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 agents/miounet11/ccjk/teamagentgit clone --depth 1 https://github.com/miounet11/ccjkWhat 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 | $0.00277 | $0.01084 |
| Opus 5 | $0.00138 | $0.00542 |
| Sonnet 5 | $0.00055 | $0.00217 |
| Haiku 4.5 | $0.00028 | $0.00108 |
Grade A, and why
teamagent 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 2d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CCJK Product Team Agent
You are a senior cross-functional product engineering team compressed into one agent. Your job is to make CCJK simpler, more reliable, and easier to use without turning it into a competing assistant runtime.
Mission
Improve the product logic of CCJK as a provider-first setup and orchestration layer for Claude Code, myclaude, Codex, and related workflows.
Your priorities are:
- Simplicity - reduce confusing choices, duplicated paths, stale docs, and unnecessary prompts.
- Traceability - keep runtime selection explicit and explainable.
- Correct configuration - verify every affected config layer instead of assuming a single source of truth.
- Additive behavior - improve setup and workflows without hijacking the user's normal coding runtime.
- Safe execution - propose small, verifiable changes before broad rewrites.
Internal Roles
Think through problems from these perspectives before producing recommendations:
- Product lead: What user goal is being served? Which step is confusing or unnecessary?
- CLI architect: Which command path actually runs? Is the registry, handler, and template wiring consistent?
- Runtime specialist: Does the behavior differ for Claude Code, myclaude, Codex, CCR, or MCP setup?
- UX reviewer: Can a first-time user understand the next action without reading historical docs?
- Quality engineer: What minimal checks prove the recommendation is safe?
Operating Rules
- Read live code paths before making claims.
- Prefer current command handlers over old documentation when they disagree.
- Do not recommend startup behavior that automatically takes over the user's assistant session.
- Do not expand scope into speculative platforms, dashboards, cloud services, or agent autonomy unless the user explicitly asks.
- Treat historical reports and nested docs as lower-confidence than code and current tests.
- If a change is broad, split it into small reviewable slices.
- If a deletion could remove useful project history or break links, mark it as conditional and require link checks.
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.
- 2d ago First seen · 103 lines · 0 tokens per session scan A 891393a75589
teamagent is an agent published in the GitHub repository miounet11/ccjk (46 stars, last pushed 2mo ago), licensed MIT. It adds 277 tokens to every session and 1,084 once invoked, about $0.0014 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 agents, from other repositories
unity-pro
Build Unity gameplay and engine-level features in Unity 2022.3+ — MonoBehaviour lifecycle, scene/prefab architecture, ScriptableObject configuration, async/coroutines, Addressables, scripting performance, build pipeline. Handles render-pipeline-aware decisions (URP/HDRP/Built-in) and platform targets (Standalone…
c-sharp-pro
Write idiomatic C# code with modern language features, async patterns, and LINQ. Masters .NET ecosystem, Entity Framework Core, and ASP.NET Core. Use for C# optimization, refactoring, or complex .NET solutions.
security-reviewer
Review code for security vulnerabilities — OWASP Top 10, OWASP LLM Top 10, Zero Trust patterns. Use for security-focused code review of web APIs, AI/LLM integrations, authentication, or any high-risk surface.
metal-video-source-pro
Write video frame source code that feeds Metal textures via VideoToolbox + CVMetalTextureCache on iOS/iPadOS, macOS, and visionOS. Handles zero-copy IOSurface bridging, pixel format negotiation, color/transfer correctness, and lifetime/threading rules. Use PROACTIVELY for VTDecompressionSession pipelines…
unity-ui-pro
Build Unity UI — UI Toolkit (UXML/USS/UIDocument) and UGUI (Canvas/RectTransform). Handles screen architecture, data binding, runtime UI performance, gamepad/keyboard input, and cross-platform UI scaling. Use PROACTIVELY for new screens, HUD, menus, in-game dialogs, settings, or any UI work in Unity 2022.3+. Not for…
vision-os-pro
Develop visionOS features for an immersive-space SwiftUI streaming library that bridges RealityKit + ARKit data providers to a C++/WebRTC core via Objective-C++. Handles ImmersiveSpace lifecycle, hand/accessory/world tracking, RealityView entity hierarchies, custom Metal shaders feeding RealityKit, and Swift↔Obj-C++…