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.
npx agentmods add instructions/fending/context-engineering/agents-mdgit clone --depth 1 https://github.com/fending/context-engineeringWhat 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 | $0.00825 | $0.00825 |
| Opus 5 | $0.00413 | $0.00413 |
| Sonnet 5 | $0.00165 | $0.00165 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
context-engineering 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 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This is the context file for this repository -- the one about context engineering. CLAUDE.md is symlinked to this file for Claude Code compatibility. For usage notes and an overview of what's here, read the README.
What This Project Is
A public companion repo to Rethinking Team Topologies for AI-Augmented Development. Working examples of context file structures (single-file, context directory, cascading, agents) alongside reference copies of the context-setup plugin (which has since moved!). Patterns you understand are here, IDE helpers you can install from ordovera/ordovera-plugins.
Structure
examples/-- All patterns and templates, organized by complexity levelsingle-file/-- Four single-file AGENTS.md examples at different complexity levelsdirectory/-- Full context directory with six template filescascading-files/-- Global, project, and subdirectory cascading examplesagents/-- Agent-as-workflow pattern with two example agents and shared configagent-teams/-- Multi-agent teams with optional Jira integration (activation, team structure, phases, templates)
examples/claude-config/-- Working skills and hooks configuration (copy to.claude/)plugins/-- Reference copies of Claude Code plugins (install from ordovera/ordovera-plugins instead)context-setup/-- Scaffold, audit, align, optimize MCP tools, usage diagnostics, and upgrade context files
evolution.md-- What changed since the June 2025 article
Standards
- No emojis, no decorative symbols
- kebab-case filenames
- Direct, practitioner voice -- not academic, not marketing
- Conventional commits (feat/fix/docs/etc)
- All markdown must pass markdownlint (MD013 disabled for line length)
- Example files use
[bracket]placeholders -- no fictional companies or products
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 · 59 lines · 825 tokens per session scan A b9e0f42233e2
context-engineering AGENTS.md is an instructions file published in the GitHub repository fending/context-engineering (11 stars, last pushed 5mo ago), licensed MIT. It adds 825 tokens to every session, about $0.0041 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.
Other instructions, from other repositories
cocoindex-code CLAUDE.md
Instructions for cocoindex-io/cocoindex-code, covering claude.md, build and test commands, architecture, process model and key layers.
packmind AGENTS.md
Instructions for PackmindHub/packmind, covering core technologies, directory structure, local development environment, working with nx and code quality.
packmind CLAUDE.md
Instructions for PackmindHub/packmind, covering nx monorepo structure, core technologies, directory structure, local development environment and working with nx.
packmind packmind-backend-tests-redaction.instructions.md
Instructions for PackmindHub/packmind: This standard establishes best practices for writing backend tests using Jest in the Packmind monorepo. It focuses on clarity, maintainability, and consistency across test suites by emphasizing behavi... .
packmind packmind-frontend-data-flow.instructions.md
Instructions for PackmindHub/packmind: This standard defines the recommended data flow pattern for frontend routes in the Packmind codebase using React Router v7 in framework mode with TanStack Query for data management. It ensures consist... .
packmind packmind-nestjs-module-hierarchy.instructions.md
Instructions for PackmindHub/packmind: Establish a consistent NestJS module structure in the API application where each resource is encapsulated in its own module with proper hierarchical organization to enhance maintainability, scalabilit... .