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.
npx agentmods add instructions/yeachan-heo/gajae-code/agents-mdgit clone --depth 1 https://github.com/Yeachan-Heo/gajae-codeWrote 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.
[](https://agentmods.dev/instructions/yeachan-heo/gajae-code/agents-md)<a href="https://agentmods.dev/instructions/yeachan-heo/gajae-code/agents-md"><img src="https://agentmods.dev/badge/instructions/yeachan-heo/gajae-code/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02615 | $0.02615 |
| Opus 5 | $0.01307 | $0.01307 |
| Sonnet 5 | $0.00523 | $0.00523 |
| Haiku 4.5 | $0.00262 | $0.00262 |
Grade A, and why
gajae-code AGENTS.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| Spawn simple commands | Bun Shell (`$\`cmd\``) | `child_process` | How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gajae-Code Agent Contract
Gajae-Code (gjc) is a Bun-workspace TypeScript monorepo with Rust natives. This file is the repo-local operating contract: architecture map, dev utilities, and the rules that are not derivable from docs/. For deep dives, start at docs/ (per-topic) and docs/tools/ (per-tool runtime docs).
Architecture
Runtime is Bun (bun@<pinned in package.json>); everything runs from source via bun, and release binaries are compiled with packages/coding-agent/scripts/build-binary.ts.
Dependency direction (roughly bottom-up):
utils ─┬─▶ ai ─────┬─▶ agent ─▶ coding-agent (gjc CLI, primary product surface)
├─▶ tui ────┘ │
└─▶ natives (napi-rs ◀── crates/pi-natives)
└─▶ stats (dashboard), sdk surfaces
| Workspace | Role |
|---|---|
packages/coding-agent |
Main gjc CLI. Entry: src/cli.ts. Subsystems live in src/ (tools, tui, session, sdk, workflow, hooks, lsp, daemon, …). Unless stated otherwise, work targets this package. |
packages/agent |
Agent runtime: tool calling, state, orchestration. |
packages/ai |
Multi-provider LLM client with streaming. src/models.json is generated — never edit; regenerate via bun run generate-models. |
packages/tui |
Terminal UI library with differential rendering. |
packages/natives + packages/natives-<platform> |
napi-rs bindings over crates/pi-natives (text/image/grep/shell/pty). See docs/natives-*.md. |
packages/stats |
Local observability dashboard (gjc stats). |
packages/utils |
Shared utilities (@gajae-code/pi-utils): logger, isCompiledBinary, path/string helpers. |
packages/*-benchmark |
Edit / orchestration-token benchmarks; not shipped. |
crates/ |
Rust: pi-natives, pi-shell/brush-* (vendored shell), pi-ast, pi-iso, git-daemon, gjc-sdk. Driven via bun scripts/run-rs-task.ts. |
When the user says "agent" or asks why the agent behaves a certain way, they mean the coding-agent CLI implementation, not the assistant editing the repo.
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.
- 4d ago First seen · 190 lines · 2,615 tokens per session scan A 3806eed07036
gajae-code AGENTS.md is an instructions file published in the GitHub repository Yeachan-Heo/gajae-code (2,691 stars, last pushed yesterday), licensed MIT. It adds 2,615 tokens to every session, about $0.0131 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.