inject

A command that supplies wiki context relevant to the coding task you are working on.

In plain words
What is it for?
Use it with a task description or keywords, such as authentication or React, TypeScript, and hooks.
Why use it?
It brings related stored information into the task so the agent can work with fewer repeated searches and less background copying.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/zelixag/ai-memex-cli/inject
Clone the repo
git clone --depth 1 https://github.com/zelixag/ai-memex-cli

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 178 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod 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 $0.00000 $0.00178
Opus 5 $0.00000 $0.00089
Sonnet 5 $0.00000 $0.00036
Haiku 4.5 $0.00000 $0.00018

Measured 2d ago against content hash c66f89ac632a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

inject 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 2d 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.

Origin

This is a copy

86% identical to fetch — 15 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/memex/inject.md · 29 lines

What it actually says

memex inject

Output relevant wiki context for the current task (saves tokens, improves precision).

Usage

/memex:inject [--task <description>] [--keywords <kw>]

Examples

  • /memex:inject --task "implement authentication"
  • /memex:inject --keywords "react,typescript,hooks"

Instructions

Current memex agent: claude-code

When calling a memex CLI command that delegates semantic work to an agent, pass --agent claude-code unless the user already provided an explicit --agent.

Run the following shell command, substituting $ARGS with any arguments the user provided after /memex:inject:

memex inject $ARGS

Report the command output to the user. If the command modifies wiki pages, briefly summarize what changed.

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. 2d ago First seen · 29 lines · 0 tokens per session scan A c66f89ac632a

Subscribe to this mod's changes

inject is a command published in the GitHub repository zelixag/ai-memex-cli (9 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 178 tokens. A static security scan graded it A with 0 findings. It is 86% identical to fetch, differing in 15 lines, and is treated as a copy.