Borrowing it
Nothing to install: this file belongs to hamidi-dev/opentab. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hamidi-dev/opentab/main/AGENTS.mdgit clone --depth 1 https://github.com/hamidi-dev/opentabWrote 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/hamidi-dev/opentab/agents-md)<a href="https://agentmods.dev/instructions/hamidi-dev/opentab/agents-md"><img src="https://agentmods.dev/badge/instructions/hamidi-dev/opentab/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.
<a href="https://agentmods.dev/instructions/hamidi-dev/opentab/agents-md"><img src="https://agentmods.dev/badge/instructions/hamidi-dev/opentab/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00936 | $0.00936 |
| Opus 5.5 | $0.00374 | $0.00374 |
| Sonnet 5.5 | $0.00187 | $0.00187 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
opentab 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 today.
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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on OpenTab
OpenTab browses local AI usage and spend in a curses TUI and a self-contained web
report. It reads multiple harnesses through a shared store interface. The PyPI
distribution is opentab-ai; the import package and command are opentab.
Read for the task
Start with Architecture for the package map. Read the relevant topic, not the entire documentation tree:
| Working on | Reference |
|---|---|
| Setup, tests, commits, releases | Contributing |
| A store, token accounting, deduplication, subagents, retention | Backend accounting; harness setup and schemas |
Startup, reload, caches, cost, --goto |
Startup and caching |
| TUI state, navigation, tables, colours, traces | TUI internals; user controls |
Costs, model rates, $, P, w |
Pricing |
| Notes, XDG files, demo, export privacy | Privacy |
| HTML payload, browser state, live server | Web browser |
| Fleet summaries, pulls, remote sessions | Multiple machines |
| Environment diagnosis, portability | Troubleshooting; Windows/WSL |
The website, the in-browser app (site/) |
Website |
Non-negotiable constraints
- Python 3.9+. Standard library only at runtime, except Windows-only
windows-curses. No new runtime dependencies. - Harness databases, transcripts and auth files are read-only. Writes belong to
OpenTab's own files or explicitly requested exports; use
persistence/paths.pyfor XDG paths. - Notes are authored data: locked read-modify-write, atomic save on each edit, no overwrite of malformed files, preserve unknown entries, never prune missing IDs.
- Keep imports acyclic and stores independent of the TUI. Use
TYPE_CHECKINGfor annotation-only back-references; preserve the top-level public API exports. - Recorded cost, API-equivalent estimates (
$), and session-only rate comparisons (w) are distinct. Never turnwinto an app-wide repricing mode. - Keep the model scan deferred until after the first TUI paint. Session extras
and content stay lazy; raw traces enter web payloads only with
--allow-raw-content, never rollup caches, fleet payloads, the served page cache, or programmatic output without the existing gate. - Demo must not expose real notes or traces, persist preferences, or launch/copy sessions. Treat selective anonymization as selective, not fully private.
- Do not hand-edit
src/opentab/data/models.json; regenerate it withscripts/update_prices.py.
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.
- today Changed · +2 lines · +27 tokens per session 4a36d083c83b
- 4d ago Changed · +1 lines · +22 tokens per session 02ceb4e1691c
- 1mo ago Changed · +3 tokens per session 8c8da287db97
- 1mo ago First seen · 70 lines · 884 tokens per session scan A bcf7a88c10ce
opentab AGENTS.md is an instructions file published in the GitHub repository hamidi-dev/opentab (95 stars, last pushed today), licensed MIT. It adds 936 tokens to every session, about $0.0037 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 2026-09-06.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.