lastlight AGENTS.md

A pointer for Last Light, a monorepo—a repository containing multiple related applications or packages—to its main agent guidance and package-specific instructions.

In plain words
What is it for?
Use it when starting work in the Last Light repository, especially before changing packages or the server application.
Why use it?
It tells agents where the single source of truth is and prevents them from treating duplicated pointer files as separate rules.

Instructions file for CodexOpenCode

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/nearform/lastlight/agents-md
Clone the repo
git clone --depth 1 https://github.com/nearform/lastlight

Made for: Codex, OpenCode.

Per session 120 This file is loaded in full into every session.
When invoked 120 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 $0.00120 $0.00120
Opus 5 $0.00060 $0.00060
Sonnet 5 $0.00024 $0.00024
Haiku 4.5 $0.00012 $0.00012

Measured 3d ago against content hash 545a03e51695, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lastlight 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 3d 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 · 10 lines

What it actually says

Last Light monorepo

The canonical guidance for agents lives in CLAUDE.md — start there for workspace orientation (packages, dependency graph, commands), and follow its links to the per-package CLAUDE.md files (the full dev guide is apps/server/CLAUDE.md).

AGENTS.md files in this repo are pointers to the co-located CLAUDE.md, which is the single source of truth — they are never duplicated.

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. 3d ago First seen · 10 lines · 120 tokens per session scan A 545a03e51695

Subscribe to this mod's changes

lastlight AGENTS.md is an instructions file published in the GitHub repository nearform/lastlight (22 stars, last pushed 6d ago), licensed MIT. It adds 120 tokens to every session, about $0.0006 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.