight Finder, a self-hosted flight price tracker. This is the cross-tool entry point. See CLAUDE.md for the deeper conventions and the "Altitude" design system, README.md for the product overview, and API.md for the runtime HTTP API you can call against a running instance.
Stack
TypeScript (strict) monorepo on Node >= 22, npm workspaces. Next.js 16 (App
Router, React 19) web app, Prisma 7 over PostgreSQL 16, Redis 7 for caching and
rate limiting, Playwright for scraping, Vitest for tests. Secrets come from
Doppler, never .env files.
Setup
npm install
docker compose up -d db redis # or: make setup
npm run db:push # apply the Prisma schema
npm run db:generate # generate the Prisma client
npm run dev # Next.js web app on http://localhost:3003
make dev wraps the database, Redis, and dev-server steps.
Checks (run before every commit and PR)
npm run ci # lint + typecheck + test + build (web) + build (cli)
# or individually:
npm run lint # ESLint, both workspaces, --max-warnings 0
npm run typecheck # tsc strict, both workspaces
npm run test # Vitest, both workspaces
npm run ci must pass before you push; GitHub Actions runs the same gate. Linting
is zero-warnings and typecheck is strict (noUncheckedIndexedAccess).
Monorepo layout
apps/web: the Next.js app and API backend (@flight-finder/web). Prisma schema atapps/web/prisma/schema.prisma; core logic underapps/web/src/lib/(auth, prisma, redis, notifications, scraper).packages/cli: the Ink/React terminal UI (@flight-finder/cli). It reuses the scraper fromapps/webvia relative imports.apps/desktop: the Tauri (Rust) launcher. It is not an npm workspace and is built and versioned on its own.
All four version points (root, apps/web, packages/cli, apps/desktop) are kept
in lockstep; the /create-release flow bumps them together.
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.
- 6d ago First seen · 90 lines · 1,022 tokens per session scan A 435f0908b978
flight-finder AGENTS.md is an instructions file published in the GitHub repository affromero/flight-finder (145 stars, last pushed yesterday), licensed MIT. It adds 1,022 tokens to every session, about $0.0051 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 2026-08-30.
Other instructions, from other repositories
full-stack-ai-agent-template CLAUDE.md
Claude Code instructions for vstorm-co/full-stack-ai-agent-template, covering claude.md, project overview, commands, install dependencies and run tests.
full-stack-ai-agent-template AGENTS.md
AGENTS.md instructions for vstorm-co/full-stack-ai-agent-template, covering agents.md, project overview, commands, cli and architecture.
ODS CLAUDE.md
Claude Code instructions for Osmantic/ODS, covering claude.md, project overview, repository structure, build & development commands and linting and validation.
nosia AGENTS.md
AGENTS.md instructions for dilolabs/nosia, covering 37signals rails configuration, tech stack, architecture, core philosophy and key commands.
FastGPT AGENTS.md
AGENTS.md instructions for labring/FastGPT, covering agents.md, 项目概述, 设计文档, 架构 and packages (库代码).
tutor-management-app CLAUDE.md
Instructions for t1112000/tutor-management-app, covering claude.md, commands, architecture, auth and page pattern.