Agent
Compresses top retrieval chunks into citation-rich summary packets that preserve intent while cutting token usage.
44 4mo ago A 22 tokens
original MIT
Agent
Runs hybrid retrieval with strict FTS-first policy, BM25 lexical ranking, vector merge, and top 3-5 reranking for token-efficient context selection.
44 4mo ago A 38 tokens
original MIT
Agent
Preprocesses large corpora by removing low-signal noise and creating overlap-aware chunks for retrieval indexing.
44 4mo ago A 25 tokens
original MIT
Agent
Delegate to this agent for deep codebase exploration — semantic search, exact symbol lookup and reference tracing over a Beacon index. Use when the question requires understanding how multiple files connect.
43 11d ago A 39 tokens
original MIT
dba
05cdeust/ai-architect-mcp-codebase
Agent Claude Code
Database specialist adapting to any engine (PostgreSQL, SQLite, MongoDB, etc.) — schema design, query optimization, migrations, and index tuning.
4 2d ago A 33 tokens
original MIT
orchestrator
06cdeust/ai-architect-mcp-codebase
Agent Claude Code
Orchestrates parallel agent execution across worktrees — spawns, coordinates, and merges work from multiple specialized agents.
4 2d ago A 26 tokens
original MIT
cdeust/ai-architect-mcp-codebase
Agent Claude Code
Research scientist improving benchmark scores through neuroscience papers, IR literature, and technical analysis of failure modes.
4 2d ago A 23 tokens
original MIT
domain
08Agent
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
4 19d ago A 0 tokens
copy · 77% MIT
Agent
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.
4 19d ago A 0 tokens
copy · 91% MIT
Agent
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
4 19d ago A 0 tokens
copy · 81% MIT
Agent
Devil's advocate for architecture decisions. Use when proposing a new system design, choosing a technology, or making a significant structural change. Challenges assumptions and proposes alternatives.
3 3d ago A 38 tokens
original MIT
Agent
Use after the red team has reported findings. Proposes concrete fixes, hardening measures, and defense-in-depth strategies. Reviews red team findings for false positives and prioritizes remediation by risk.
3 3d ago A 42 tokens
original MIT
Agent
Use when reviewing code for security vulnerabilities. Thinks like an attacker. Searches for current CVEs and OWASP Top 10 issues relevant to the tech stack. Invoke for security audits, pre-deployment reviews, or when touching auth, payments, or user data.
3 3d ago A 57 tokens
original MIT
Agent Claude Code
Use proactively when the user wants to plan a token budget, pack a system-prompt + retrieval + memory + team-context bundle into a budget, count tokens, or optimize for prompt caching. May read from retrieval and memory tools to assemble content. Does NOT index, store memories, or score teams.
2 10d ago A 66 tokens
original MIT
Agent Claude Code
Use proactively when the user wants to store or retrieve facts, decisions, patterns, or preferences across Koshi sessions, capture decisions made in a turn, sync to/from a Markdown vault, or prune the memory store. Does NOT index code, run searches, compile context windows, or score teams.
2 10d ago A 65 tokens
original MIT
Agent Claude Code
Use when the request spans multiple Koshi pillars (retrieval + memory, index-then-pack, score-then-tune), or the right specialist persona is not obvious. Generalist with access to all 24 Koshi MCP tools. Defers to single-pillar specialists (koshi-librarian, koshi-memory-keeper, koshi-context-packer…
2 10d ago A 95 tokens
original MIT