What is LongTable AGENTS.md?

Project instructions for LongTable, a research workspace and software refactoring project. They define which documents are authoritative and how agents should describe the system and record design decisions.

Use them when designing LongTable, editing its PRD or specification, adding supporting design records, or deciding where canonical project guidance belongs.

They give contributors a shared set of working and editing rules, reducing inconsistent architecture decisions and documentation. The instructions also separate research concepts from provider-specific agent settings.

How HosungYou/LongTable configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to HosungYou/LongTable. 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/HosungYou/LongTable/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/HosungYou/LongTable

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hosungyou/longtable/agents-md/github.svg)](https://agentmods.dev/instructions/hosungyou/longtable/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/hosungyou/longtable/agents-md"><img src="https://agentmods.dev/badge/instructions/hosungyou/longtable/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hosungyou/longtable/agents-md"><img src="https://agentmods.dev/badge/instructions/hosungyou/longtable/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 659 This file is loaded in full into every session.

When invoked 659 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.

Model	Per session	Once invoked
Fable 5.1	$0.00659	$0.00659
Opus 5.5	$0.00264	$0.00264
Sonnet 5.5	$0.00132	$0.00132
Haiku 4.5	$0.00066	$0.00066

Measured 22d ago against content hash dab09d68d358, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

LongTable 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 22d 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 · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This directory contains the refactoring source of truth for LongTable and is also a LongTable research workspace.

Purpose

Use this directory to design the next architecture for LongTable before implementation changes are made elsewhere.

Working Rules

Treat PRD.md and Spec.md as the primary documents.
Treat files under docs/ as supporting design records.
Do not define provider-specific behavior in a way that becomes the core product contract.
Prefer researcher-centered harness language over AI assistant language.
Checkpoints must be defined by research meaning, not by agent identity alone.
Memory must distinguish explicit state, inferred hypotheses, and open tensions.
.claude and .codex should be treated as adapter outputs, not as the canonical source.

Editing Rules

Keep documents concise and decision-oriented.
When adding a new design document, cross-link it from Spec.md or docs/MIGRATION-MAP.md.
Avoid inventing terminology when established language is good enough.
If a new mechanism affects researcher trust, checkpoint behavior, or profile inference, document the rationale explicitly.

Required Supporting Docs

docs/ARCHITECTURE.md
docs/CHECKPOINTING.md
docs/MEMORY.md
docs/PROVIDER-STRATEGY.md
docs/MIGRATION-MAP.md

Implementation Boundary

This folder is for architecture and refactoring design. Do not treat it as the production runtime.

Runtime Contract

Treat researcher interaction as the primary task.
Read .longtable/current-session.json before giving substantial guidance.
Use .longtable/project.json as stable project context.
Use .longtable/state.json as layered working memory.
Prefer currentGoal, currentBlocker, nextAction, and openQuestions over generic assumptions.
Treat AGENTS.md as runtime guidance, not as the researcher-facing resume artifact.

Invocation Rules

If the user message starts with lt , longtable , long table , or 롱테이블 followed by a directive and :, treat it as an explicit LongTable invocation.
Supported explicit directives are: explore, review, critique, draft, commit, panel, status, editor, reviewer, methods, theory, measurement, ethics, voice, venue.
For explicit LongTable invocations, do not begin by scanning the workspace. Use the current session files first and answer as LongTable immediately.
For general research requests in this workspace, prefer LongTable behavior before generic coding behavior.

Read the full file on GitHub · 62 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.

22d ago Changed · -9 lines · -91 tokens per session dab09d68d358
2mo ago First seen · 71 lines · 750 tokens per session scan A ce9aaddb0e51

Subscribe to this mod's changes

LongTable AGENTS.md is an instructions file published in the GitHub repository HosungYou/LongTable (6 stars, last pushed 22d ago), licensed MIT. It adds 659 tokens to every session, about $0.0026 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.

Claude Code academic-research codex human-in-the-loop mcp open-science

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).

microsoft/vscode · 9,715 tokens

LongTable: Instructions file for Codex