What is Context-Engineering AGENTS.md?

Project instructions for a TypeScript repository that combines AI-assisted development with benchmark checks. They define coding rules, dependency limits, secret scanning, and required benchmark behavior.

Use them when modifying the repository, adding benchmark runners, changing configuration, or reviewing whether a contribution follows its required engineering rules.

They make important project decisions explicit before code is changed. This helps prevent changes that fail benchmarks, leak secrets, break the TypeScript style, or add unnecessary dependencies.

How BEKO2210/Context-Engineering configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to BEKO2210/Context-Engineering. 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/BEKO2210/Context-Engineering/claude/setup-context-engineering-template-AyLkU/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/BEKO2210/Context-Engineering

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/beko2210/context-engineering/agents-md/github.svg)](https://agentmods.dev/instructions/beko2210/context-engineering/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/beko2210/context-engineering/agents-md"><img src="https://agentmods.dev/badge/instructions/beko2210/context-engineering/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/beko2210/context-engineering/agents-md"><img src="https://agentmods.dev/badge/instructions/beko2210/context-engineering/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 691 This file is loaded in full into every session.

When invoked 691 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	$0.00691	$0.00691
Opus 5.5	$0.00276	$0.00276
Sonnet 5.5	$0.00138	$0.00138
Haiku 4.5	$0.00069	$0.00069

Measured 2mo ago against content hash 7b9e266a0403, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Project-Wide Persistent Context

Identity

This is the Context Engineering + Closed-Loop Agent Benchmarks template repository, created by Belkis Aslani. It provides a production-grade scaffold for AI-assisted development workflows with built-in quality gates and benchmark-driven feedback loops.

Hard Rules

Benchmark-first policy: Every change must pass npm run benchmark before merge. Score must meet or exceed the target in benchmarks/thresholds.json.
No secrets in repo: The CI pipeline scans for leaked keys/tokens. Any match fails the build immediately.
ESM only: All TypeScript uses ES modules. No require(), no CommonJS.
Strict TypeScript: strict: true in tsconfig. No any without justification.
Minimal dependencies: Every new dependency must be justified. The dep scanner enforces a maximum count and a blocklist.
Deterministic benchmarks: All benchmark runners must produce identical scores given identical input. No network calls, no randomness.

Decision Rules

Adding a runner: Create a new file in benchmarks/runners/, implement the BenchmarkRunner interface from benchmarks/types.ts, register it in benchmarks/run.ts.
Changing weights: Edit benchmarks/scorecard.json. Weights must sum to 100.
Changing thresholds: Edit benchmarks/thresholds.json. Document the reason in docs/decisions.md.
Adding orchestrator steps: Extend tools/orchestrator/controller.ts state machine. Document in docs/orchestrator.md.

Where to Find Things

What	Where
Project docs	`docs/`
Copy-paste prompts	`prompts/`
Benchmark runners	`benchmarks/runners/`
Benchmark config	`benchmarks/scorecard.json`
Score thresholds	`benchmarks/thresholds.json`
Orchestrator	`tools/orchestrator/`
Reports	`reports/`
Example project	`examples/context-minimal/`
Lessons learned	`memory/lessons.json`
Patterns catalog	`memory/patterns.md`

Read the full file on GitHub · 66 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 · 66 lines · 691 tokens per session scan A 7b9e266a0403

Subscribe to this mod's changes

Context-Engineering AGENTS.md is an instructions file published in the GitHub repository BEKO2210/Context-Engineering (2 stars, last pushed 9mo ago), licensed MIT. It adds 691 tokens to every session, about $0.0028 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.

Memory and context

Context-Engineering AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Context-Engineering AGENTS.mdBEKO2210/Context-Engineering	Instructions file	2	9mo ago	MIT	A	691	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-Engineering: Instructions file for Codex