fleet-scan

fleet-scan is a skill for Claude Code from YoungjaeDev/my-claude-plugins. It costs 149 tokens per session (1,154 once invoked), scanned B, original, MIT.

A fleet-wide report for mem0, a memory service, that checks all applications for memory counts, noisy entries, fragmented users, and configuration problems.

In plain words
What is it for?
It helps inspect memory quality and configuration across every mem0 application, including possible junk application identifiers and ranking or retention settings.
Why use it?
Memory data can become duplicated, noisy, or split across application and user identifiers. The scan shows these issues and checks whether the service is configured as expected.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT variable. Also seen: reads .claude/ paths; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the wiki plugin — 6 skills shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add YoungjaeDev/my-claude-plugins
Claude Code
/plugin install wiki

Made for: Claude Code.

Or install wiki, the plugin that ships this one along with the rest of its 6 skills.

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 fleet-scan

README.md
[![agentmods](https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/fleet-scan.svg)](https://agentmods.dev/skills/youngjaedev/my-claude-plugins/fleet-scan)
Your own site
<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/fleet-scan"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/fleet-scan.svg" alt="Measured on agentmods" height="20"></a>
Per session 149 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,154 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00149 $0.01154
Opus 5 $0.00075 $0.00577
Sonnet 5 $0.00030 $0.00231
Haiku 4.5 $0.00015 $0.00115

Measured yesterday against content hash 84adea92002c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

fleet-scan scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- MEM0_RERANK unset -> add `"MEM0_RERANK": "off"` to `~/.claude/settings.json` env.
plugins/wiki/skills/fleet-scan/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fleet-scan

Codex note

Script is plain python3 on all runtimes. Codex 0.135 does NOT export CLAUDE_PLUGIN_ROOT: always resolve PLUGIN_ROOT first (block below).

Steps

  1. Resolve the plugin root (cross-runtime), then run the scan:

    PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-}"
    [ -z "$PLUGIN_ROOT" ] && [ -d plugins/wiki/scripts ] && PLUGIN_ROOT=plugins/wiki
    if [ -z "$PLUGIN_ROOT" ]; then
      cache_root="${CODEX_PLUGIN_CACHE:-$HOME/.codex/plugins/cache}"
      PLUGIN_ROOT=$(ls -1d "$cache_root"/*/wiki/* 2>/dev/null | sort | tail -1)
    fi
    [ -d "$PLUGIN_ROOT/scripts" ] || { echo "wiki scripts not found"; exit 1; }
    # Interpreter detection — python3 alone breaks python.org Windows installs; validate
    # the candidate really is Python 3 (a python->python2 alias would die on f-strings)
    PY=""; for c in python3 python "py -3"; do
      if $c -c 'import sys; raise SystemExit(0 if sys.version_info[0] == 3 else 1)' >/dev/null 2>&1; then PY=$c; break; fi
    done
    [ -n "$PY" ] || { echo "no Python 3 interpreter found (tried python3, python, py -3)"; exit 1; }
    $PY "$PLUGIN_ROOT/scripts/fleet_scan.py"
    
    • Requires MEM0_API_KEY; the script exits with guidance if unset.
    • Full-fleet scan pages every app: expect ~1-2 minutes on large stores.
  2. Interpret the report for the user:

    • JUNK? flag = basename-style name + noise >= 90% + zero manual types. These are cwd-fallback artifacts; suggest cleanup --app <name> --all.
    • FRAG pairs = same project split across two app_ids (recall is split). Merge is out of scope v1: report only.
    • High noise% on a real project = suggest cleanup --app <name> --type session_summary.
  3. Do NOT delete anything from this skill. Route to the cleanup skill.

Config posture (absorbed from doctor)

When the user asks about local mem0 configuration ('mem0 설정 점검', hook timeouts, rerank) rather than fleet contents, run the posture check. Shell state does not persist across tool calls, so this block re-resolves PLUGIN_ROOT and the interpreter itself:

Read the full file on GitHub · 71 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. yesterday First seen · 71 lines · 149 tokens per session scan B 84adea92002c

Subscribe to this mod's changes

fleet-scan is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 149 tokens to every session and 1,154 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens