agent-memory-atlas: Skill for Codex

.agents/skills/use-the-atlas/SKILL.md

use-the-atlas is a skill for Codex from neoneye/agent-memory-atlas. It costs 92 tokens per session (1,823 once invoked), scanned A, original, MIT.

A guide for choosing and building the smallest useful memory system for a product, using the Agent Memory Atlas as a reference.

In plain words
What is it for?
It helps decide which memory patterns a product needs, review an existing memory design, or plan additions while recording what is intentionally deferred.
Why use it?
It prevents adding unnecessary storage and recall mechanisms that make a product harder to maintain than its needs justify.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is neoneye/agent-memory-atlas's own configuration. It tells Codex how to work on agent-memory-atlas 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 agent-memory-atlas configures →

Reuse

Borrowing it

Nothing to install: this file belongs to neoneye/agent-memory-atlas. 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/neoneye/agent-memory-atlas/main/.agents/skills/use-the-atlas/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/neoneye/agent-memory-atlas

Made for: Codex.

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 use-the-atlas

README.md
[![agentmods](https://agentmods.dev/badge/skills/neoneye/agent-memory-atlas/use-the-atlas/github.svg)](https://agentmods.dev/skills/neoneye/agent-memory-atlas/use-the-atlas)
Your own site
<a href="https://agentmods.dev/skills/neoneye/agent-memory-atlas/use-the-atlas"><img src="https://agentmods.dev/badge/skills/neoneye/agent-memory-atlas/use-the-atlas/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 use-the-atlas

Your own site · 80×15
<a href="https://agentmods.dev/skills/neoneye/agent-memory-atlas/use-the-atlas"><img src="https://agentmods.dev/badge/skills/neoneye/agent-memory-atlas/use-the-atlas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,823 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00092 $0.01823
Opus 5 $0.00046 $0.00911
Sonnet 5 $0.00018 $0.00365
Haiku 4.5 $0.00009 $0.00182

Measured 11d ago against content hash ebefe0015b4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

use-the-atlas 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 11d 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/skills/use-the-atlas/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use the Atlas

The other three skills in this repository grow the corpus. This one spends it.

The failure this skill exists to prevent: an agent pointed at 155 reports reads widely, finds the most rigorous mechanism, and builds it. The result is a tombstone and a governed write gateway on a single-user notes app that needed scoped SQLite and an explicit write path. The atlas's own pattern index says the correctable stack is "one stack among several, not a bar the others fail to clear" — and a warning addressed to a human reader does not constrain an agent unless something makes it.

So the discipline here is subtractive. Adopt the smallest set that closes a failure this product can actually suffer, and write down what you deferred.

Pick a mode first, and do not drift out of it

The four jobs people ask for are different, and three of them do not touch the target repository. State which one you are in before you start, and treat approval of an artifact as approval of that artifact only — a person who approved a build brief has approved a design, not a commit.

Mode You produce You may modify the target repo
decide which patterns this product needs, and why no
design the build brief no
review a closure report over the memory that already exists, with the open rows named no
build brief → separate approval to implement → code and tests yes, after that second approval

Default to the narrowest mode the request supports. "What does my memory design need?" is decide. "Review my memory implementation" is review and ends with a report — the gaps it finds are findings, not a work order. Moving from design to build needs the developer to say so after reading the brief; the brief being approved is not that sentence.

What you read, and what you do not

Do not read the system reports. Read these, in order:

  1. content/patterns/index.md § How to use the library — failure → pattern.
  2. The same page's § Stacks, by what you are building — five profile rows, each naming the failure that hurts for that shape, each with a what you can defer paragraph.
  3. The pattern pages you selected — Cost to adopt, Tradeoffs, Implementation checklist, Tests to require, Seen in the atlas.
  4. content/overview.md § 8 What I Would Build (ship-first order) and § 10 Practical Checklist.
  5. content/benchmarks.md § 6 and § 7 when you need the deletion and contradiction tests in detail.

Read the full file on GitHub · 155 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 155 lines · 92 tokens per session scan A ebefe0015b4c

Subscribe to this mod's changes

use-the-atlas is a skill published in the GitHub repository neoneye/agent-memory-atlas (66 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 1,823 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

thoughtline-memory

Persistent, project-aware memory for AI coding agents. Use thoughtline whenever you make a decision, fix a bug, learn something non-obvious, or need to recall prior work.

AgusLoza2021/Thoughtline · 40 tokens

deja-search

Search deja before re-deriving past work: when the user refers to earlier sessions or decisions, before debugging an error, and before implementing something that may already exist. It searches this machine's own history across every AI coding tool used on it, going back further than deja itself was installed.

vshulcz/deja-vu · 57 tokens

plur-create-engrams

Create or improve PLUR engrams from conversations, documents, decisions, observations, and explicit preferences. Use for memory extraction, engram authoring, or reviewing proposed memories, including global, scoped, pinned, retrieved, and provisional knowledge. Ordinary use of existing memories does not require this…

plur-ai/plur · 66 tokens

deja-history

Search the user's past AI coding sessions. Use when they say things like 'didn't we fix this before', 'what did we decide about X', or before re-debugging an error that may already be solved.

vshulcz/deja-vu · 47 tokens

dashboard

Open OwnMem Console, the local dashboard for this repository's memory. Use when the user asks to open the dashboard, see memory metrics, check adoption or recall quality, or set up the optional embedding lane. Requires a repository initialized with the dashboard layer.

grpcer/ownmem · 53 tokens

recall

Recall this repository's OwnMem local memory before changing code, and keep it healthy. Use when a repository contains .ownmem/, when past debugging lessons could apply ("have we hit this before", "why is it done this way"), or when the user mentions ownmem, project memory, or recalling across sessions.

grpcer/ownmem · 66 tokens