Brigade Fi Kimi Completion Controller — Development agent for Claude Code
Diagnose-only sidecar completion controller.
How to install Brigade Fi Kimi Completion Controller
Installs to ~/.claude/agents/b-a-m-n-claudebrigade-brigade-fi-kimi-completion-controller.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/B-A-M-N/ClaudeBrigade/HEAD/agents/brigade-fi-kimi-completion-controller.md -o ~/.claude/agents/b-a-m-n-claudebrigade-brigade-fi-kimi-completion-controller.md Restart Claude Code, or start a new session, for it to be picked up.
What Brigade Fi Kimi Completion Controller does
name: brigade-sidecar-completion-controller description: Diagnose-only sidecar completion controller. tools: Read, Grep, Glob, Bash disallowedTools: Edit, Write, NotebookEdit, Agent, Workflow maxTurns: 100 effort: high permissionMode: plan background: true
Audit the original task contract, requirements, acceptance criteria, current workspace, tests, and evidence. Return exactly one JSON result with completion=COMPLETED or NEEDS_REVIEW, coverage_map, baseline_commands, and corrections. N
Alternatives in Development
- Systematic Debugger — Use this agent when you need to diagnose and fix bugs, errors, or unexpected behavior in code 39.2k ★
- Cs Guardian — Customer success partner for account health, churn risk, renewals, escalations, and QBRs 1.3k ★
- Controller Agent — Creates thin, RESTful Rails controllers with strong parameters, proper error handling, and request specs 652 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Brigade Fi Minimax Completion Reviewer
Optional diagnose-only sidecar completion reviewer.
Brigade Fi Kimi Implementer
Mutation-capable coding worker selected by the active sidecar route.
Provider Debugger
Diagnose live-provider compatibility failures for Kimi, GLM, and other OpenAI-compatible endpoints
Kimi Ask
Use this agent when the user wants Kimi to answer a free-form question about the repository in prose — explain
Kimi Swarm Write
Use this agent ONLY when the user has explicitly asked Kimi to make EDITS across MANY disjoint targets IN PARA
Context Scout
Grounds a kimi-atlas run by scanning the target repository for the facts, conventions, and constraints relevan
Related Skills
Odyssey Testing
Testing workflow for Odyssey — when to use AppXray vs sidecar API vs XCTest, how to run feedback checks, and h
Provider Diagnose
Diagnose Kimi, GLM, and other live-provider compatibility failures
Mise Cook
Run the kitchen-brigade orchestration workflow — a lead session fans a multi-part goal to isolated worktree ag