agentmods.dev

lid AGENTS.md

lid AGENTS.md is an instructions file for Codex, OpenCode from jszmajda/lid. It costs 1,697 tokens per session, scanned A, original, MIT.

Repository instructions for coding agents working on the Linked-Intent Development project, a method for keeping a project's goals and code aligned. They also describe the repository structure, Claude Code plugins, and setup files for other coding tools.

In plain words
What is it for?
Explaining the project's purpose and folders, documenting its plugin system, and guiding setup for tools such as Cursor, Windsurf, GitHub Copilot, Aider, Continue, JetBrains Junie, Zed, and Codex.
Why use it?
It gives coding agents the project context and rules they need, so they can work consistently across different tools without guessing how the repository is organised.

Instructions file for CodexOpenCode

not rated 100 22d ago A scan 1,697 tokens original MIT
View the source file jszmajda/lid
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/jszmajda/lid/agents-md
Clone the repo
git clone --depth 1 https://github.com/jszmajda/lid

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 lid AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jszmajda/lid/agents-md.svg)](https://agentmods.dev/instructions/jszmajda/lid/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jszmajda/lid/agents-md"><img src="https://agentmods.dev/badge/instructions/jszmajda/lid/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,697 This file is loaded in full into every session.
When invoked 1,697 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01697 $0.01697
Opus 5 $0.00848 $0.00848
Sonnet 5 $0.00339 $0.00339
Haiku 4.5 $0.00170 $0.00170

Measured 4d ago against content hash 368a2af841df, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lid 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 4d 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 · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project instructions for coding agents working in this repository. The file is named AGENTS.md per the emerging cross-tool convention; tools that look for other filenames (e.g. Claude Code's CLAUDE.md) find the same content via symlink or adapter file.

Repository Purpose

This is the Linked-Intent Development (LID) project — a methodology for keeping intent and code coherent in agentic codebases. The repo ships:

  • The methodology itself (this document plus docs/).
  • Two Claude Code plugins under plugins/ — richest integration, with auto-invoking skills and slash commands.
  • Rule-file adapters for other agentic coding tools (Cursor, Windsurf, GitHub Copilot, Aider, Continue, JetBrains Junie, Zed, Codex, and any tool that reads AGENTS.md). See docs/setup.md for per-tool setup.

There is no build system, test suite, or application code. The repo is simultaneously the distribution source for the plugins and the canonical LID-on-LID reference — its own docs/ tree is LID applied to LID.

Structure

  • plugins/: Two installable Claude Code plugins
    • linked-intent-dev/: Core LID workflow skill (/linked-intent-dev), configuration skill (/update-lid), and principle-review coach (/lid-coach)
    • arrow-maintenance/: Arrow tracking overlay + /map-codebase command for brownfield bootstrap
  • .claude-plugin/marketplace.json: Claude Code plugin manifest (technical file — users install via /plugin marketplace add jszmajda/lid)
  • docs/setup.md: Per-tool setup instructions for non-Claude-Code agents
  • docs/: The HLD, LLDs, and EARS specs that define the project

Plugin Architecture (Claude Code)

Users install via:

/plugin marketplace add jszmajda/lid
/plugin install linked-intent-dev@jszmajda-lid
/plugin install arrow-maintenance@jszmajda-lid

The plugins form a layered system:

  1. linked-intent-dev is the core workflow — consult for ALL code changes. Every change walks the full arrow (HLD → LLD → EARS → Tests → Code) with a stop at each phase boundary. Bug fixes walk the same arrow — find where intent diverged and cascade from there; no short-circuit. Fresh projects start with /linked-intent-dev + a description of what to build (the workflow bootstraps LID inline). Established projects use /update-lid to reconcile drift, change modes, or refresh conventions.

Read the full file on GitHub · 102 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. 4d ago First seen · 102 lines · 1,697 tokens per session scan A 368a2af841df

Subscribe to this mod's changes

lid AGENTS.md is an instructions file published in the GitHub repository jszmajda/lid (100 stars, last pushed 22d ago), licensed MIT. It adds 1,697 tokens to every session, about $0.0085 per session on Opus 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.

LLMagentic-codingai-codingclaude-codeclaude-code-pluginears
Related

Other instructions, from other repositories

catalyst AGENTS.md

AGENTS.md instructions for coalesce-labs/catalyst, covering agents.md, what this repository is, agent philosophy, build & test and key principles.

coalesce-labs/catalyst · 6,878 tokens

infynon-cli CLAUDE.md

Instructions for d4rkNinja/infynon-cli, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

d4rkNinja/infynon-cli · 700 tokens

catalyst CLAUDE.md

Claude Code instructions for coalesce-labs/catalyst, covering claude code, loading & invocation, orchestration runtime, pull request review (codex) and code understanding (serena mcp).

coalesce-labs/catalyst · 836 tokens

infynon-cli AGENTS.md

Instructions for d4rkNinja/infynon-cli, covering agents, release tag guardrails and why this is required.

d4rkNinja/infynon-cli · 297 tokens

Clawness CLAUDE.md

Instructions for fullymiddleaged/Clawness, covering claude.md — working on clawness, what this is, architecture (request flow), key files and design decisions (don't undo without reading these).

fullymiddleaged/Clawness · 17,519 tokens

pg-aiguide CLAUDE.md

Claude Code instructions for timescale/pg-aiguide, covering tiger docs mcp server - development guidelines, build, test & run commands, code style guidelines and python (ingest/).

timescale/pg-aiguide · 419 tokens