Borrowing it
Nothing to install: this file belongs to zelixag/ai-memex-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zelixag/ai-memex-cli/main/.claude/skills/ai-memex/SKILL.mdgit clone --depth 1 https://github.com/zelixag/ai-memex-cliWrote 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/zelixag/ai-memex-cli/ai-memex)<a href="https://agentmods.dev/skills/zelixag/ai-memex-cli/ai-memex"><img src="https://agentmods.dev/badge/skills/zelixag/ai-memex-cli/ai-memex.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 5.1 | $0.00152 | $0.00813 |
| Opus 5 | $0.00076 | $0.00407 |
| Sonnet 5 | $0.00030 | $0.00163 |
| Haiku 4.5 | $0.00015 | $0.00081 |
Grade A, and why
ai-memex 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ai-memex
Core rule: preserve source truth and make knowledge compound. Never blur raw source material, citations, contradictions, or operation history.
This skill makes the agent the main interface for maintaining an LLM wiki. Use the memex CLI as a deterministic toolbox, not as the source of semantic judgment.
Workflow Selector
| User intent | Workflow | Reference |
|---|---|---|
| Save a URL, file, text, or search result | Capture | references/capture-workflow.md |
| Turn raw material into wiki pages | Ingest | references/ingest-workflow.md |
| Ask what the wiki knows | Query | references/query-workflow.md |
| Save a useful conversation or debugging session | Distill | references/distill-workflow.md |
| Health-check the wiki, fix or surface semantic issues | Lint | references/lint-workflow.md |
| Unsure about vault layout or page format | Protocol | references/vault-protocol.md |
| Any destructive, ambiguous, or broad rewrite | Safety | references/safety-rules.md |
Default Loop
- Identify the user's workflow from the selector.
- Run
memex statuswhen the vault location or current state is unclear. - Load only the reference files needed for the workflow.
- Use CLI commands for deterministic operations:
status,fetch,search,lint,link-check, and mechanicaldistill. - Use agent judgment for semantic work: merging knowledge, writing wiki pages, preserving citations, handling contradictions, and updating
index.md/log.md. - Run or recommend
memex lintafter substantial wiki edits.
CLI Use Policy
Allowed without extra confirmation:
memex statusmemex search <query>memex lintmemex link-checkmemex fetch <url|query>for user-requested capturememex distillfor user-requested session capture
Avoid unless the user explicitly asks:
memex watch --daemon --heal- broad install/update/config changes
- commands that overwrite generated agent instructions
Safety Gates
Ask before:
What ships with it
7 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.
- 7d ago First seen · 86 lines · 152 tokens per session scan A ca933a8b5d04
ai-memex is a skill published in the GitHub repository zelixag/ai-memex-cli (9 stars, last pushed 4mo ago), licensed MIT. It adds 152 tokens to every session and 813 once invoked, about $0.0008 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
wiki
A persistent Markdown knowledge base maintained by an AI agent. Markdown is a plain-text format for structured notes; the knowledge base can hold personal research or documentation about an open-source project's design.
claw-memory-management
Workspace memory management guide: memory layers, writing rules, entry format, and maintenance. Use when writing, updating, or maintaining memory files (memory/YYYY-MM-DD.md and MEMORY.md).
wegent-knowledge
Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.
project-wiki
A system for creating and maintaining a project wiki: a set of organized documents that explain a software project's plans, rules, references, and progress.
mindos-zh
A local knowledge-base assistant for storing and finding decisions, meeting notes, procedures, troubleshooting lessons, and preferences across conversations and coding agents. It works only with the MindOS knowledge base.
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…