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/mex-memory/mex/mex-inboxnpx skills add mex-memory/mex --skill mex-inboxgit clone --depth 1 https://github.com/mex-memory/mexWrote 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/mex-memory/mex/mex-inbox)<a href="https://agentmods.dev/skills/mex-memory/mex/mex-inbox"><img src="https://agentmods.dev/badge/skills/mex-memory/mex/mex-inbox.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 | $0.00116 | $0.00727 |
| Opus 5 | $0.00058 | $0.00364 |
| Sonnet 5 | $0.00023 | $0.00145 |
| Haiku 4.5 | $0.00012 | $0.00073 |
Grade A, and why
mex-inbox 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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MEX Inbox
Prepare governed Spec-memory proposals. Treat Inbox as a proposal workflow, not email and not a general Wiki mutation system.
Keep the scope honest
- Create exactly one
spec.createorspec.updatechange per draft. - Support only
spec,requirement,constraint, andacceptance_criterionentities. - Reject unsupported durable knowledge honestly. Do not silently translate architecture, conventions, patterns, Workstreams, Relays, or arbitrary Wiki pages into Specs.
- Require a clear durable claim. Do not capture unresolved brainstorming as team memory.
Prepare a draft
- Distill the durable knowledge, rationale, and useful evidence from the conversation.
- Decide whether it creates a new Spec-family entity or updates an existing exact entity.
- For an update, resolve the canonical target and current revisions before drafting. Never guess an ID or revision.
- Preserve useful files, code, commits, entities, and external links as evidence only when actually available. Never invent provenance, authors, dates, events, or history.
- Build one request against the action-scoped runtime contract.
- Run the exact preview flow and summarize the human effect before technical details.
- When the user already asked to create, save, or draft it, apply that exact successful checkout-local draft preview without asking again.
- Return
/inbox?view=drafts&draft=<id>and state that the draft is checkout-local, nothing was published or shared, and review or publication happens in Hub.
Read references/cli-workflows.md before executing any Inbox mutation. Load only the operation being performed.
Apply the approval policy
- Proceed with read-only list, show, and target resolution.
- Treat an explicit create/save/draft request as authorization only for the local draft preview and exact apply.
- Preview a local draft deletion, explain that the checkout-local draft will be removed, and obtain fresh confirmation before applying.
- For publish, approve, reject, withdraw, mark stale, or repair: create a semantic preview, explain the local-versus-Git-tracked effect, and wait for fresh explicit confirmation. Apply the exact preview unchanged only after confirmation.
- Keep Git commit, push, pull, and staging separate from every MEX authorization.
- Never approve or publish merely because this skill activated.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 45 lines · 116 tokens per session scan A ec0e61b45c9f
mex-inbox is a skill published in the GitHub repository mex-memory/mex (1,540 stars, last pushed yesterday), licensed MIT. It adds 116 tokens to every session and 727 once invoked, about $0.0006 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
project-brain
Triggers (all require explicit user request — do NOT activate just because a brain/ folder exists): (1) The user wants to set up project-level memory ("set up project brain", "scaffold project context", "init project brain", "建项目脑"). (2) The user is in a directory containing brain/ AND explicitly asks to resume /…
context-health-check
Context window health check. Trigger with /ctx or phrases like "context check", "do I need a new conversation", "how much context left". Evaluates current context consumption and recommends whether to start a new conversation.
semantic-search
Zero-dependency TF-IDF search across MUSE memory, roles, and skills. Use when user wants to find information across their project context.
context-receipts
Emit privacy-safe receipts for context selection, deferral, hydration, compaction, pruning, delegation, usage attribution, and boundary handoffs.
engram
Local-first personal AI identity and memory layer for MCP-compatible coding tools (Claude Code, Codex, Cursor, and others). Use this skill when the user wants to continue from a previous session ("continue from last session", "pick up where we left off"), recall a past decision ("what did we decide", "what was our…
fec-image-generation
用于生成或编辑图表、图形资产、海报、UI 样机、产品图、信息图、学术图、漫画、头像、分镜、品牌板或图像编辑工作流，尤其是导出 PNG 需要视觉质检和有限自动修复时。文字密集图表优先使用确定性的 Mermaid/SVG/HTML/canvas 源；浏览器可打开的技术图优先使用 HTML technical diagrams，覆盖系统蓝图、架构图、部署拓扑、Agent runtime、memory flow、before-after architecture、流程、序列、数据流、生命周期、runbook、PII/数据血缘和状态机；不要用于不涉及生成图像的普通 UI 打磨。中文触发词包括…