agent-context AGENTS.md

A set of instructions for AI coding agents working in large repositories. It uses project context files to decide where to search and what rules to load before inspecting source code.

In plain words
What is it for?
Use it when an agent needs to navigate a large codebase, follow scoped search rules, and load the right templates or validation requirements for a task.
Why use it?
It prevents an agent from searching unrelated folders or opening code before understanding the repository’s task-specific rules. This makes work more focused and consistent.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/cote-star/agent-context/agents-md
Clone the repo
git clone --depth 1 https://github.com/cote-star/agent-context

Made for: Codex, OpenCode.

Per session 74 This file is loaded in full into every session.
When invoked 74 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00074 $0.00074
Opus 5 $0.00037 $0.00037
Sonnet 5 $0.00015 $0.00015
Haiku 4.5 $0.00007 $0.00007

Measured 2d ago against content hash d6c094db351a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-context 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 2d 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 · 7 lines

What it actually says

  1. Read .agent-context/current/routes.json to identify task type
  2. Load contracts from .agent-context/current/completeness_contract.json + .agent-context/current/search_scope.json
  3. Search ONLY within scoped directories defined in search_scope.json
  4. Do not open repo source files before step 3
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. 2d ago First seen · 7 lines · 74 tokens per session scan A d6c094db351a

Subscribe to this mod's changes

agent-context AGENTS.md is an instructions file published in the GitHub repository cote-star/agent-context (2 stars, last pushed 2mo ago), licensed MIT. It adds 74 tokens to every session, about $0.0004 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 2026-08-31.