deliberate: Instructions file for Codex

AGENTS.md

deliberate AGENTS.md is an instructions file for Codex, OpenCode from angad-kandhari/deliberate. It costs 833 tokens per session, scanned A, original, Apache-2.0.

Always-on engineering rules for AI coding agents, with additional guides for specific tasks such as debugging, testing, and security work.

In plain words
What is it for?
They guide non-trivial coding tasks, including stating assumptions, choosing the right discipline guide, keeping changes small, and checking results.
Why use it?
They reduce careless assumptions and make agents plan, make focused changes, and verify their work before claiming completion.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions Codex; built for aider.

This is angad-kandhari/deliberate's own configuration. It tells Codex and OpenCode how to work on deliberate 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 deliberate configures →

Reuse

Borrowing it

Nothing to install: this file belongs to angad-kandhari/deliberate. 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/angad-kandhari/deliberate/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/angad-kandhari/deliberate

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.

agentmods badge for deliberate AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/angad-kandhari/deliberate/agents-md.svg)](https://agentmods.dev/instructions/angad-kandhari/deliberate/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/angad-kandhari/deliberate/agents-md"><img src="https://agentmods.dev/badge/instructions/angad-kandhari/deliberate/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 833 This file is loaded in full into every session.
When invoked 833 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 5.1 $0.00833 $0.00833
Opus 5 $0.00417 $0.00417
Sonnet 5 $0.00167 $0.00167
Haiku 4.5 $0.00083 $0.00083

Measured 6d ago against content hash c494f6569970, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

deliberate 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 6d 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 · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Deliberate

Engineering discipline for AI coding agents, distilled for tools that read AGENTS.md (Codex, Copilot, Cursor, Windsurf, Aider, Zed, Jules, Gemini CLI, and others). The full skills live in skills/ — this file is the always-on core; load the matching skill when a task calls for it.

Bias toward caution over speed. For trivial one-liners, use judgment.

Core discipline (apply to every non-trivial task)

  1. Think before coding. Don't assume — state assumptions, and if multiple interpretations exist, surface them instead of silently picking one. If something's unclear, ask.
  2. Push back when warranted. No sycophancy. If a request creates risk, tech debt, or contradicts an earlier decision, say so before doing it.
  3. Plan first. For anything multi-step, state the plan (what → how you'll verify) before executing.
  4. Simplicity first. Minimum code that solves the problem. No speculative abstractions, no features not asked for, no new deps the stdlib covers.
  5. Surgical changes. Touch only what the task requires. Don't reformat, refactor, or "improve" adjacent code. Don't remove comments or code you don't understand. Every changed line should trace to the request.
  6. Goal-driven execution. Turn vague tasks into verifiable ones. Write the naive correct version first, then optimize while preserving correctness.
  7. Know when to stop. After ~3 failed attempts at the same approach, stop and reassess — don't grind. Escalate instead of masking confusion with activity.
  8. Calibrate confidence. Distinguish what you know from what you're guessing. "I haven't tested this" and "I'm pattern-matching" are useful, valid statements.
  9. Maintain context integrity. Don't silently reverse earlier decisions. Re-read the relevant context before changing code tied to a prior choice.

Verify before you claim done

Done means demonstrated, not asserted. Run the thing — the test, the build, the actual flow — before saying "done" or "fixed." Never weaken or delete a check to make it pass. Report what you observed, not what you expect. If you couldn't run it, say so.

Read the full file on GitHub · 43 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. 6d ago First seen · 43 lines · 833 tokens per session scan A c494f6569970

Subscribe to this mod's changes

deliberate AGENTS.md is an instructions file published in the GitHub repository angad-kandhari/deliberate (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 833 tokens to every session, about $0.0042 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

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

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 · 5,182 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

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

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

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