agentmods.dev

fli: Instructions file for Codex

AGENTS.md

fli AGENTS.md is an instructions file for Codex, OpenCode from punitarani/fli. It costs 794 tokens per session, scanned A, original, MIT.

A project instruction guide for Fli, a Python library and command-line tool that retrieves Google Flights data. It documents installation, formatting, tests, the command-line tool, the server interface, and release steps.

In plain words
What is it for?
Use it to install dependencies, lint, format, test, run the flight-search tools, start the server interface, and prepare manual releases.
Why use it?
It gives a coding agent the project's normal commands and warns which tests depend on the live Google Flights service and may fail because of rate limits.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is punitarani/fli's own configuration. It tells Codex and OpenCode how to work on fli 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 fli configures →

not rated 3.5krepo +33 changed 1mo ago A scan 794 tokens original MIT
View source ↗ punitarani/fli deepwiki.com
About the project

Fli is a Python library, command-line tool, and MCP server for searching Google Flights data programmatically. Travelers and software agents use it to search flights, compare dates, filter results, and find cheaper travel options. The catalogue entries provide instructions and a skill for using Fli.

punitarani/fli · 3,480 stars · on GitHub · deepwiki.com

Reuse

Borrowing it

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

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 fli AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/punitarani/fli/agents-md"><img src="https://agentmods.dev/badge/instructions/punitarani/fli/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 794 This file is loaded in full into every session.
When invoked 794 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 $0.00794 $0.00794
Opus 5.5 $0.00318 $0.00318
Sonnet 5.5 $0.00159 $0.00159
Haiku 4.5 $0.00079 $0.00079

Measured 1mo ago against content hash 36493ae552aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fli 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 1mo 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 · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Cursor Cloud specific instructions

Overview

Fli is a Python library providing programmatic access to Google Flights data via reverse-engineered API. It offers a CLI (fli), MCP server (fli-mcp / fli-mcp-http), and Python API. No external services (databases, caches, etc.) are required.

Development commands

All standard commands are in the Makefile and CLAUDE.md. Key ones:

  • Install deps: uv sync --all-extras
  • Lint: make lint (ruff)
  • Format: make format
  • Tests: make test (standard, offline), make test-all (including fuzz, still offline), make test-live (small stable live set, real network), make test-live-fuzz (adds the noisier fuzz-gated live test, opt-in only)
  • CLI: uv run fli flights JFK LAX 2026-05-15
  • MCP HTTP server: uv run fli-mcp-http (serves at http://127.0.0.1:8000/mcp/)

Testing caveats

  • Almost all tests, including most of tests/search/, run entirely offline against captured fixtures/stubs — no network access is required and none of them are rate-limited.
  • A small number of tests are marked live because they call the real Google Flights API: test_search_flights_new_filters_live.py, the parametrized case in test_search_flights_fuzz.py, the four search tests in tests/mcp/test_mcp_server.py::TestMCPServer, and a handful of previously-unmocked cases in test_search_flights.py / test_search_dates.py. These are skipped unless --live is passed (--all does not enable them), so make test / make test-all never hit the network. --fuzz, --live and --all are independent skip-only gates: a test needs every gate that applies to it passed together (the fuzz-gated live case needs both --all/--fuzz and --live at once — -m live --live alone silently drops it from collection). Run make test-live (pytest -m live --live, no --all) for the small, stable live set if you have network access — the same set that runs daily in .github/workflows/live-canary.yml, which retries one failed batch after a short pause before filing/updating a GitHub issue. make test-live-fuzz additionally runs the 100-case fuzz-gated live test, which is noticeably flakier under its back-to-back burst (~11% per-case failures measured) and is opt-in only — never scheduled. Any of these may skip on a transient transport failure but fail on an actual regression.

Read the full file on GitHub · 53 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. 1mo ago Changed · +15 lines · +335 tokens per session 36493ae552aa
  2. 2mo ago First seen · 38 lines · 459 tokens per session scan A 75400bfc3300

Subscribe to this mod's changes

fli AGENTS.md is an instructions file published in the GitHub repository punitarani/fli (3,480 stars, last pushed 1mo ago), licensed MIT. It adds 794 tokens to every session, about $0.0032 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 2026-08-30.

apiflights-apigoogle-flightsgoogle-flights-apimcpmcp-server
Related

fli AGENTS.md compared with instructions from other repositories

fli AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
fli AGENTS.mdpunitarani/fliInstructions file3.5k1mo agoMITA794Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode