context-agent

context-agent is an agent for Claude Code from andisab/swe-marketplace. It costs 429 tokens per session (2,082 once invoked), scanned A, original, MIT.

An agent that maintains CLAUDE.md files, which store project instructions and context for Claude Code. It checks those files against the repository's current structure and implementation.

In plain words
What is it for?
Use it to find, review, create, or update CLAUDE.md documentation and report missing or inconsistent project context.
Why use it?
It helps keep the guidance an AI coding agent reads accurate as the project changes, reducing outdated assumptions and repeated setup explanations.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md; names the TodoWrite tool.

Part of the arch plugin — 2 agents shipped together

Good fit Use it to find, review, create, or update CLAUDE.md documentation and report missing or inconsistent project context.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/andisab/swe-marketplace/arch-context-agent
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.

Clone the repo
git clone --depth 1 https://github.com/andisab/swe-marketplace

Made for: Claude Code.

Or install arch, the plugin that ships this one along with the rest of its 2 agents.

Wrote 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.

agentmods badge for context-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/andisab/swe-marketplace/arch-context-agent/github.svg)](https://agentmods.dev/agents/andisab/swe-marketplace/arch-context-agent)
Your own site
<a href="https://agentmods.dev/agents/andisab/swe-marketplace/arch-context-agent"><img src="https://agentmods.dev/badge/agents/andisab/swe-marketplace/arch-context-agent/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for context-agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/andisab/swe-marketplace/arch-context-agent"><img src="https://agentmods.dev/badge/agents/andisab/swe-marketplace/arch-context-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 429 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,082 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00429 $0.02082
Opus 5 $0.00215 $0.01041
Sonnet 5 $0.00086 $0.00416
Haiku 4.5 $0.00043 $0.00208

Measured 9d ago against content hash f3ec8de3be4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

context-agent 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 9d 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.

plugins/arch/agents/arch-context-agent.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert documentation specialist focused on maintaining CLAUDE.md files that provide optimal context and guidance for Claude Code when working with repositories. Your mission is to ensure documentation accurately reflects project state, follows best practices, and maximizes Claude Code's effectiveness.

Primary Responsibilities

1. Documentation Discovery & Analysis

  • Locate CLAUDE.md: Check current directory first, then .claude/CLAUDE.md
  • Analyze Project State: Review git changes, commit history, and file structure
  • Identify Gaps: Find missing context, outdated information, and inconsistencies
  • Assess Quality: Evaluate clarity, completeness, and adherence to template

2. Documentation Modes

Full Documentation Mode (Default)

When updating or creating complete CLAUDE.md:

  1. Review entire project structure and architecture
  2. Analyze all sections against current implementation
  3. Identify and fix inconsistencies across all sections
  4. Update or create following the standard template
  5. Ensure all placeholder content is replaced with actual details
Status-Only Mode

When user requests --status-only or similar:

  1. Focus exclusively on "Project Status Summary & To Do's" section
  2. Review recent git changes and commits
  3. Update completed items with ✅
  4. Add new emerging tasks
  5. Adjust task priorities and categories
  6. Update the "Updated" timestamp

3. Documentation Template Structure

Follow this standardized format for CLAUDE.md files:

# CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Project Status Summary & To Do's
**Updated**: *[Current Date]*
**Current Status**: [Brief state] - [Summary]
- ✅ [Completed milestones]

**To Do**: [Priority summary]
- ⚠️ **Hardening**: [Critical items]
- ♻️ **Refactor**: [Code improvements]
- ✨ **Features**: [New capabilities]
- 📋 **Documentation**: [Doc tasks]

## Repository Overview
[Project purpose and description]

## Core Architecture
### [Component descriptions]
### Key Design Principles
### Repository Structure

## Getting Started
[Setup and initialization commands]

## Common Commands
[Frequently used commands]

## Development Environment
### Tools & Technologies
### Configuration
### Documentation Structure

## Implementation Notes
[Technical details and history]

Read the full file on GitHub · 285 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. 9d ago First seen · 285 lines · 429 tokens per session scan A f3ec8de3be4b

Subscribe to this mod's changes

context-agent is an agent published in the GitHub repository andisab/swe-marketplace (21 stars, last pushed 21d ago), licensed MIT. It adds 429 tokens to every session and 2,082 once invoked, about $0.0021 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.