Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/niels-emmer/myace/memory-systemnpx skills add niels-emmer/myace --skill memory-systemgit clone --depth 1 https://github.com/niels-emmer/myaceWrote 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/niels-emmer/myace/memory-system)<a href="https://agentmods.dev/skills/niels-emmer/myace/memory-system"><img src="https://agentmods.dev/badge/skills/niels-emmer/myace/memory-system.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00031 | $0.00912 |
| Opus 5 | $0.00015 | $0.00456 |
| Sonnet 5 | $0.00006 | $0.00182 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
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 2d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
A coding agent's context resets between sessions. Without a durable place to record decisions, conventions, and the reasoning behind them, every new session either re-derives context from scratch (slow, and prone to contradicting earlier decisions) or plows ahead without it (fast, and prone to redoing work or reversing a decision nobody remembers making). This skill defines a small, low-overhead file layout that fixes that, and the routine for keeping it current.
When to use it
At the start of every nontrivial task, before touching code. At the end of every nontrivial task, before considering it done. "Nontrivial" means: it involved a design or approach decision, it changed behavior a future session would need to know about, or it took more than a few minutes of back-and-forth to get right. A one-line typo fix doesn't need a memory update; a new feature, an architecture change, or a fix for a subtle bug does.
File layout
Create these under docs/memory/ in the project root the first time this skill is used on a project that doesn't have them yet:
docs/memory/core-principles.md— the stable layer. Architectural decisions and constraints that rarely change: the chosen stack, non-negotiable invariants, things that would require a real conversation to reverse. Keep this short — if it's growing every week, content belongs in one of the other files instead.docs/memory/workflow.md— the process layer. How this specific team/project actually works day to day: branching conventions, how releases happen, where things like migrations or config live, anything a new session needs to act consistently with existing practice. Changes more often than core-principles but still infrequently.docs/memory/decisions.md— the evidence/decision log. Append-only. Every nontrivial task adds one dated entry here. Never edit or delete a past entry to "clean it up" — if a decision was later reversed, add a new entry noting the reversal and why; the history is the point.
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.
- 2d ago First seen · 43 lines · 31 tokens per session scan A 7569659077bf
Memory System is a skill published in the GitHub repository niels-emmer/myace (1 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 912 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
maintain-codex-wiki
Maintain a review-first Markdown knowledge base for Codex practices with source provenance, engineering capture, citation-aware queries, explicit archive and promotion, and deterministic linting. Use when asked to capture a durable engineering lesson, ingest Codex research, query or archive what the repository knows…
memory-clean
Audit memory directory for structural issues (orphans, dangling refs, duplicates, missing sections, oversized entries) and staleness against session-history transcripts; report-first, fix-on-confirmation. Use when the user says "audit memory", "memory hygiene", or "find stale/duplicate memories".
memory-update
Scan agent's session-history transcripts for save-worthy signals (corrections, preferences, decisions, references), propose and write auto-memory files with valid frontmatter and MEMORY.md entry. Use when the user says "save this to memory", "remember that", or "scan this session for memories".
memory-sanitize
Produce share-safe copies of memory files under /tmp with PII redacted (paths, emails, session IDs, dates) and credentials scanned (tokens, keys); never mutates originals. Use when the user says "sanitize memory for sharing", "redact memory PII", or "scan memory for credentials".
prjct
The agentic harness for AI coding agents: machine-verified ships, guarded edits, and project lookup that beats re-deriving from source. Run the prjct verb yourself; use prjct work normally.
update-okf
Use after implementation changes to update OKF from git diff or changed files. Extract durable behavior, architecture, domain, data, and playbook changes into relevant OKF documents and log entries. Do not use for temporary task notes or changes with no durable project knowledge impact.