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/lolaplex/agents-memory/memory-syncnpx skills add Lolaplex/agents-memory --skill memory-syncgit clone --depth 1 https://github.com/Lolaplex/agents-memoryWhat 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 | $0.00067 | $0.01495 |
| Opus 5 | $0.00034 | $0.00747 |
| Sonnet 5 | $0.00013 | $0.00299 |
| Haiku 4.5 | $0.00007 | $0.00150 |
Grade A, and why
memory-sync 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 yesterday.
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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memory-sync
Local markdown memory. Not cloud.
Paths
User memory: ~/.agents/memory. Project memory: <repo>/.agents/memory.
| File | What |
|---|---|
~/.agents/memory/USER.md |
Identity, talk style, stack, ALWAYS/NEVER |
~/.agents/memory/PROJECTS.md |
slug / path / role / stack / status |
~/.agents/memory/concepts/ |
Ideas |
~/.agents/memory/entities/ |
Named things |
~/.agents/memory/workflows/ |
Procedures |
~/.agents/memory/projects/<slug>/ |
Link to a real tree (not a second copy) |
~/.agents/memory/notes/<collection>/ |
Personal notes. Guide: projects, interests, education, finance, family, preferences, programming, work, certifications, scratch — not a closed set |
<repo>/.agents/memory/staging/ |
Inbox only (captured.md, from-chats.md). Distill, then empty. |
<repo>/.agents/memory/ |
research (input); plans/ tasks/ waves/ roadmap/ decisions/ as 001-topic.md; notes/proposed|implemented|rejected/<class>/ |
~/.agents/AGENTS.md |
Canonical always-on (USER + PROJECTS). CLAUDE.md is bound to it. |
~/.agents/memory/chats-index.md |
Chat title catalog |
~/.agents/memory/scan.json |
Roots, ignore list (includes .agents, .cursor), agent rule name |
~/.agents/rules/*.mdc |
Personal always-on rules (canonical). Sync binds them into ~/.cursor/rules/. Example: run-commands.mdc |
MCP server agents-memory: see abi/MCP.md. CLI/injection: python -m agents_memory --help-json.
When this skill fires
- User asks for Bestandaufnahme / inventory / memory sync / Projekte updaten
- User (or you) created a new folder under a
scan.jsonroot - A path in
PROJECTS.mdis wrong or missing - After editing
USER.mdorPROJECTS.mdby hand → alwayspython -m agents_memory sync
Bestandaufnahme workflow
- Run
python -m agents_memory inventory(or MCPinventory_projects). - Show the user a tight list:
- unknown: on disk, not in memory
- missing: in memory, path gone
- For each unknown, ask (or infer if obvious):
- add → role + stack (one line each)
- ignore → never list again (
ignore_project/--ignore SLUG) - skip → leave for later
- Register adds write
PROJECTS.md,projects/<slug>/README.md(link), and<repo>/.agents/memory/files (README.md,staging/captured.md), then sync inject. No empty folders. No repo.cursor/. - For missing: confirm delete from
PROJECTS.mdor fix the path. Do not guess a new path. - Run
python -m agents_memory syncif you edited markdown by hand. - Tell the user: your Agent picks up MCP + rules after reload if the server name changed.
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.
- yesterday Changed · +1 lines 3441fcc7e076
- 2d ago First seen · 87 lines · 67 tokens per session scan A 7f632a14a2db
memory-sync is a skill published in the GitHub repository Lolaplex/agents-memory (3 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 1,495 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 2026-08-31.
Other skills, from other repositories
On_Board
Skill "On_Board" from swisspra/On_Board, covering greetings agents!, welcome on board — agent shared memory skill.md, ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━, drop into any project that uses on board mcp and via native instruction file system.
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…
spec-driven-development
Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea. Use when a single requirement spans several independently testable capabilities and needs decomposing into a…
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or…
peon-ping-log
Log exercise reps for the Peon Trainer. Use when user says they did pushups, squats, or wants to log reps. Examples - "/peon-ping-log 25 pushups", "/peon-ping-log 30 squats", "log 50 pushups".
human-approval
Request human approval before performing a SAFETY-CRITICAL, IRREVERSIBLE, or SCOPE-EXPANDING action — submit a structured context (action, scope, risk, consequence) plus options, then STOP the current turn. The platform redispatches the agent after the human decides. NEVER use for routine deliverables (writing docs /…