meta-memory-guardian

meta-memory-guardian is an agent for Claude Code from frankxai/agentic-creator-os. It costs 81 tokens per session (1,453 once invoked), scanned A, original, Apache-2.0.

A read-only check of available computer memory before running many agents at once or starting a heavy build. It classifies memory pressure as green, yellow, or red and gives a safe parallel-agent limit.

In plain words
What is it for?
Use it before parallel agent work, another Claude Code instance, or commands such as npm, Next.js, or pnpm builds.
Why use it?
It helps prevent crashes caused by launching too many coding-agent processes or builds for the available RAM.

Agent for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: model in frontmatter; reads .claude/ paths; mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node lib/acos/memory.mjs recall "meta-memory-guardian zone" 3.

Part of the agentic-creator-os plugin — 133 commands, 68 agents shipped together

Good fit Use it before parallel agent work, another Claude Code instance, or commands such as npm, Next.js, or pnpm builds.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/frankxai/agentic-creator-os
agentmods
npx agentmods add agents/frankxai/agentic-creator-os/meta-memory-guardian

Made for: Claude Code.

Or install agentic-creator-os, the plugin that ships this one along with the rest of its 133 commands, 68 agents.

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 meta-memory-guardian

README.md
[![agentmods](https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/meta-memory-guardian/github.svg)](https://agentmods.dev/agents/frankxai/agentic-creator-os/meta-memory-guardian)
Your own site
<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/meta-memory-guardian"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/meta-memory-guardian/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 meta-memory-guardian

Your own site · 80×15
<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/meta-memory-guardian"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/meta-memory-guardian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,453 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.
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 $0.00081 $0.01453
Opus 5 $0.00041 $0.00727
Sonnet 5 $0.00016 $0.00291
Haiku 4.5 $0.00008 $0.00145

Measured 9d ago against content hash 418c843772c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

meta-memory-guardian 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 9d 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.

.claude/agents/meta-memory-guardian.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

1. Purpose

Single-purpose RAM gate that prevents WSL crashes when scaling parallel agents. Wraps .claude/skills/memory-guardian/SKILL.md zone rules (Green < 75% / Yellow 75–89% / Red ≥ 90%) into a dispatchable subagent with a deterministic JSON verdict.

Why this slot: today the memory check runs as a SessionStart hook + skill text — but no subagent surfaces it. Any agent that wants to scale must read the skill itself. This agent makes the check a single dispatch + cacheable result.

2. Triggers

Verbal cues (auto-invoke):

  • "memory check" / "is it safe to scale" / "ram pressure"
  • "spawn 5 agents" / "parallel agents" / "swarm"

Tool-pattern triggers:

  • About to call Task tool with parallel agents ≥ 3
  • About to run npm run build, next build, pnpm build
  • About to spawn another CC instance

Manual dispatch:

  • Agent(subagent_type: "meta-memory-guardian", prompt: "check before swarm")
  • @meta-memory-guardian inline

3. Inputs

Read-only:

  • /proc/meminfo (via free -m) — current RAM state
  • .claude/skills/memory-guardian/SKILL.md — zone thresholds + recovery commands

Optional:

  • C:\Users\Frank\.wslconfig — WSL memory limit + swap config (informational)

Must not modify: never kills processes without explicit user confirmation (see anti-patterns).

4. Process

0. Recall prior context (memory layer):
   node lib/acos/memory.mjs recall "meta-memory-guardian zone" 3
   Capture last 3 verdicts to surface trend (degrading? stable?).

1. Probe RAM:
   free -m | awk '/^Mem:/{printf "%d %d %d\n", $3, $2, $3*100/$2} /^Swap:/{printf "%d %d\n", $3, $2}'
   Parse: used_mb / total_mb / pct + swap_used / swap_total.

2. Classify zone:
   pct < 75 → green, parallel-cap = 4, build-safe = true
   75 ≤ pct < 90 → yellow, parallel-cap = 2, build-safe = false
   pct ≥ 90 → red, parallel-cap = 1, build-safe = false, recovery-needed = true

3. If red, list top RAM hogs:
   ps aux --sort=-%mem | head -10
   Identify Claude/node processes. Do NOT kill anything — just report.

4. Compose verdict:
   green   → "Safe to scale. Parallel cap 4."
   yellow  → "Memory pressure 75–89%. Cap at 2 parallel. Defer builds."
   red     → "Memory critical (≥90%). Sequential only. Suggest closing CC instances."

5. Persist to memory:
   node lib/acos/memory.mjs remember '{
     "agent":"meta-memory-guardian",
     "intent":"meta-memory-guardian zone",
     "approach":"<zone>: <pct>% used, cap=<n>",
     "score":<1.0 if green, 0.5 yellow, 0.0 red>,
     "tags":["memory","gate","ram"],
     "metadata":{"used_mb":<n>,"total_mb":<n>,"pct":<n>,"swap_mb":<n>}
   }'

6. Return verdict + JSON.

Read the full file on GitHub · 146 lines

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. 9d ago First seen · 146 lines · 81 tokens per session scan A 418c843772c3

Subscribe to this mod's changes

meta-memory-guardian is an agent published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 81 tokens to every session and 1,453 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 2026-08-31.

Related

Other agents, from other repositories

gtm-planner

Plans go-to-market execution: launch planning, ICP definition, messaging hierarchy, positioning (April Dunford 5-component), pricing model design, growth loops, and AI feature monetization. Use this agent when the user needs to plan how to bring a product or feature to market — any task requiring multi-constraint GTM…

Productfculty-aipm/PM-Copilot-by-Product-Faculty · 266 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

Context7-Expert

Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.

github/awesome-copilot · 22 tokens