context-management

context-management is a plugin for Claude Code from Sagargupta16/claude-skills. Its manifest loads nothing; the 1 skill, 1 command, 1 agent it bundles cost 147 tokens per session together, scanned A, original, MIT.

A set of methods for managing the conversation space an AI coding agent can use during a session.

In plain words
What is it for?
Planning context compaction, preventing context quality from degrading, branching work, and separating tasks handled by sub-agents.
Why use it?
Long coding sessions can lose important instructions or become repetitive when earlier context is crowded. These methods address when to shorten context, split work, or isolate sub-agent tasks.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest. Also seen: mentions subagents.

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.

Claude Code
/plugin marketplace add Sagargupta16/claude-skills
agentmods
npx agentmods add plugins/sagargupta16/claude-skills/context-management
Clone the repo
git clone --depth 1 https://github.com/Sagargupta16/claude-skills

Made for: Claude Code.

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-management

README.md
[![agentmods](https://agentmods.dev/badge/plugins/sagargupta16/claude-skills/context-management.svg)](https://agentmods.dev/plugins/sagargupta16/claude-skills/context-management)
Your own site
<a href="https://agentmods.dev/plugins/sagargupta16/claude-skills/context-management"><img src="https://agentmods.dev/badge/plugins/sagargupta16/claude-skills/context-management.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill, 1 command, 1 agent cost 147 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

context-management 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 5d 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/context-management/.claude-plugin/plugin.json · 6 lines

What it actually says

{
  "name": "context-management",
  "description": "Context window management -- compaction timing, context rot prevention, branching strategies, and sub-agent isolation patterns.",
  "version": "4.2.0"
}
Contents

What it installs

The manifest is a name and a version. 1 skill, 1 command, 1 agent travel with it, and installing the plugin installs all of them — 147 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 5d ago First seen · 6 lines scan A 492229cd0474

Subscribe to this mod's changes

context-management is a plugin published in the GitHub repository Sagargupta16/claude-skills (5 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Related

Other plugins, from other repositories

context-guard

Per-session context-window observability plus the first shipped consumer: a statusline wrapper tees each session's contextwindow fields to a per-session snapshot file, a zone resolver classifies usage into smart/acceptable/dumb bands (percentage bands plus window-class token bands, conservative-min combination, zones.

melodic-software/claude-code-plugins · not measured

claude-memory

Keeps a repo's Claude Code memory layer healthy and under your control, against criteria derived from official Claude Code documentation. The audit skill checks the instruction/memory layer (CLAUDE.md, CLAUDE.local.md, .claude/rules/, auto-memory) with a deterministic script-backed spine plus judgment-tier checks. The.

melodic-software/claude-code-plugins · not measured

commons

Shared infrastructure: daily master brief (single autonomous entry point with Yesterday Debrief gate, Key Stats headline block, and reports/summary/ trend store), product identity, brand voice, brand review, marketing identity, marketing strategy, marketing briefs, hypothesis ledgers (H-###), CLI reference, and…

systempromptio/systemprompt-marketplace · not measured

test-writing

Generate and validate PHPUnit tests for Shopware 6. Unit tests: analyzes source classes to detect category (DTO, Service, Flow/Event, DAL, Exception) and applies category-specific templates. Migration tests: analyzes SQL operations to generate pattern-appropriate migration tests with 8 migration-specific rules.…

shopwareLabs/ai-coding-tools · not measured

dev-tooling

Three MCP servers for PHP and JavaScript operations plus an optional PHP language server. PHP (php-tooling): PHPStan, ECS, Rector, PHPUnit, PHPUnit coverage gap analysis, Symfony Console. Administration (js-admin-tooling): ESLint, Stylelint, Prettier, Jest, TypeScript, Vite builds. Storefront (js-storefront-tooling)…

shopwareLabs/ai-coding-tools · not measured

discipline

Discipline correctors that re-anchor a standing rule mid-session, then audit both the work in flight and the pre-existing state and choices it trusts, and correct what has drifted: do-your-research (research and no-assumptions discipline; sibling do-your-research-deep escalates to a typed full inventory of the…

melodic-software/claude-code-plugins · not measured