adaptive-grok-build-pro: Instructions file for Claude Code

AGENTS.md

adaptive-grok-build-pro AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from Dimkox/adaptive-grok-build-pro. It costs 2,770 tokens per session, scanned A, original, MIT.

Project instructions for Adaptive Grok Build Pro, including how agents start work, record decisions, and preserve project handoffs.

In plain words
What is it for?
Use them to find the current milestone, choose the correct branch or task, record useful decisions or mistakes, and protect secrets and runtime data.
Why use it?
They let a new agent continue from a fresh checkout without relying on earlier chat messages or fabricating missing local state.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: UserPromptSubmit hook event, but also the file is AGENTS.md. Also seen: mentions subagents; mentions AGENTS.md.

This is Dimkox/adaptive-grok-build-pro's own configuration. It tells Claude Code, Codex and OpenCode how to work on adaptive-grok-build-pro itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything adaptive-grok-build-pro configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Dimkox/adaptive-grok-build-pro. 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/Dimkox/adaptive-grok-build-pro/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Dimkox/adaptive-grok-build-pro

Made for: Claude Code, 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.

agentmods badge for adaptive-grok-build-pro AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dimkox/adaptive-grok-build-pro/agents-md.svg)](https://agentmods.dev/instructions/dimkox/adaptive-grok-build-pro/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/dimkox/adaptive-grok-build-pro/agents-md"><img src="https://agentmods.dev/badge/instructions/dimkox/adaptive-grok-build-pro/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,770 This file is loaded in full into every session.
When invoked 2,770 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02770 $0.02770
Opus 5 $0.01385 $0.01385
Sonnet 5 $0.00554 $0.00554
Haiku 4.5 $0.00277 $0.00277

Measured 7d ago against content hash 6f9216579ffb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

adaptive-grok-build-pro 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 7d 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 · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adaptive Grok Build Pro Engineering Contract

Agent self-learning

  • If you make a decision that turns out to be correct and worth the effort, log it in decisions.md (pattern + why it worked, no more than 3 sentences).
  • If you make a mistake that leads to a problem, identify the root cause (not the symptom) and record it in mistakes.md.

Fresh-clone bootstrap

  • START_HERE.md is the zero-context entrypoint. PROJECT_STATE.json is the machine-readable current handoff. A new agent must not require chat history to understand the current milestone and next action.
  • .grok-stack/runtime/active-route.json is machine-local runtime state and may legitimately be absent in a fresh clone. Never fabricate it. If it is absent, read START_HERE.md and PROJECT_STATE.json, fetch remote refs, then either continue the active pull-request branch named there or route a new task before implementation.
  • Milestone designs and implementation plans must live in the repository or the active pull request before a session ends. Chat is the lowest-priority source of truth.
  • Secrets, PEM/private keys, credentials, PostgreSQL runtime state, runtime approvals/receipts and host-local deployment scratch are intentionally not Git content. Their absence does not make a fresh clone incomplete for source development.

Independent merge trust

  • Prompt files, hooks, .grok-stack/runtime, local delegated grants, local receipts, change packages, local tests and agent reviews are workflow evidence only. They are not merge authority.
  • The authoritative merge gate is the GitHub App-owned policy-epoch Check Run adaptive-trust-ci/verified@<policy-sha12> for the exact pull-request head SHA. Branch protection binds that exact check name to the configured GitHub App ID.
  • Never use GitHub Actions for this repository. Trust CI is operated from trust-ci/ with PostgreSQL durable state, isolated exact-SHA runners, external holdout validation, source-mutation detection, signed attestations and human-signed scoped approvals.
  • An agent must never generate, read, request, submit or simulate a human approval private key. Human security approvals are signed outside the agent environment and verified by the Trust CI API against its server-mounted public-key store.
  • Repository changes cannot modify deployed Trust CI policy, deployed holdout bundle, deployed images, PostgreSQL state, CI signing keys, GitHub App key, human trust stores or branch protection. Those live outside the pull-request trust domain.

Read the full file on GitHub · 175 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.

  1. 7d ago First seen · 175 lines · 2,770 tokens per session scan A 6f9216579ffb

Subscribe to this mod's changes

adaptive-grok-build-pro AGENTS.md is an instructions file published in the GitHub repository Dimkox/adaptive-grok-build-pro (2 stars, last pushed yesterday), licensed MIT. It adds 2,770 tokens to every session, about $0.0138 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens