context

A command for searching stored memories by a word and related terms, then displaying the matching context. It can expand searches such as “auth” to include login, sessions, tokens, and similar concepts.

In plain words
What is it for?
Use it to find remembered information about authentication, databases, APIs, styling, testing, or other supported search topics.
Why use it?
It saves you from manually searching through all saved project notes when you need earlier context about a topic.

Command

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/sukinshetty/nemp-memory/context
Clone the repo
git clone --depth 1 https://github.com/SukinShetty/Nemp-memory
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,196 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.

ModelPer sessionOnce invoked
Fable 5 $0.00008 $0.04196
Opus 5 $0.00004 $0.02098
Sonnet 5 $0.00002 $0.00839
Haiku 4.5 $0.00001 $0.00420

Measured 2d ago against content hash c164a0445b7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context 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.

commands/context.md · 509 lines

How it starts

The opening of the file, as written. The whole thing — 509 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/nemp:context

Find and display memories relevant to a search query using smart keyword expansion.

Usage

/nemp:context auth           # Find memories related to authentication
/nemp:context database       # Find database-related memories
/nemp:context api            # Find API-related memories
/nemp:context style          # Find styling/CSS memories
/nemp:context test           # Find testing-related memories

Instructions

1. Get the Search Query

Extract the search term from the user's command argument.

If no argument provided, show help:

Nemp Context Search

Usage: /nemp:context <search-term>

Examples:
  /nemp:context auth      - Find authentication memories
  /nemp:context database  - Find database memories
  /nemp:context api       - Find API memories
  /nemp:context style     - Find styling/CSS memories
  /nemp:context test      - Find testing memories

Smart search expands your query to related terms!

2. Expand Keywords Using Smart Mappings

Based on the search term, expand to related keywords:

KEYWORD MAPPINGS:

auth, login, authentication:
  → auth, authentication, login, session, jwt, oauth, nextauth, clerk,
    supabase-auth, passport, token, credentials, signin, signup, logout

database, db:
  → database, db, postgres, postgresql, mysql, sqlite, mongo, mongodb,
    prisma, drizzle, mongoose, sequelize, knex, typeorm, schema, migration

api, endpoint:
  → api, endpoint, route, rest, graphql, trpc, fetch, axios, request,
    response, http, webhook, cors, middleware

style, css, styling:
  → style, css, tailwind, emotion, styled-components, chakra, mantine,
    theme, design, scss, sass, less, classname, styling

test, testing:
  → test, testing, jest, vitest, playwright, cypress, unit, integration,
    e2e, mock, fixture, assertion, coverage, spec

state, store:
  → state, store, redux, zustand, jotai, recoil, context, provider,
    reducer, action, selector, persist

deploy, hosting:
  → deploy, deployment, hosting, vercel, netlify, aws, docker, kubernetes,
    ci, cd, pipeline, github-actions, build

config, env, environment:
  → config, configuration, env, environment, dotenv, settings, options,
    variables, secrets, keys

error, debug:
  → error, debug, debugging, exception, catch, try, logging, sentry,
    bugsnag, stack, trace, console

types, typescript:
  → types, typescript, interface, type, generic, zod, yup, schema,
    validation, typing

Read the full file on GitHub · 509 lines

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 · 509 lines · 8 tokens per session scan A c164a0445b7f

Subscribe to this mod's changes

context is a command published in the GitHub repository SukinShetty/Nemp-memory (128 stars, last pushed 2mo ago), licensed MIT. It adds 8 tokens to every session and 4,196 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.