HezaoHezao
Featured
poirot
Poirot is a deep research agent kernel with a middleware-first architecture, five-layer long-term memory, multi-agent orchestration, sandbox isolation, and a three-layer skill self-evolution system, backed by 2400+ tests.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It addresses a real gap in Codex's native MultiAgentV2 by providing per-worker model control and safety limits, making parallel execution predictable and cost-efficient.
Who it is for
- Codex power users seeking fine-grained model routing
- Developers automating multi-source research or multi-module engineering tasks
- Teams that need safe, auditable parallel workflows without agent proliferation
Use cases
- Parallel research across multiple independent topics
- Multi-section content generation with separate writing and review tasks
- Implementing, testing, and reviewing independent modules without file ownership overlap
- Thread Orchestration for upstream workflows like Deep Research
Strengths
- Explicit model and reasoning assignment per background task
- Built-in safety caps: max 6 concurrent tasks, 8 total, no sub‑sub‑agents
- Preserves lead agent ownership of planning, integration, and verification
- Works within existing Codex App background‑task tools without replacing MultiAgentV2
Considerations
- Requires Codex App background‑task tools (not available in all environments)
- Not designed for simple questions, status checks, or sequential operations
- Background tasks cannot use Ultra; Terra excluded from automatic routing by default
README quick start
[!IMPORTANT] This repository is a generated compatibility mirror. The editable source, Issues, and contributions live in zjp1997720/zhijian-skills.
Codex Model Routing Team
Give Codex a bounded team of model-routed background tasks while one lead keeps control of planning, integration, and verification.
简体中文 · Canonical source · Standalone mirror
Use it for complex parallel work when one lead Agent should plan and integrate while bounded background tasks run on explicitly chosen models.
Install
The standard skills CLI shorthand is valid:
npx skills add zjp1997720/codex-model-routing-team
For a global Codex installation without symlinks:
npx skills add zjp1997720/codex-model-routing-team \
-g -a codex --skill codex-model-routing-team --copy -y
The full GitHub URL works too:
npx skills add https://github.com/zjp1997720/codex-model-routing-team
Verify that the installed package contains both the entrypoint and its supporting policies:
npx skills ls -g -a codex
find ~/.agents/skills/codex-model-routing-team -maxdepth 2 -type f | sort
The file list must include SKILL.md, references/routing-policy.md, references/task-packet.md, and references/thread-lifecycle.md. If only SKILL.md appears, remove that incomplete installation and install the current release again.
Activate it
Explicit activation works immediately after installation:
Use $codex-model-routing-team to research these six independent topics in parallel, then verify and synthesize the findings.
To let Codex activate the Skill automatically for suitable complex work, add the following standing authorization to ~/.codex/AGENTS.md. Put it in a project-level AGENTS.md instead when the authorization should apply only to that project.
## Codex background model-routing authorization
- The user authorizes Codex to use `$codex-model-routing-team` automatically for complex, parallelizable tasks, create independent background tasks, and assign a model and reasoning level to each task. Before dispatch, briefly state the number of tasks, model, reasoning level, and responsibility. No additional confirmation is required.
- The lead agent keeps its current model and owns planning, file ownership, integrati
Description
Route complex Codex tasks to model-specific background workers with bounded concurrency and lead-agent verification.
Related repositories
Similar projects matched by category, topics, and programming language.
bjan
Featured
claudemux
Claudemux is a lightweight, dependency-minimal message bus that lets multiple Claude Code sessions communicate in real-time over tmux, enabling one session to ask another a question and receive the answer without manual intervention.
powerycy
Featured
goutoujunshi
An AI relationship coach that provides emotional support, relationship science, and actionable strategies through a multidisciplinary knowledge base.