What is gojaja AGENTS.md?

Repository-specific instructions for agents and developers working on the gojaja package. They explain where important documentation and code live, along with rules for changing, testing, and validating the project.

Use them when editing gojaja, choosing where to look for information, running checks, changing filesystem or path-handling code, and deciding what must not be committed.

They reduce mistakes caused by ignoring the repository's architecture, file rules, data format, or testing expectations.

How smilezheng/gojaja configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to smilezheng/gojaja. 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/smilezheng/gojaja/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/smilezheng/gojaja

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/smilezheng/gojaja/agents-md/github.svg)](https://agentmods.dev/instructions/smilezheng/gojaja/agents-md)

Your own site

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

Per session 1,060 This file is loaded in full into every session.

When invoked 1,060 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	$0.01060	$0.01060
Opus 5	$0.00530	$0.00530
Sonnet 5	$0.00212	$0.00212
Haiku 4.5	$0.00106	$0.00106

Measured 9d ago against content hash d34b078b5a96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gojaja 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 9d 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 · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Working notes for any agent (or human) editing this repository.

This repository builds the gojaja package; it is not a project that consumes it. The .gojaja/ runtime layer is only created when an end-user runs gojaja init inside their own project. Do not commit a .gojaja/ directory at the repo root.

Where to look first

You want to ...	Read ...
Understand the architecture	docs/DESIGN.md
Know what file lives where on disk	docs/SCHEMA.md
Implement an agent that talks to the layer	docs/PROTOCOL.md
Pick the next PR to land	docs/ROADMAP.md
See what just shipped	CHANGELOG.md

Working rules

src/ is authoritative implementation. tests/ is the regression contract; never weaken a test to make code pass.
All filesystem access in command code must go through the Store interface (src/core/store.ts). Direct fs.* usage is allowed only inside src/core/*.ts adapters and inside tests.
Path / role-id / slug inputs must be validated by the helpers in src/core/paths.ts and src/core/role-id.ts. No ad-hoc regexes in command code.
The on-disk schema version is SCHEMA_VERSION in src/cli/runtime.ts. Current: 3.0.0 (v3 two-tree layout per RFC-0001). Bump it together with any breaking change to the layout written by LocalFsStore.initialise, and update docs/SCHEMA.md in the same PR.
v3 splits the layer into a small git-tracked user tree at <project>/.gojaja/ (project.json, config.yaml, roles/.md, state/project_state.md) and a per-user central tree at ~/.gojaja/projects/<id>/ (task board, events, sessions, RFCs, worklog, locks). Path routing is decided by classifyPath in src/core/path-routing.ts; new mutable surfaces default to central unless they're a fresh-clone contract. v2 single-root layouts still open via openStoreOrThrow (no project.json marker) for the deprecation window.
SYSTEM is no longer an implicit default. Any command that emits an event with from: SYSTEM requires explicit --as-system at the CLI layer (resolveActor in src/cli/identity.ts). role create / role delete also accept a delegated session owning config.yaml. SYSTEM events carry actorMeta (pid / cwd / user / hostname / tty / ppid) so audit can identify the originating process. See CHANGELOG PR9 SYSTEM-1/-2/-3 for the threat model.
Every typed error class has a stable exit code (see docs/DESIGN.md → Errors). Do not invent new ad-hoc process.exit(7) calls; subclass GojajaError instead.

Read the full file on GitHub · 89 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.

9d ago First seen · 89 lines · 1,060 tokens per session scan A d34b078b5a96

Subscribe to this mod's changes

gojaja AGENTS.md is an instructions file published in the GitHub repository smilezheng/gojaja (40 stars, last pushed 2mo ago), licensed MIT. It adds 1,060 tokens to every session, about $0.0053 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.

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 · 5,153 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

gojaja: Instructions file for Codex