agentmods.dev

tabstack-cli: Instructions file for Codex

AGENTS.md

tabstack-cli AGENTS.md is an instructions file for Codex, OpenCode from Mozilla-Ocho/tabstack-cli. It costs 2,600 tokens per session, scanned A, original, MIT.

A reference for controlling tabstack, a command-line tool, from an AI agent. It documents setup, commands, input and output formats, flags, and error codes.

In plain words
What is it for?
Use it to run tabstack commands, extract or generate JSON, automate tasks, and process research or automation output line by line.
Why use it?
It removes guesswork when automating tabstack, especially around authentication, machine-readable output, streamed results, and failed commands.

Instructions file for CodexOpenCode

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

This is Mozilla-Ocho/tabstack-cli's own configuration. It tells Codex and OpenCode how to work on tabstack-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 tabstack-cli configures →

not rated 12repo 3d ago A scan 2,600 tokens original MIT
View source ↗ Mozilla-Ocho/tabstack-cli tabstack.ai
Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mozilla-ocho/tabstack-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/mozilla-ocho/tabstack-cli/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,600 This file is loaded in full into every session.
When invoked 2,600 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 $0.02600 $0.02600
Opus 5.5 $0.01040 $0.01040
Sonnet 5.5 $0.00520 $0.00520
Haiku 4.5 $0.00260 $0.00260

Measured 2mo ago against content hash 1367e56af98d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tabstack-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 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.

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 · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using tabstack from an AI agent

This document tells an LLM agent how to drive the tabstack CLI correctly. It is a reference, not a tutorial: every command, flag, input format, output shape, and failure mode is listed so you can call the tool without guessing.

TL;DR for agents

  • Always pass -o json so output is deterministic and parseable. Without it, output is pretty-printed on a TTY and only switches to JSON when piped.
  • Provide an API key via the TABSTACK_API_KEY env var (preferred for automation) or --api-key. Do not rely on an interactive auth login prompt.
  • Branch on the exit code, not on stderr text: 0 ok, 1 runtime/network, 2 bad input or missing key, 3 API error or task failure.
  • extract json / generate json return exactly the JSON shape your schema describes. Nothing is wrapped or reshaped. Validate your schema before calling; malformed schemas fail locally with exit 2.
  • automate and research stream. In -o json they emit NDJSON (one JSON object per line); read line by line, do not JSON.parse the whole output.

Setup

export TABSTACK_API_KEY="<key>"        # preferred for non-interactive use
# optional:
export TABSTACK_BASE_URL="<url>"       # override API root

Key resolution precedence (highest first): --api-key flag → TABSTACK_API_KEY → config file (~/.config/tabstack/config.toml). If no key is found, commands that hit the API exit 2 (non-retryable config error) with a clear message.

Global flags (valid on every command)

Flag Effect
-o, --output pretty|json Set json for agents. Default auto-detects (pretty on TTY, json when piped).
--api-key <key> API key, overrides env + config.
--base-url <url> API root, overrides env + config.
--no-color Disable ANSI colour (also honours NO_COLOR). Irrelevant under -o json.
--timeout <dur> Timeout for non-streaming calls only, e.g. 30s, 2m. Ignored by automate/research.

Read the full file on GitHub · 225 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. 2mo ago First seen · 225 lines · 2,600 tokens per session scan A 1367e56af98d

Subscribe to this mod's changes

tabstack-cli AGENTS.md is an instructions file published in the GitHub repository Mozilla-Ocho/tabstack-cli (12 stars, last pushed 3d ago), licensed MIT. It adds 2,600 tokens to every session, about $0.0104 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.

Browser automation
Related

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

tabstack-cli AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
tabstack-cli AGENTS.mdMozilla-Ocho/tabstack-cliInstructions file123d agoMITA2,600Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA1,907GitHub Copilot