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/add-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/add-memory-system)<a href="https://agentmods.dev/skills/neoneye/agent-memory-atlas/add-memory-system"><img src="https://agentmods.dev/badge/skills/neoneye/agent-memory-atlas/add-memory-system.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 97 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00057 | $0.06998 |
| Opus 5 | $0.00028 | $0.03499 |
| Sonnet 5 | $0.00011 | $0.01400 |
| Haiku 4.5 | $0.00006 | $0.00700 |
Grade A, and why
add-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 3d 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 — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Memory System
Add one memory system to the atlas as a code-grounded, commit-pinned analysis. Treat the individual report, comparative synthesis, homepage, and generated site as one change.
Screen the checkout first — this is a precondition, not a suggestion. Run the
screen-repository skill before reading a single file of a newly cloned tree:
python3 scripts/screen_repo.py /absolute/path/to/source-repository
Analysis means cloning a stranger's repository onto a personal machine and often
running its build or its tests. Auto-executing hooks fire without a command being
typed, and an unpinned dependency is a supply-chain compromise waiting on somebody
else's account. Read every RUNS finding before doing anything else, keep the
default posture read-only, and prefer npm ci --ignore-scripts and a throwaway
venv over the documented install when execution is genuinely needed. NOTHING SCANNED is a finding, not a pass, and so is FRESH — never install a
third-party dependency published in the last seven days, because that window is
where an undetected registry compromise lives. npm ci does not protect you
there: it reproduces the lockfile faithfully however new the pin is. Record the
outcome in the report's History entry.
If the atlas already has a report for this repository, this is the wrong skill — use reanalyze-memory-system, which covers re-pinning, deciding whether a published claim went stale, and the rename-and-redirect convention. Check first:
rg -l '^source_url:.*<owner>/<repo>' content/systems/
A renamed upstream will not match on name; search the pinned revision as well before concluding it is new.
Establish the inputs
Resolve these before writing:
- The Agent Memory Atlas repository root.
- A local checkout of the memory-system repository.
- A unique lowercase filename slug.
- The canonical source repository URL.
- The exact full commit ID being analyzed.
Prefer a local checkout because the report must trace implementation paths. Do not change the source repository. If only a URL is available, clone it to a temporary directory when network access and user authorization allow it.
What ships with it
2 files 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.
- 3d ago Changed · +36 lines ebbe5fa3f6e3
- 8d ago First seen · 359 lines · 57 tokens per session scan A f07082d73376
add-memory-system is a skill published in the GitHub repository neoneye/agent-memory-atlas (61 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 6,998 once invoked, about $0.0003 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.
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.
plur-session-end
Extract durable learnings at the end of a session. Saves corrections, preferences, and codebase patterns as engrams — nothing ephemeral, nothing sensitive.