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 skills/mdrideout/junjo/junjo-local-developmentnpx skills add mdrideout/junjo --skill junjo-local-developmentgit clone --depth 1 https://github.com/mdrideout/junjoWrote 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/mdrideout/junjo/junjo-local-development)<a href="https://agentmods.dev/skills/mdrideout/junjo/junjo-local-development"><img src="https://agentmods.dev/badge/skills/mdrideout/junjo/junjo-local-development.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 | $0.00041 | $0.00354 |
| Opus 5 | $0.00020 | $0.00177 |
| Sonnet 5 | $0.00008 | $0.00071 |
| Haiku 4.5 | $0.00004 | $0.00035 |
Grade A, and why
junjo-local-development 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 3d 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
Junjo Local Development
Owners
- Read
apps/studio/TESTING.mdfor the greenfield reset, local identity, credential provisioning, and validation workflow. - Read the selected example's README and
.env.examplefor its runtime and configuration contract. - Use
tooling/scripts/provision_local_studio.pyto prepare persistent local Studio credentials and ignored example environments.
Required boundaries
- Create the local owner and credentials only through Studio's public setup, session, and management APIs.
- Never edit SQLite, add migration or startup seeds, commit generated
credentials, or copy local
.envfiles into deployment artifacts. - Use persistent provisioned credentials for local human or coding-agent iteration. Keep automated validators isolated with disposable credentials that they create and remove themselves.
- Treat
apps/studio/TESTING.mdand the example-owned files as sources of truth. Do not reproduce their endpoint, credential, or environment details in new agent guidance.
Workflow
- Identify whether the task needs an ordinary restart or an explicitly authorized greenfield reset.
- Follow the Studio testing runbook to configure and start the development stack.
- Run the local provisioner before starting examples or evaluation commands.
- Follow the selected example's own run and validation instructions.
- Keep production deployment work in its owning deployment workflow; the local provisioner must never be used against production or a remote Studio.
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.
- 3d ago First seen · 40 lines · 41 tokens per session scan A 50b9a253200d
junjo-local-development is a skill published in the GitHub repository mdrideout/junjo (20 stars, last pushed 3d ago), licensed Apache-2.0. It adds 41 tokens to every session and 354 once invoked, about $0.0002 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
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
quinn
Proves the system works by writing and executing comprehensive test suites.
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
antigravity-sdk-e2e-dev
Spin up a live local Omnigent server and exercise the Antigravity (Gemini) SDK harness end-to-end — build antigravity agents, run real turns, smoke-test, and bug-bash. Load when developing, testing, or debugging the antigravity harness (omnigent/inner/antigravityexecutor.py, antigravityharness.py…
cursor-sdk-e2e-dev
Spin up a live local Omnigent server and exercise the Cursor SDK harness end-to-end — build cursor agents, run real turns, smoke-test, and bug-bash. Load when developing, testing, or debugging the cursor harness (omnigent/inner/cursorexecutor.py, cursorharness.py, cursorauth.py) or its auth / model / tool-bridge…