agent-memory-atlas: Skill for Codex

.agents/skills/reanalyze-memory-system/SKILL.md

reanalyze-memory-system is a skill for Codex from neoneye/agent-memory-atlas. It costs 78 tokens per session (4,061 once invoked), scanned A, original, MIT.

A workflow for updating an existing Agent Memory Atlas report after the analyzed repository has changed.

In plain words
What is it for?
It helps screen a newer checkout, compare it with the previous review, and fold confirmed changes into the existing memory-system report.
Why use it?
It keeps research tied to a current code version and can reveal new security or dependency concerns that were absent before.

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 →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/screen_repo.py /absolute/path/to/source-repository.

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/reanalyze-memory-system/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 reanalyze-memory-system

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/neoneye/agent-memory-atlas/reanalyze-memory-system"><img src="https://agentmods.dev/badge/skills/neoneye/agent-memory-atlas/reanalyze-memory-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,061 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Memory Poisoning · line 136
    Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
    Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 $0.00078 $0.04061
Opus 5 $0.00039 $0.02031
Sonnet 5 $0.00016 $0.00812
Haiku 4.5 $0.00008 $0.00406

Measured 6d ago against content hash a3696ae4425e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

reanalyze-memory-system 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 6d 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/reanalyze-memory-system/SKILL.md · 317 lines

How it starts

The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Re-analyze Memory System

The atlas pins every report to a commit. Upstream moves; the pin does not. This skill covers the second-most-common workflow in the repository: reading a system again at a newer commit and folding the result into the report that exists.

Screen the new checkout first, every time. Run the screen-repository skill before reading the diff:

python3 scripts/screen_repo.py /absolute/path/to/source-repository

A re-read clones a newer commit than the one that was screened, and the newest commit is exactly where a compromise would arrive — a postinstall added last week, a hook that was not there at the pin, a dependency range that resolved to something new. Screening once at first reading is worth nothing here. Compare the screen against the previous one where it matters: a new RUNS finding since the pin is itself a reason to slow down, and a FRESH finding is close to guaranteed — a project that just moved has just changed its dependency surface, which is exactly the seven-day window the cooldown exists for. Re-reads are the common case for that finding, not the exception.

It is not add-memory-system. There is no scaffolding, no new slug, no new homepage card. Read that skill for the report format, the capability definitions, the matrix rules and the build/validate loop — all of that still applies. This one covers what is different.

The rule that gets broken

Write the result, not the re-review. The report describes the system at the pinned commit. It is not a changelog of the atlas's own understanding.

Grep the repository's history for Fold the .* re-review into the report instead of narrating it and you will find the same correction applied more than once. The forms that keep appearing and must not:

  • "Re-read on , N commits past the previous pin…"
  • "At the commit this report first covered…"
  • "This report previously said…" / "the atlas had missed…"
  • "The report was updated to reflect…"

Check the finished report with:

Read the full file on GitHub · 317 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. 6d ago Changed · +24 lines a3696ae4425e
  2. 10d ago First seen · 293 lines · 78 tokens per session scan A a06cb505f474

Subscribe to this mod's changes

reanalyze-memory-system is a skill published in the GitHub repository neoneye/agent-memory-atlas (64 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 4,061 once invoked, about $0.0004 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

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-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

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

plur-memory

Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.

plur-ai/plur · 31 tokens

Effective Memory

The essential habits for an AI agent with memory — session bookends, learning triggers, verification, safety, and the operational discipline that turns raw recall into compounding intelligence. Pinned, always-injected.

plur-ai/plur · 44 tokens