Borrowing it
Nothing to install: this file belongs to jszmajda/lid. 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/jszmajda/lid/main/AGENTS.mdgit clone --depth 1 https://github.com/jszmajda/lidWrote 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/jszmajda/lid/agents-md)<a href="https://agentmods.dev/instructions/jszmajda/lid/agents-md"><img src="https://agentmods.dev/badge/instructions/jszmajda/lid/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/jszmajda/lid/agents-md"><img src="https://agentmods.dev/badge/instructions/jszmajda/lid/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 | $0.02136 | $0.02136 |
| Opus 5.5 | $0.00854 | $0.00854 |
| Sonnet 5.5 | $0.00427 | $0.00427 |
| Haiku 4.5 | $0.00214 | $0.00214 |
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 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 — 110 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/). - Three Claude Code plugins under
plugins/(two core, one opt-in experimental) — richest integration, with auto-invoking skills and slash commands. Cursor reads the same plugins through its own manifests. - 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). Seedocs/setup.mdfor per-tool setup.
There is no build system or application code. The plugins are prose (skills, references, templates); the only executable code is maintainer tooling under tools/ (the alternate-model eval runner and the packaging checks), which ships in no plugin. 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/: Three installable plugins (Claude Code and Cursor)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 skill (/arrow-maintenance) and brownfield bootstrap skill (/map-codebase)lid-experimental/: Opt-in experiments under evaluation (review-depth,bidirectional-differential)
.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 agentsdocs/: The HLD, LLDs, and EARS specs that define the projecttools/: Maintainer tooling that ships in no pluginalt-model-evals/: runs the skills' eval suites on non-Claude models (optional evidence, never a merge gate; seedocs/intent/alt-model-evals/)packaging-checks/: checks that the plugins are well-formed and load whole on a host (the merge gate; seedocs/intent/packaging-checks/); also regenerates the shipped workflow doc
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 · +5 lines · +201 tokens per session f4498ababe0b
- yesterday Changed 93432be7a097
- 16d ago Changed · +3 lines · +238 tokens per session 779e8f4740c4
- 1mo ago First seen · 102 lines · 1,697 tokens per session scan A 368a2af841df
lid AGENTS.md is an instructions file published in the GitHub repository jszmajda/lid (115 stars, last pushed yesterday), licensed MIT. It adds 2,136 tokens to every session, about $0.0085 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.
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.