What is namba-ai AGENTS.md?

Repository instructions for NambaAI, a coding workflow and command system used with Codex.

They help with planning, implementing specifications, running checks, managing tasks and preparing releases in NambaAI projects.

They tell the coding agent which commands, workflows and project rules to follow, reducing confusion when changing the repository.

How Nam-Cheol/namba-ai configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Nam-Cheol/namba-ai. 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/Nam-Cheol/namba-ai/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Nam-Cheol/namba-ai

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/nam-cheol/namba-ai/agents-md.svg)](https://agentmods.dev/instructions/nam-cheol/namba-ai/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/nam-cheol/namba-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/nam-cheol/namba-ai/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,571 This file is loaded in full into every session.

When invoked 1,571 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	$0.01571	$0.01571
Opus 5	$0.00785	$0.00785
Sonnet 5	$0.00314	$0.00314
Haiku 4.5	$0.00157	$0.00157

Measured 7d ago against content hash 8e69574e8ae4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

namba-ai 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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NambaAI

You are the NambaAI orchestrator for this repository.

Codex-Native Mode

When the user references namba, namba help, namba project, namba regen, namba update, namba codex access, namba plan, namba harness, namba fix, namba run SPEC-XXX, namba queue, namba sync, namba pr, namba land, namba release, $namba-coach, $namba-create, $namba-queue, $namba-review-resolve, or $namba-release, treat those as Namba workflow commands or guidance entry points inside the current Codex session.

Prefer direct Codex-native execution for namba run SPEC-XXX: read the SPEC package, implement the work in-session, run validation, and sync artifacts.
Use the installed namba CLI for init, doctor, project, regen, update, codex access, plan, harness, fix, queue, pr, land, release, and sync when it is available and the command should mutate repo state or maintain the installed CLI directly.
If the namba CLI is unavailable, perform the equivalent workflow manually with .namba/ as the source of truth.
Use repo skills under .agents/skills/ as the single skill surface. Command-entry and guidance skills such as $namba-help, $namba-coach, $namba-create, $namba-run, $namba-queue, $namba-pr, $namba-land, $namba-release, $namba-plan, $namba-plan-review, $namba-harness, $namba-fix, $namba-review-resolve, and the plan-review skills under .namba/specs/<SPEC>/reviews/ replace provider-specific custom command wrappers.
When delegating work with Codex multi-agent features, use built-in subagents such as default, worker, and explorer, plus project-scoped custom agents under .codex/agents/*.toml; keep .md role cards as readable mirrors.

Workflow

Run namba regen when template-generated Codex assets need regeneration.
Run namba project to refresh project docs and codemaps.
Use $namba-coach when the user's current goal is vague or a command choice may need correction before handing off to one workflow.
Use $namba-create when you need to create a repo-local skill, a project-scoped custom agent, or both through the preview-first Codex-native creation flow.
Run namba plan "<description>" for feature planning and, unless --no-review is present, continue immediately with $namba-plan-review SPEC-XXX after the SPEC is created. Use namba harness "<description>" for harness-oriented planning, namba fix --command plan "<issue description>" for bugfix SPEC planning, or namba fix "<issue description>" for direct repair.
Run the relevant plan-review skills when review is not automatic, or use $namba-plan-review when you want the create-plus-review loop bundled, and keep .namba/specs/<SPEC>/reviews/readiness.md current when the SPEC needs product, engineering, or design sign-off.
Run namba run SPEC-XXX to execute the SPEC with Codex-native workflow.
Use $namba-queue or namba queue start <SPEC-RANGE|SPEC-LIST> when existing SPEC packages should move through the conveyor one active SPEC at a time.
Run namba sync to refresh artifacts and PR-ready documents.
Run namba pr "<title>" to prepare the GitHub review handoff.
Run namba land after approvals and checks pass to merge plus refresh local main.

Read the full file on GitHub · 55 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.

7d ago First seen · 55 lines · 1,571 tokens per session scan A 8e69574e8ae4

Subscribe to this mod's changes

namba-ai AGENTS.md is an instructions file published in the GitHub repository Nam-Cheol/namba-ai (11 stars, last pushed 14d ago), licensed MIT. It adds 1,571 tokens to every session, about $0.0079 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.

agentic-workflow ai-agents ai-coding cli codex

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

namba-ai: Instructions file for Codex