What is ghostlight AGENTS.md?

A repository guide for Ghostlight that tells coding agents what project documents to read, in what order, and which records define the project’s current decisions and status.

Use it when starting work in the Ghostlight repository, especially before changing a subsystem or reviewing its architecture.

It helps agents recover the project’s history and rules instead of relying on memory or making conflicting changes.

How sylin-org/ghostlight configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to sylin-org/ghostlight. 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/sylin-org/ghostlight/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/sylin-org/ghostlight

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/sylin-org/ghostlight/agents-md/github.svg)](https://agentmods.dev/instructions/sylin-org/ghostlight/agents-md)

Your own site

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

Per session 4,666 This file is loaded in full into every session.

When invoked 4,666 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	$0.04666	$0.04666
Opus 5.5	$0.01866	$0.01866
Sonnet 5.5	$0.00933	$0.00933
Haiku 4.5	$0.00467	$0.00467

Measured 14d ago against content hash 500c21532197, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ghostlight 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 14d 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 · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ghostlight -- agent guide

This is the canonical onboarding document for any coding agent (or human) working in this repository, regardless of which tool or model you are. CLAUDE.md is a thin pointer here. Assume you have no memory of prior sessions: everything you need is in this file and the documents it points to.

Branches

There are only two branches: main and dev, locally and on the remote. main contains the published product. All implementation, experiments, dependency updates and release preparation happen on dev. Do not create feature, agent or release branches. Advance main from dev only after the release is publicly delivered with its compatible adapter. The one exception is the 2.0 cutover, where main advances right after v2.0.0 becomes the latest release and before the staged extension is published, because the short install commands fetch their scripts from main (ADR-0200, second amendment of 2026-10-16). Preserve historical work in archive tags and pending edits in Git stashes; never discard it to clean up branch names.

Read this first (in order)

docs/MEMORY.md -- standing owner directives and durable learnings, with a pointer to the documentation map.
The current-state sections at the top of docs/STATUS.md: in-flight work, branch state, and any release in progress. Older dated sections are history; read them only when relevant.
Before changing a subsystem, read its ADRs (index: docs/adr/README.md) and the docs/1.0 contract that covers it (INTENT, LANGUAGE, ARCHITECTURE, ACCEPTANCE). ADRs are authoritative. Do not re-litigate or silently contradict one. To change a decision, write a new ADR or a marked amendment, never rewrite history.

Read on demand: docs/SPEC.md (deep governance rationale; ADRs win), docs/DEV-LOOP.md (required before any build/run/deploy on a dev machine), CONTRIBUTING.md (test tiers and PR expectations).

Read the full file on GitHub · 300 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.

14d ago Changed · +14 lines · +275 tokens per session 500c21532197
17d ago Changed · +46 lines · +998 tokens per session eb7d199541a7
1mo ago Changed · +9 lines · +104 tokens per session 50b7f8f070e4
1mo ago Changed · -4 tokens per session 33b7d7b46427
2mo ago First seen · 231 lines · 3,293 tokens per session scan A e2f1f03fc011

Subscribe to this mod's changes

ghostlight AGENTS.md is an instructions file published in the GitHub repository sylin-org/ghostlight (1 stars, last pushed 8d ago), licensed Apache-2.0. It adds 4,666 tokens to every session, about $0.0187 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.

access-control ai-agents browser-automation browser-extension chromium developer-tools

ghostlight AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ghostlight AGENTS.mdsylin-org/ghostlight	Instructions file	1	8d ago	Apache-2.0	A	4,666	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

ghostlight: Instructions file for Codex