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.
curl -O https://raw.githubusercontent.com/neoneye/agent-memory-atlas/main/.agents/skills/reanalyze-memory-system/SKILL.mdgit clone --depth 1 https://github.com/neoneye/agent-memory-atlasWrote 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.
[](https://agentmods.dev/skills/neoneye/agent-memory-atlas/reanalyze-memory-system)<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.
<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>- NVIDIA SkillSpector warn
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.
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 | $0.00078 | $0.04061 |
| Opus 5 | $0.00039 | $0.02031 |
| Sonnet 5 | $0.00016 | $0.00812 |
| Haiku 4.5 | $0.00008 | $0.00406 |
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.
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:
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.
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.
- 6d ago Changed · +24 lines a3696ae4425e
- 10d ago First seen · 293 lines · 78 tokens per session scan A a06cb505f474
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.
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.
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…
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.
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.
plur-memory
Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.
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.