harness agents

mindfold-ai/Trellis

Agent Claude Code

Code and tech search expert. Finds files, patterns, and tech solutions, and PERSISTS every finding to the current task's research/ directory. No code modifications outside that directory.

mindfold-ai/Trellis

Agent

Architecture sparring partner for Trellis. Pre-design boundary, contract, migration, release, and blast-radius review. Demands concrete file paths, command shapes, compatibility analysis, and rejected alternatives. NOT an implementer.

mindfold-ai/Trellis

Agent

Code and tech search expert. Finds patterns, specs, and tech solutions. Populates task JSONL context files.

notnotype/neuro-book

Agent Claude Code

Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.

notnotype/neuro-book

Agent

Profile-scoped agent context directory.

itsinseong/value-for-fable

Agent

A delegation-only subagent based on Sonnet Fable 5 for independent implementation, analysis, research, or writing tasks. It returns readable results to the main session instead of applying a working mode directly.

Rigos0/superturtle

Agent Claude Code

Code architecture reviewer. Catches shortcuts, duplication, bloated files, and missed reuse opportunities. Focuses on structure, not style. Read-only.

Rigos0/superturtle

Agent Claude Code

Dedicated code reviewer. Reads diffs/commits, reviews changed files, and returns a terse report of problems found. Prompt MUST specify scope: unstaged changes, a commit range, or since-branch-point. Read-only — no file edits.

Rigos0/superturtle

Agent Claude Code

Git archaeology agent. Digs through commit history to answer 'when/why/who' questions about code changes. Give it a question and it will search logs, blames, and diffs to find the answer.

Lyt060814/nanocode

Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

Lyt060814/nanocode

Agent

Compare two outputs WITHOUT knowing which skill produced them.

Lyt060814/nanocode

Agent

Evaluate expectations against an execution transcript and outputs.

iLearn-Lab/EvoHarness

Agent Claude Code

Review workspace docs against the live harness surface and identify the most valuable doc repair.

iLearn-Lab/EvoHarness

Agent Claude Code

Review plugin catalogs and recommend the next highest-leverage bundle to add or clean up.

iLearn-Lab/EvoHarness

Agent Claude Code

Design local MCP services that surface reusable tools, resources, and prompts without fragile boot paths.

crystian/skill-map

Agent Claude Code

Commit pipeline for skill-map. Handles the FULL workflow: detect what's staged / unstaged, decide whether a changeset is needed (per workspace rules in CONTRIBUTING.md), regenerate spec integrity hashes, ROADMAP cross-references, and the conventional commit itself. The workspace CHANGELOG.md files are generated by…

crystian/skill-map

Agent Claude Code

Owns the angle of an article. Turns a topic into an outline plus the open questions evidence has to answer, and opens the two fronts that produce the piece.

crystian/skill-map

Agent Claude Code

Answers the outline's open questions with citable sources and hands the evidence downstream for verification.

babyworm/rtl-agent-team

Agent

Phase 1 research pipeline orchestrator. Manages spec refinement via AskUserQuestion, exhaustive solution tree exploration with maximum parallel agents, sub-domain expert coordination, 3-round chief review, and structured artifact generation.

babyworm/rtl-agent-team

Agent

Phase 1 research team coordination teammate. Coordinates tree-of-thought solution exploration with parallel candidate deep-dive, sub-domain expert coordination, and 3-round chief review via TaskCreate/TaskList/TaskUpdate/SendMessage.

babyworm/rtl-agent-team

Agent

Phase 3 μArch design pipeline orchestrator. Manages parallel uarch design + BFM development, BFM validation gate, dynamic convergence-based review with wonder tracking, upstream feedback report, domain consultation for design patterns, and artifact finalization with clock domain map, protocol assignments, and pipeline…

seungmanchoi/react-native-fsd-agent-template

Agent Claude Code

An integration specialist for connecting apps to APIs and managing shared data, using Axios, TanStack Query, and Zustand. It also covers analytics and crash reporting, secure token storage, store-review requests, and ad-related infrastructure.

seungmanchoi/react-native-fsd-agent-template

Agent Claude Code

An app-planning agent that writes a PRD, or Product Requirements Document—a written description of what a product should do. It designs user stories, features, information structure, and screen flows.

seungmanchoi/react-native-fsd-agent-template

Agent Claude Code

A code-review and quality-checking agent for projects that use Feature-Sliced Design. It checks architecture rules, type safety, and security, and can run type checks and linting.