airstrings-cli: Instructions file for Codex

AGENTS.md

airstrings-cli AGENTS.md is an instructions file for Codex, OpenCode from symbionix-sl/airstrings-cli. It costs 2,714 tokens per session, scanned A, original, MIT.

A set of AGENTS.md instructions for using AirStrings CLI, a command-line program for managing localized text in the AirStrings platform. It explains authentication, structured output, exit codes, commands, and paging.

In plain words
What is it for?
Use it when listing or changing projects, strings, locales, sections, bundles, and imports, including scripted workflows that need JSON output and retry handling.
Why use it?
It gives an AI agent the rules needed to run the CLI safely and interpret its results correctly.

Instructions file for CodexOpenCode

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

This is symbionix-sl/airstrings-cli's own configuration. It tells Codex and OpenCode how to work on airstrings-cli 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 airstrings-cli configures →

Reuse

Borrowing it

Nothing to install: this file belongs to symbionix-sl/airstrings-cli. 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/symbionix-sl/airstrings-cli/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/symbionix-sl/airstrings-cli

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 airstrings-cli AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/symbionix-sl/airstrings-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/symbionix-sl/airstrings-cli/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,714 This file is loaded in full into every session.
When invoked 2,714 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 $0.02714 $0.02714
Opus 5.5 $0.01086 $0.01086
Sonnet 5.5 $0.00543 $0.00543
Haiku 4.5 $0.00271 $0.00271

Measured 23d ago against content hash 7c64c3bbd421, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

airstrings-cli 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 23d 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 · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AirStrings CLI — agent guide

airstrings manages localized strings for the AirStrings platform. This file is the contract for driving it from an AI agent or script. Read it once; every command below is stable and machine-friendly.

Golden rules

  • Add --json to any command for structured stdout. Human text goes to stdout, errors and progress go to stderr.

  • Branch on the exit code, not on message text:

    code meaning retry?
    0 ok —
    1 generic error no
    2 usage / bad input no (fix the command)
    3 auth (bad/expired key) no (fix credentials)
    4 not found no
    5 network yes (backoff)
    6 rate limited yes (backoff)
    7 environment protected (production) no — publish to staging; a human promotes
    8 plan limit reached no — a human upgrades
    9 login pending yes — after the user approves the printed URL

    Exit 3 also covers a read key used for a write.

  • With --json, errors go to stderr as one JSON object: {"error":{"message":"…","next_step":"…","exit_code":7}}. next_step is the single action that unblocks you (a command or a dashboard link). MCP tool errors carry the same message and Next step: text.

  • Any command + --help/-h prints its help text and exits 0 — nothing is executed, no side effects. Safe to probe usage this way.

  • Unknown flags exit 2 (usage) — the command does not run. Fix the invocation.

  • Set NO_COLOR=1 (or just pipe — non-TTY auto-disables color) for clean output.

Auth — three ways

Login (one command after signup): airstrings init --json in the repo. With no key it logs in through the browser, stores an org key (as_org_…) in ~/.config/airstrings/credentials.json (0600), creates a project named after the folder and writes .airstrings/config.json. It never reuses a project by name: a name collision exits 2 and names the existing project (use --project <id> or --name <other>).

Read the full file on GitHub · 201 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. 23d ago Changed · +1 lines · +57 tokens per session 7c64c3bbd421
  2. 29d ago Changed · +16 lines · +300 tokens per session 37a23aac3095
  3. 1mo ago Changed · +24 lines · +428 tokens per session ed600c8f2c2c
  4. 1mo ago Changed · +26 lines · +397 tokens per session 7459c054a4c2
  5. 2mo ago First seen · 134 lines · 1,532 tokens per session scan A ba06b3cde63e

Subscribe to this mod's changes

airstrings-cli AGENTS.md is an instructions file published in the GitHub repository symbionix-sl/airstrings-cli (0 stars, last pushed 22d ago), licensed MIT. It adds 2,714 tokens to every session, about $0.0109 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 2026-08-31.

Related

airstrings-cli AGENTS.md compared with instructions from other repositories

airstrings-cli AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
airstrings-cli AGENTS.mdsymbionix-sl/airstrings-cliInstructions file022d agoMITA2,714Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode