# brifl/coding-agent-orchestration architecture

> Architecture diagram of the GitHub repository brifl/coding-agent-orchestration, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-06). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/brifl/coding-agent-orchestration
- Repository: https://github.com/brifl/coding-agent-orchestration

## Overview

Vibe is a coding-agent orchestration system: a user asks the dispatcher for status or the next action, follows a selected prompt loop, and records verified progress in file-backed state until checkpoints and stages are complete. The graph emphasizes the dispatcher, prompt catalog, workflow sequencing, planning and checkpoint support, and installed skill experience. It also preserves the RLM context-bundle/runtime/provider branch. Source excerpts are partial; unsampled feature links are shown only where the README or SOURCE INDEX supports them.

Main entry points: [`tools/agentctl.py`](https://github.com/brifl/coding-agent-orchestration/blob/main/tools/agentctl.py) (Workflow CLI), [`tools/prompt_catalog.py`](https://github.com/brifl/coding-agent-orchestration/blob/main/tools/prompt_catalog.py) (Prompt lookup), [`tools/rlm/context_bundle.py`](https://github.com/brifl/coding-agent-orchestration/blob/main/tools/rlm/context_bundle.py) (Context bundler), [`.vibe/PLAN.md`](https://github.com/brifl/coding-agent-orchestration/blob/main/.vibe/PLAN.md) (Checkpoint plan)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_dispatch["Workflow dispatch"]
  node_agentctl["Workflow CLI<br/>[agentctl.py]"]
  node_workflow_engine["Workflow sequencing<br/>[workflow_engine.py]"]
  node_workflow_defs["Configured loops"]
end

subgraph group_planning["Planning and state"]
  node_state["Workflow state<br/>[STATE.md]"]
  node_plan["Checkpoint plan<br/>[PLAN.md]"]
  node_history_context["History and context<br/>[.vibe]"]
  node_plan_pipeline["Plan generation<br/>[plan_pipeline.py]"]
  node_checkpoint_templates["Checkpoint templates"]
end

subgraph group_prompts["Prompts and skills"]
  node_loop_prompts["Loop prompt catalog"]
  node_prompt_catalog["Prompt lookup<br/>[prompt_catalog.py]"]
  node_prompt_paths["Prompt path resolution"]
  node_resource_resolver["Resource resolution"]
  node_skills["Agent skills<br/>[skills]"]
  node_bootstrap["Repository bootstrap<br/>[bootstrap.py]"]
  node_skillctl["Skill management<br/>[skillctl.py]"]
end

subgraph group_rlm["RLM task runtime"]
  node_context_builder["Context bundler<br/>[context_bundle.py]"]
  node_task_schema["RLM task validation<br/>[validate_task.py]"]
  node_rlm_executor["RLM skill executor<br/>[executor.py]"]
  node_rlm_runtime["Persistent RLM runtime<br/>[runtime.py]"]
  node_provider_base["Provider interface<br/>[base.py]"]
  node_provider_health["Provider checks<br/>[provider_check.py]"]
  node_provider_http["HTTP helpers<br/>[http_utils.py]"]
  node_bundle_store[("Bundle and run files")]
end

node_user(("Engineer / agent"))
node_llm_service{{"LLM endpoint"}}

node_user -->|"requests next action"| node_agentctl
node_agentctl -->|"reads and updates"| node_state
node_agentctl -->|"consults backlog"| node_plan
node_agentctl -->|"uses sequencing"| node_workflow_engine
node_workflow_engine -.->|"loads loops"| node_workflow_defs
node_agentctl -->|"retrieves prompt"| node_prompt_catalog
node_prompt_catalog -->|"resolves catalog"| node_prompt_paths
node_prompt_paths -->|"finds installed resource"| node_resource_resolver
node_prompt_catalog -.->|"reads prompts"| node_loop_prompts
node_user -->|"follows selected loop"| node_loop_prompts
node_user -->|"records evidence"| node_state
node_bootstrap -->|"installs skills"| node_skills
node_skillctl -->|"resolves resources"| node_resource_resolver
node_user -->|"bootstraps repository"| node_bootstrap
node_agentctl -->|"generates plan"| node_plan_pipeline
node_plan_pipeline -.->|"writes checkpoints"| node_plan
node_agentctl -->|"instantiates template"| node_checkpoint_templates
node_checkpoint_templates -.->|"adds checkpoint"| node_plan
node_agentctl -->|"captures context"| node_history_context
node_context_builder -->|"validates task"| node_task_schema
node_context_builder -.->|"writes bundle"| node_bundle_store
node_rlm_executor -->|"builds context"| node_context_builder
node_rlm_executor -->|"runs task"| node_rlm_runtime
node_rlm_runtime -.->|"reads and persists"| node_bundle_store
node_provider_health -->|"uses interface"| node_provider_base
node_provider_health -.->|"sends checks"| node_provider_http
node_provider_http -->|"sends HTTP request"| node_llm_service

click node_agentctl "https://github.com/brifl/coding-agent-orchestration/blob/main/tools/agentctl.py"
click node_workflow_engine "https://github.com/brifl/coding-agent-orchestration/blob/main/tools/workflow_engine.py"
click node_workflow_defs "https://github.com/brifl/coding-agent-orchestration/tree/main/workflows"
click node_loop_prompts "https://github.com/brifl/coding-agent-orchestration/blob/main/prompts/template_prompts.md"
click node_prompt_catalog "https://github.com/brifl/coding-agent-orchestration/blob/main/tools/prompt_catalog.py"
click node_prompt_paths "https://github.com/brifl/coding-agent-orchestration/blob/main/tools/prompt_catalog_paths.py"
click node_resource_resolver "https://github.com/brifl/coding-agent-orchestration/blob/main/tools/resource_resolver.py"
click node_skills "https://github.com/brifl/coding-agent-orchestration/tree/main/.codex/skills"
click node_bootstrap "https://github.com/brifl/coding-agent-orchestration/blob/main/tools/bootstrap.py"
click node_skillctl "https://github.com/brifl/coding-agent-orchestration/blob/main/tools/skillctl.py"
click node_state "https://github.com/brifl/coding-agent-orchestration/blob/main/.vibe/STATE.md"
click node_plan "https://github.com/brifl/coding-agent-orchestration/blob/main/.vibe/PLAN.md"
click node_history_context "https://github.com/brifl/coding-agent-orchestration/tree/main/.vibe"
click node_plan_pipeline "https://github.com/brifl/coding-agent-orchestration/blob/main/tools/plan_pipeline.py"
click node_checkpoint_templates "https://github.com/brifl/coding-agent-orchestration/blob/main/tools/checkpoint_templates.py"
click node_context_builder "https://github.com/brifl/coding-agent-orchestration/blob/main/tools/rlm/context_bundle.py"
click node_task_schema "https://github.com/brifl/coding-agent-orchestration/blob/main/tools/rlm/validate_task.py"
click node_rlm_executor "https://github.com/brifl/coding-agent-orchestration/blob/main/skills/rlm-tools/executor.py"
click node_rlm_runtime "https://github.com/brifl/coding-agent-orchestration/blob/main/tools/rlm/runtime.py"
click node_provider_base "https://github.com/brifl/coding-agent-orchestration/blob/main/tools/rlm/providers/base.py"
click node_provider_health "https://github.com/brifl/coding-agent-orchestration/blob/main/tools/rlm/provider_check.py"
click node_provider_http "https://github.com/brifl/coding-agent-orchestration/blob/main/tools/rlm/providers/http_utils.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_agentctl,node_workflow_engine,node_workflow_defs toneBlue
class node_state,node_plan,node_history_context,node_plan_pipeline,node_checkpoint_templates toneAmber
class node_loop_prompts,node_prompt_catalog,node_prompt_paths,node_resource_resolver,node_skills,node_bootstrap,node_skillctl toneMint
class node_context_builder,node_task_schema,node_rlm_executor,node_rlm_runtime,node_provider_base,node_provider_health,node_provider_http,node_bundle_store toneRose
class node_user,node_llm_service toneIndigo
```

## Components

### Workflow dispatch

- [Workflow CLI](https://github.com/brifl/coding-agent-orchestration/blob/main/tools/agentctl.py): `tools/agentctl.py`
- [Workflow sequencing](https://github.com/brifl/coding-agent-orchestration/blob/main/tools/workflow_engine.py): `tools/workflow_engine.py`
- [Configured loops](https://github.com/brifl/coding-agent-orchestration/tree/main/workflows): `workflows`

### Planning and state

- [Workflow state](https://github.com/brifl/coding-agent-orchestration/blob/main/.vibe/STATE.md): `.vibe/STATE.md`
- [Checkpoint plan](https://github.com/brifl/coding-agent-orchestration/blob/main/.vibe/PLAN.md): `.vibe/PLAN.md`
- [History and context](https://github.com/brifl/coding-agent-orchestration/tree/main/.vibe): `.vibe`
- [Plan generation](https://github.com/brifl/coding-agent-orchestration/blob/main/tools/plan_pipeline.py): `tools/plan_pipeline.py`
- [Checkpoint templates](https://github.com/brifl/coding-agent-orchestration/blob/main/tools/checkpoint_templates.py): `tools/checkpoint_templates.py`

### Prompts and skills

- [Loop prompt catalog](https://github.com/brifl/coding-agent-orchestration/blob/main/prompts/template_prompts.md): `prompts/template_prompts.md`
