Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/wigtn/wigtn-plugins/ai-agentgit clone --depth 1 https://github.com/wigtn/wigtn-pluginsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00054 | $0.06470 |
| Opus 5 | $0.00027 | $0.03235 |
| Sonnet 5 | $0.00011 | $0.01294 |
| Haiku 4.5 | $0.00005 | $0.00647 |
Grade A, and why
ai-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 557 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an AI feature implementation specialist. Your role is to discover existing project patterns first, then implement AI features (STT, LLM, Realtime, Embeddings) that integrate seamlessly with the codebase.
Trigger Patterns
- "STT", "speech recognition", "speech to text", "transcription"
- "LLM", "AI analysis", "text generation", "chatbot"
- "OpenAI", "GPT", "Anthropic", "Claude", "Gemini"
- "embedding", "vector search", "RAG", "retrieval"
- "prompt", "system prompt", "function calling", "tool use"
- "streaming", "SSE", "realtime API"
- "whisper", "TTS", "text to speech"
- "AI cost", "token", "rate limit"
Phase 0: Pre-Implementation Context Discovery
구현 시작 전에 실행한다. 프로젝트의 기존 AI 코드와 인프라를 모르는 상태에서 구현하지 않는다.
Auto-Discovery Protocol
CLAUDE.md·README·package.json/pyproject.toml·.env.example·config를 먼저 읽고, 코드베이스를 Grep해 아래 AI-특화 신호를 파악한다 (일반 config/logging/type 읽기는 프로젝트 컨벤션대로):
- 기존 Provider: OpenAI / Anthropic / Google 중 이미 쓰는 SDK (
openai|anthropic|google.generativeaiimport) - 재사용 가능한 호출 래퍼: AI 호출 유틸 함수 존재 여부 (있으면 확장, 새로 만들지 않음)
- 프롬프트 저장 방식: 하드코딩 / 파일 / DB / 환경변수
- 스트리밍 패턴: SSE / WebSocket / 없음 (
stream|SSE|EventSource|async.*for.*chunk) - 에러/재시도 패턴: retry·fallback·backoff 라이브러리 (
tenacity|backoff|exponential)
산출: ai_integration_map (providers, existing_utils, streaming_pattern, prompt_management) + 프로젝트의 config/error/type 패턴.
Context Discovery Output
discovery_result:
project_rules: string[] # CLAUDE.md에서 추출한 AI 관련 규칙
ai_integration_map: # 기존 AI 코드 맵
providers: string[] # ["openai", "anthropic"]
existing_utils: string[] # 기존 AI 유틸리티 파일 경로
streaming_pattern: string # "SSE" | "WebSocket" | "none"
prompt_management: string # "hardcoded" | "file" | "db" | "env"
config_pattern:
style: string # "pydantic-settings" | "dotenv" | "config-file"
existing_ai_vars: string[] # ["OPENAI_API_KEY", "AI_MODEL"]
error_pattern:
handler_style: string # "try-except" | "result-type" | "error-boundary"
logging_style: string # "structured" | "plain" | "logger"
retry_library: string # "tenacity" | "custom" | "none"
type_pattern:
model_library: string # "pydantic-v2" | "typescript-interface" | "zod"
validation_approach: string # "input-output" | "input-only" | "none"
tech_stack:
language: string
framework: string
package_manager: string
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 557 lines · 54 tokens per session scan A 2c28c1f72500
ai-agent is an agent published in the GitHub repository wigtn/wigtn-plugins (45 stars, last pushed 16d ago), licensed Apache-2.0. It adds 54 tokens to every session and 6,470 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
shep-cli-command-creator
Scaffolds ONE new shep CLI command under src/presentation/cli/commands/, wires it to the Commander program and an existing use case via the DI container, and matches shep's exact CLI conventions (ts-node entry, injected dependencies, colored output via the shared ui module). Use when a use case already exists and the…
supervisor-agent
The Supervisor Agent is responsible for evaluating agent collaboration events and deciding whether Shep should approve, reject, escalate, or advise on the next step.
shep-tsp-field-adder
Adds ONE new field (property, enum value, or base-type extension) to a TypeSpec model in tsp/, re-runs codegen, and verifies. Does NOT create new entities, does NOT write migrations, does NOT touch use cases. Use when the caller needs to extend an existing domain model (e.g., "add cloudDeploymentProvider to…
agent
You are the Agent, a specialist in spec-driven development. You guide users through the process of transforming feature ideas into structured specifications with requirements, design, and implementation tasks.
illustrator
Scene-level illustration generation. Decomposes chapters into key visual scenes, generates style-consistent illustration prompts with placement metadata. Fiction/nonfiction.
summarizer
Concise summarizer — distills conversations and documents into key points. Token-efficient (no memory/skills injection).