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-openai-agentsnpx skills add mdrideout/junjo --skill junjo-openai-agentsgit 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-openai-agents)<a href="https://agentmods.dev/skills/mdrideout/junjo/junjo-openai-agents"><img src="https://agentmods.dev/badge/skills/mdrideout/junjo/junjo-openai-agents.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 5.1 | $0.00090 | $0.01050 |
| Opus 5 | $0.00045 | $0.00525 |
| Sonnet 5 | $0.00018 | $0.00210 |
| Haiku 4.5 | $0.00009 | $0.00105 |
Grade A, and why
junjo-openai-agents 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Junjo + OpenAI Agents
Integrate Junjo additively inside the application repository. The OpenAI Agents SDK remains the outer Agent runtime. Junjo remains the native, opinionated Workflow, state, concurrency, telemetry, and evaluation layer.
Boundaries
- Install the optional extra with
junjo[openai-agents]. Do not add OpenAI Agents dependencies to Junjo's default runtime path. - Use the public
junjo.plugins.openai_agentsmodule. Do not copy adapters or instrumentation into the application. - Keep telemetry bootstrap application-owned and process-lifetime. Reuse the
application's existing OpenTelemetry SDK
TracerProviderand exporter. - Instrument explicitly during application startup and close the returned integration handle during shutdown. Never instrument at module import time.
- Treat OpenAI Agent spans as standard OpenTelemetry GenAI evidence. Do not rewrite them into fake Junjo Agent spans or send them through a separate proprietary ingestion path.
- Keep native Junjo Workflows and Agents semantically native. Their tool adapters translate inputs, outputs, and invocation cleanup; they do not merge execution identities or lifecycle ownership.
- Preserve separate Studio credentials: the application telemetry API key exports OTLP; the developer access token operates datasets and evidence.
Inspect before changing
Read the application's instructions, dependency manifest, telemetry startup, shutdown path, Agent construction, Junjo definitions, and evaluation harness. Inspect the installed public API and docs rather than guessing signatures.
Determine how the application configures OpenAI Agents tracing processors. Junjo wraps the active first-party tracing provider and preserves its processors and export policy. Reuse the application's OpenTelemetry provider and make one owner responsible for shutdown.
Compose explicit tools
Expose a fresh native Junjo Workflow or Junjo Agent invocation through the framework-specific adapter that matches it. Map:
What ships with it
1 file 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.
- 6d ago First seen · 108 lines · 90 tokens per session scan A ff9a30c9ed58
junjo-openai-agents is a skill published in the GitHub repository mdrideout/junjo (20 stars, last pushed 6d ago), licensed Apache-2.0. It adds 90 tokens to every session and 1,050 once invoked, about $0.0005 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
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
implementation-final-review
Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and…
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
api-docs
Document a module or public API surface (functions, classes, CLI commands, endpoints) from the code itself. Use when the user asks for API reference, to document a module, or to write usage docs for a public interface.
benchmark-tune
Use this skill when running, debugging, interpreting, or documenting mesh-llm benchmark tune model-serving throughput trials, including choosing ctx/batch/ubatch/mmap/mlock/speculative-decoding sweeps, running benchmark tune on local or SSH hosts, collecting JSON evidence, and applying tolerance-aware recommendations.…
deploy-windows
Use this skill when installing, deploying, launching, serving, or troubleshooting mesh-llm on a Windows machine — PowerShell install via install.ps1, flavor selection (CUDA/ROCm/Vulkan/CPU), source builds, the contrib helper scripts, and verifying it serves.