agentmods.dev

LivingAtlas: Instructions file for Codex

AGENTS.md

LivingAtlas AGENTS.md is an instructions file for Codex, OpenCode from ProvisioInsights/LivingAtlas. It costs 796 tokens per session, scanned A, original, MIT.

A set of instructions for the LivingAtlas repository, covering what work belongs in the checkout and how that work should be tracked and documented.

In plain words
What is it for?
Use it when making code, documentation, infrastructure, or test-fixture changes in the LivingAtlas project.
Why use it?
It gives coding agents a shared set of boundaries for GitHub work, system layers, privacy, and public-safe communication.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is ProvisioInsights/LivingAtlas's own configuration. It tells Codex and OpenCode how to work on LivingAtlas itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything LivingAtlas configures →

not rated 0repo 1mo ago A scan 796 tokens original MIT
View source ↗ ProvisioInsights/LivingAtlas
Reuse

Borrowing it

Nothing to install: this file belongs to ProvisioInsights/LivingAtlas. 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/ProvisioInsights/LivingAtlas/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ProvisioInsights/LivingAtlas

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 LivingAtlas AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/provisioinsights/livingatlas/agents-md/github.svg)](https://agentmods.dev/instructions/provisioinsights/livingatlas/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/provisioinsights/livingatlas/agents-md"><img src="https://agentmods.dev/badge/instructions/provisioinsights/livingatlas/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.

agentmods 80×15 button for LivingAtlas AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/provisioinsights/livingatlas/agents-md"><img src="https://agentmods.dev/badge/instructions/provisioinsights/livingatlas/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 796 This file is loaded in full into every session.
When invoked 796 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00796 $0.00796
Opus 5.5 $0.00318 $0.00318
Sonnet 5.5 $0.00159 $0.00159
Haiku 4.5 $0.00080 $0.00080

Measured 2mo ago against content hash 546c72834a96, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

LivingAtlas 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 2mo 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 · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

Repository Scope

Treat this checkout as the active Living Atlas repository for code, docs, tests, infrastructure templates, and synthetic fixtures.

GitHub Work Tracking

Use GitHub as the durable work ledger for this repository. Track Living Atlas work in GitHub Issues and the org project:

  • Project: ProvisioInsights project #3, Living Atlas Roadmap
  • URL: https://github.com/orgs/ProvisioInsights/projects/3
  • Repository: ProvisioInsights/LivingAtlas

When creating or updating work items:

  • Prefer GitHub Issues for durable tasks, bugs, gates, and follow-up work.
  • Use GitHub sub-issues when a larger issue needs child tasks or acceptance gates.
  • Add every Living Atlas issue and sub-issue to the Living Atlas Roadmap project unless there is a specific reason not to.
  • Keep project status aligned with issue/PR state; do not leave completed merge work as untracked side context.
  • Reference issue numbers in branches, commits, PRs, and handoffs when the work maps to a tracked item.
  • Use public-safe summaries in issue bodies and comments. Do not paste secrets, private deployment evidence, recovery material, personal graph contents, private source paths, or local profile data into GitHub.
  • Private deployment evidence belongs in the approved private overlay or local evidence paths, with only public-safe status and issue links in this repo.

System Layers

Architecture docs govern runtime/storage/access:

  • Cloudflare custody
  • local replica
  • encryption/key management
  • identity/configuration control plane
  • sync/offline/conflict behavior
  • MCP access
  • CRUD/audit/activity
  • metadata leakage and privacy boundaries

Temporal-edge docs govern knowledge semantics:

  • edge/event ontology
  • predicates and endpoint types
  • bitemporal date semantics
  • relationship vocabulary
  • Logseq/Obsidian migration rules

When these conflict, runtime/security architecture wins for where data lives and who can access it. Temporal-edge docs win for what graph facts mean.

Read the full file on GitHub · 96 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. 2mo ago First seen · 96 lines · 796 tokens per session scan A 546c72834a96

Subscribe to this mod's changes

LivingAtlas AGENTS.md is an instructions file published in the GitHub repository ProvisioInsights/LivingAtlas (0 stars, last pushed 1mo ago), licensed MIT. It adds 796 tokens to every session, about $0.0032 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.

Related

LivingAtlas AGENTS.md compared with instructions from other repositories

LivingAtlas AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
LivingAtlas AGENTS.mdProvisioInsights/LivingAtlasInstructions file01mo agoMITA796Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode