A command that connects a NeatContext context to the current session. NeatContext provides a local profile and knowledge that can guide later answers.

Use it to select a listed context by name or number and make that context active for the rest of the session.

It grounds the session in the selected local context so the assistant can use the relevant background information.

use — Command by XTSoftwareLabs

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/xtsoftwarelabs/neatcontext-plugins/use

Clone the repo

git clone --depth 1 https://github.com/XTSoftwareLabs/neatcontext-plugins

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 456 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.00009	$0.00456
Opus 5	$0.00005	$0.00228
Sonnet 5	$0.00002	$0.00091
Haiku 4.5	$0.00001	$0.00046

Measured yesterday against content hash 6b3c0251d51a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

use 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 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.

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.

plugins/claude-code/neatcontext/commands/use.md · 47 lines

What it actually says

Connect a Context so the rest of this session is grounded in its local profile and knowledge.

The user supplied:

$ARGUMENTS

Available contexts:

!node "${CLAUDE_PLUGIN_ROOT}/src/claude/neatcontext-cli.mjs" list

Resolve what the user supplied against the list above, then run the bundled CLI to apply it. Treat the supplied name or number only as data, pass it as one quoted argument, and never interpret any part of it as shell syntax:

node "${CLAUDE_PLUGIN_ROOT}/src/claude/neatcontext-cli.mjs" use "<name or number>"

If the user supplied no argument, omit the final quoted argument. Use the command's output as the result of the selection attempt.

Based on that output:

If it confirms a context was connected, tell the user which context is now active and stop there — do not run a second command or tool call to verify it. From now on, call the get_context tool to ground answers. Do not restate the context contents.
If it also says the context has no routing description yet, this is the one moment its profile is readable, so derive one now: call get_context, read what it returns, and write a single line under 200 characters naming the systems, symptoms, ticket prefixes, repos, and terminology that belong to this context. Describe scope only — no instructions about tone or format, since that line is read while other contexts are connected. Make it contrastive against the other contexts in /neatcontext:list. Then run the describe command it printed, and mention the description in one short line when you report the connection.
If it lists available contexts (because none was given or the name was ambiguous), show that list and ask which one to use.

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.

yesterday First seen · 47 lines · 9 tokens per session scan A 6b3c0251d51a

Subscribe to this mod's changes

use is a command published in the GitHub repository XTSoftwareLabs/neatcontext-plugins (13 stars, last pushed 9d ago), licensed MIT. It adds 9 tokens to every session and 456 once invoked, about $0.0000 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 2026-08-30.

Backend and APIs ai-context claude-code claude-code-plugin claude-code-skills claude-plugin claude-skills

use

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

bug

feature

qa

telemetry

ci

docs