Gajae Code is an external coding-agent harness that works inside repositories or worktrees and guides an agent through planning, review, approval, and code changes. It is for developers who want to use an existing coding-plan subscription while controlling agent work from a terminal, phone, or bot. The catalogue entries provide extensions such as skills, agents, commands, plugins, and MCP integrations for the harness.
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 skills add Yeachan-Heo/gajae-code --skill gjc-sdk-authorgit 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/skills/yeachan-heo/gajae-code/gjc-sdk-author)<a href="https://agentmods.dev/skills/yeachan-heo/gajae-code/gjc-sdk-author"><img src="https://agentmods.dev/badge/skills/yeachan-heo/gajae-code/gjc-sdk-author/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.
<a href="https://agentmods.dev/skills/yeachan-heo/gajae-code/gjc-sdk-author"><img src="https://agentmods.dev/badge/skills/yeachan-heo/gajae-code/gjc-sdk-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00024 | $0.00413 |
| Opus 5 | $0.00012 | $0.00206 |
| Sonnet 5 | $0.00005 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
gjc-sdk-author 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.
What it actually says
Author broker-bound GJC session scripts
Start from the owned templates in this skill directory:
templates/direct-sdk.tstemplates/direct-sdk.py
Authoring contract
- Invoke the documented
gjc sdk sessionCLI as a child process. It routes live controls throughSessionRouterand lifecycle mutations throughSessionLifecycleServiceand the Broker. - Require explicit repository and session-ID inputs. Run the CLI with the repository as its working directory; do not infer a session from local state.
- Never scan
.gjc/state/sdk, parse endpoint records, read endpoint credentials, or open a raw per-session WebSocket. - Use only
gjc sdk session raw query <sessionId> --query <query>for fixed inspection queries andgjc sdk session raw control <sessionId> --op <operation> --json-input <object> --confirmfor fixed controls. - Pass CLI arguments as an argv array, never through a shell command string.
- Keep query and control operation names on fixed allowlists. Reject secret-shaped input fields before dispatch.
- Require an immediately preceding, single-use human approval before every mutation.
- Use the template's nonce-bearing operation/session/input-bound standard-input challenge; never replace it with a free boolean or reusable approval.
- Send no CLI request after denial or cancellation.
- Bind durable workflow controls to the expected session ID.
- Render only parsed, redacted CLI JSON. Discard raw CLI stderr and never render credentials.
- Keep broader lifecycle orchestration behind
gjc sdk session raw globalwith a stable idempotency key or an SDK-core lifecycle facade; the canonical templates do not invent lifecycle routing. - State that approval is a trusted-local procedural safeguard, not capability isolation; Broker and Router retain attachment authority.
Generated user scripts belong in the user's workspace. Only the two canonical templates are owned by this clean-generated bundle.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 30 lines · 24 tokens per session scan A e58fe81a880e
gjc-sdk-author is a skill published in the GitHub repository Yeachan-Heo/gajae-code (2,744 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 413 once invoked, about $0.0001 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.
Other skills, from other repositories
langgraph-docs
Fetches and references LangGraph Python documentation to build stateful agents, create multi-agent workflows, and implement human-in-the-loop patterns. Use when the user asks about LangGraph, graph agents, state machines, agent orchestration, LangGraph API, or needs LangGraph implementation guidance.
stripe-projects
Use after E2B sandbox/API access has been provisioned through Stripe Projects and the user needs to use the resulting E2B API key with the E2B CLI, JavaScript SDK, Python SDK, or Code Interpreter SDK.
ax-python-llm
Use when writing Python code with axllm for using the generated Ax package, factory functions, package docs, examples, and API reference.
ax-python-signature
Use when writing Python code with axllm for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
claude-api
Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.