What is context-management-for-agents AGENTS.md?

Project instructions for a collection of 28 skills that teach coding agents how to manage their context, meaning the information they use while working.

Use them when adding or maintaining agent skills, working with the research files, or following the repository's context-management and tooling rules.

They describe the repository layout, supported agent tools, and required ways to inspect or change the project.

How navendubrajesh/context-management-for-agents configures Codex and

Reuse

Borrowing it

Nothing to install: this file belongs to navendubrajesh/context-management-for-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/navendubrajesh/context-management-for-agents/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/navendubrajesh/context-management-for-agents

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/navendubrajesh/context-management-for-agents/agents-md/github.svg)](https://agentmods.dev/instructions/navendubrajesh/context-management-for-agents/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/navendubrajesh/context-management-for-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/navendubrajesh/context-management-for-agents/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/navendubrajesh/context-management-for-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/navendubrajesh/context-management-for-agents/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,567 This file is loaded in full into every session.

When invoked 1,567 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01567	$0.01567
Opus 5.5	$0.00627	$0.00627
Sonnet 5.5	$0.00313	$0.00313
Haiku 4.5	$0.00157	$0.00157

Measured 2mo ago against content hash 0b2accd37e68, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

context-management-for-agents AGENTS.md 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 2mo 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.

AGENTS.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to AI coding agents (GitHub Copilot, Cursor, Amazon Kiro, Google Antigravity, Amazon Q Developer, and other AGENTS.md-conformant tools) when working with code in this repository.

Project Overview

Context Management for Agents: an open collection of 28 Agent Skills teaching context engineering and harness engineering for production AI agent systems. 13 skills are platform-agnostic; 15 platform skills cover five agentic coding tools (3 skills each for Copilot, Cursor, Kiro, Antigravity, and Amazon Q Developer).

Context engineering is the discipline of curating everything that enters a model's context window (system prompts, tool definitions, retrieved documents, message history, tool outputs) to maximize signal within limited attention budget.

Repository Structure

skills/ — 28 skill directories, each with SKILL.md (YAML frontmatter: name, description) and optional references/
examples/ — 5 demonstration projects
researcher/ — File-based research OS: rubrics, mechanism registry, claim provenance, corpus index, benchmarks, validation scripts
template/SKILL.md — Canonical skill template
SKILL.md (root) — Collection-level skill map
.plugin/plugin.json — Open Plugins manifest
bin/cli.js — Multi-platform installer (--platform copilot|cursor|kiro|antigravity|amazonq|claude)

Skill stacks (co-installation)

This repository provides context engineering knowledge skills. Workflow harnesses (e.g. GStack with /ship, /qa, /review) are complementary — install both with separate namespaces:

Stack	Purpose	Typical install path (Cursor)
GStack	Build, test, ship, browser QA	`.cursor/skills/gstack/`
Context engineering (this repo)	Context window discipline	`.cursor/skills/context-engineering/`

Rules:

Read one matching SKILL.md on activation; never load all skills up front.
When a GStack workflow skill is active, follow its procedure; use context skills for what to keep, compress, or mask.
Install: npx context-management-for-agents --platform cursor --setup (namespaced + discovery symlinks).

Read the full file on GitHub · 114 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.

2mo ago First seen · 114 lines · 1,567 tokens per session scan A 0b2accd37e68

Subscribe to this mod's changes

context-management-for-agents AGENTS.md is an instructions file published in the GitHub repository navendubrajesh/context-management-for-agents (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,567 tokens to every session, about $0.0063 per session on Opus 5.5. 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 2026-08-31.

Building agents Memory and context

context-management-for-agents AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
context-management-for-agents AGENTS.mdnavendubrajesh/context-management-for-agents	Instructions file	2	1mo ago	MIT	A	1,567	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

context-management-for-agents: Instructions file for Codex