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 skills add BongSuCHOI/memex --skill show-memex-dashboardgit clone --depth 1 https://github.com/BongSuCHOI/memexWrote 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/bongsuchoi/memex/show-memex-dashboard)<a href="https://agentmods.dev/skills/bongsuchoi/memex/show-memex-dashboard"><img src="https://agentmods.dev/badge/skills/bongsuchoi/memex/show-memex-dashboard/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.
<a href="https://agentmods.dev/skills/bongsuchoi/memex/show-memex-dashboard"><img src="https://agentmods.dev/badge/skills/bongsuchoi/memex/show-memex-dashboard.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00039 | $0.00727 |
| Opus 5 | $0.00019 | $0.00364 |
| Sonnet 5 | $0.00008 | $0.00145 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
show-memex-dashboard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Show Memex Dashboard
Resolve PLUGIN_ROOT as two directories above this skill directory. The default
URL is http://127.0.0.1:3847; the PORT environment variable overrides the
port and the server always binds loopback only.
Before starting a process, inspect the port owner. Reuse it only when it is the Memex server for this installed root. If another process owns the port, report the conflict without terminating it.
Start a new server only when needed:
node "$PLUGIN_ROOT/cli/runtime-exec.js" memex-ui
The server is ready once it prints Memex Workspace <version>, the loopback URL
and the resolved DB: path.
Keep the process observable for clean shutdown. Open only the route relevant to the request:
| 화면 | 경로 | 용도 |
|---|---|---|
| 개요 | / |
범위 요약, 파이프라인 상태, 최근 기억 변화 |
| 대화 원장 | /conversations |
세션·턴 원문과 추출 근거 |
| 기억·사실 | /facts |
기억 검색, 상세 패널에서 수정·비활성화·복원·삭제·계층 승격/강등. 목록 행과 상세에 주입 계층 배지(글로벌 공용 / 프로젝트 공용 / 브랜치: <name> / 워크스페이스)와 그 계층의 주입 조건 툴팁이 붙습니다. 프로젝트 범위에서 브랜치·워크스페이스 계층 기억이 가려져 있으면 배너가 알려 주고, ?tiers=all로 포함해서 볼 수 있습니다 |
| 분류 | /taxonomy |
온톨로지 도메인과 주제 분류 |
| 지식 지도 | /graph |
기억 관계 지도 (2D Map / 3D Galaxy) |
| 활동 · 추적 | /activity |
처리 작업, 모델 시도, 변경 이력, 로그 |
| 관리 | /settings |
런타임, 관리 작업, 다기기 동기화(기본 꺼짐), 화면 설정, 진단 |
Scope is a query parameter on every route: ?scope=all reads every project plus
common memory, ?scope=global reads common memory only, and
?scope=project&project=<encoded-canonical-absolute-cwd> reads one project. With
no parameter the browser falls back to the last scope it stored and otherwise to
all (the JSON API alone still defaults to global). Conversations, activity and
interpretive-context rows are not visible from the global-only scope, so use
?scope=all or a project scope for those. The selector is labelled
전체 프로젝트 (조회) because that scope is read-only breadth: injection always
uses the current project plus common memory.
/facts?fact=<id> and /facts/<id> both open the memory detail drawer.
Report the URL and exact process started or reused. Do not install dependencies, register hooks/plugins, change facts, or expose the server beyond loopback merely to show the dashboard.
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.
- today Changed · +25 lines 202066740137
- 10d ago First seen · 28 lines · 39 tokens per session scan A df103f1a7779
show-memex-dashboard is a skill published in the GitHub repository BongSuCHOI/memex (0 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 727 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 2026-08-31.
Other skills, from other repositories
potpie-graph
Use when the task can read or write the project-memory graph through the potpie CLI: discover the contract with graph catalog, read named views with graph read, resolve entity identity with graph search-entities, create validated plans with graph propose, commit plans with graph commit --verify, inspect quality with…
potpie-repo-baseline
Use when establishing, refreshing, or deeply understanding a repository's baseline memory in Potpie: purpose, application type, features, services/modules, environments, deploy shape, dependencies, API contracts, datastores, integrations, ownership, and explicit preferences. The harness reads authored and…
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
hybrid-memory
Hybrid memory strategy combining OpenClaw's built-in QMD vector memory with Graphiti temporal knowledge graph. Use for all memory recall requests.
midmem-dev
Develop/iterate on the MidMem middleware core (this repo's packages/core — the shared "LLM Wiki" knowledge layer). Use when adding or changing MidMem capability — retrieval lanes, tiers/lifecycle, work-memory events, concept routing, claims, grounding, the MCP/CLI/hook surfaces, or its tests. Encodes the…
brain
Health-check the second brain so failures are not silent: is the local search server alive, is the RAG index fresh, is the session-memory ledger filling, did the nightly distillation run. Read-only, with a green/red verdict per component. Triggers: "/brain", "/memory", "is the reindex alive".