- [Prompt lookup](https://github.com/brifl/coding-agent-orchestration/blob/main/tools/prompt_catalog.py): `tools/prompt_catalog.py`
- [Prompt path resolution](https://github.com/brifl/coding-agent-orchestration/blob/main/tools/prompt_catalog_paths.py): `tools/prompt_catalog_paths.py`
- [Resource resolution](https://github.com/brifl/coding-agent-orchestration/blob/main/tools/resource_resolver.py): `tools/resource_resolver.py`
- [Agent skills](https://github.com/brifl/coding-agent-orchestration/tree/main/.codex/skills): `.codex/skills`
- [Repository bootstrap](https://github.com/brifl/coding-agent-orchestration/blob/main/tools/bootstrap.py): `tools/bootstrap.py`
- [Skill management](https://github.com/brifl/coding-agent-orchestration/blob/main/tools/skillctl.py): `tools/skillctl.py`

### RLM task runtime

- [Context bundler](https://github.com/brifl/coding-agent-orchestration/blob/main/tools/rlm/context_bundle.py): `tools/rlm/context_bundle.py`
- [RLM task validation](https://github.com/brifl/coding-agent-orchestration/blob/main/tools/rlm/validate_task.py): `tools/rlm/validate_task.py`
- [RLM skill executor](https://github.com/brifl/coding-agent-orchestration/blob/main/skills/rlm-tools/executor.py): `skills/rlm-tools/executor.py`
- [Persistent RLM runtime](https://github.com/brifl/coding-agent-orchestration/blob/main/tools/rlm/runtime.py): `tools/rlm/runtime.py`
- [Provider interface](https://github.com/brifl/coding-agent-orchestration/blob/main/tools/rlm/providers/base.py): `tools/rlm/providers/base.py`
- [Provider checks](https://github.com/brifl/coding-agent-orchestration/blob/main/tools/rlm/provider_check.py): `tools/rlm/provider_check.py`
- [HTTP helpers](https://github.com/brifl/coding-agent-orchestration/blob/main/tools/rlm/providers/http_utils.py): `tools/rlm/providers/http_utils.py`
- **Bundle and run files**

### Other components

- **Engineer / agent**
- **LLM endpoint**

## Connections

- Engineer / agent → Workflow CLI: requests next action (evidence: `README.md`)
- Workflow CLI → Workflow state: reads and updates (evidence: `README.md`)
- Workflow CLI → Checkpoint plan: consults backlog (evidence: `README.md`)
- Workflow CLI → Workflow sequencing: uses sequencing (evidence: `tools/agentctl.py`)
- Workflow sequencing → Configured loops: loads loops
- Workflow CLI → Prompt lookup: retrieves prompt (evidence: `tools/agentctl.py`)
- Prompt lookup → Prompt path resolution: resolves catalog (evidence: `tools/prompt_catalog_paths.py`)
- Prompt path resolution → Resource resolution: finds installed resource (evidence: `tools/prompt_catalog_paths.py`)
- Prompt lookup → Loop prompt catalog: reads prompts
- Engineer / agent → Loop prompt catalog: follows selected loop (evidence: `README.md`)
- Engineer / agent → Workflow state: records evidence (evidence: `README.md`)
- Repository bootstrap → Agent skills: installs skills (evidence: `README.md`)
- Skill management → Resource resolution: resolves resources (evidence: `tools/skillctl.py`)
- Engineer / agent → Repository bootstrap: bootstraps repository (evidence: `README.md`)
- Workflow CLI → Plan generation: generates plan (evidence: `tools/agentctl.py`)
- Plan generation → Checkpoint plan: writes checkpoints
- Workflow CLI → Checkpoint templates: instantiates template (evidence: `tools/agentctl.py`)
- Checkpoint templates → Checkpoint plan: adds checkpoint
- Workflow CLI → History and context: captures context (evidence: `README.md`)
- Context bundler → RLM task validation: validates task (evidence: `tools/rlm/context_bundle.py`)
- Context bundler → Bundle and run files: writes bundle
- RLM skill executor → Context bundler: builds context (evidence: `skills/rlm-tools/executor.py`)
- RLM skill executor → Persistent RLM runtime: runs task (evidence: `skills/rlm-tools/executor.py`)
- Persistent RLM runtime → Bundle and run files: reads and persists
- Provider checks → Provider interface: uses interface (evidence: `tools/rlm/provider_check.py`)
- Provider checks → HTTP helpers: sends checks
- HTTP helpers → LLM endpoint: sends HTTP request (evidence: `tools/rlm/providers/http_utils.py`)
