Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentnpx agentmods add skills/humanerd-drew/opencode-drewgent/taste-reviewWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/taste-review)<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/taste-review"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/taste-review.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00034 | $0.01306 |
| Opus 5 | $0.00017 | $0.00653 |
| Sonnet 5 | $0.00007 | $0.00261 |
| Haiku 4.5 | $0.00003 | $0.00131 |
Grade A, and why
taste-review 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 4d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taste Review Skill
Trend Harvester가 수집+분석한 keep 리스트에서 1개를 골라 심층 분석하고, 그 툴에서 배울 수 있는 taste 결정을 추출하여 vault에 기록한다.
Execution Model — Kanban Delegation
Taste Review는 더 이상 직접 cron job에서 실행되지 않는다. 다음 플로우로 동작:
cron: taste-review-trigger (fast LLM, 화/금 10:00)
→ kanban_create(title="taste-review: YYYY-MM-DD", assignee="default")
→ kanban worker (본 분석 실행)
- Trigger cron (
taste-review-trigger,66d907f7bce4): 빠른 모델(opencode-go/deepseek-v4-flash)로 keep 리스트 확인 → 새 항목 있으면 kanban task 생성 → 종료 (수초) - Kanban worker: 실제 분석 실행 (web_search + file write + LLM reasoning) — cron idle timeout(600s)과 무관
Phase 1 — Pick & Research
항목 선택
analyzed/keep/디렉토리에서 아직 evaluated/에 없는 항목 1개 선택- 이미
applied/또는evaluated/에 있는 항목은 스킵
웹 리서치
web_search또는 직접 URL로 해당 툴의 README와 문서 탐색- 다음에 집중:
- 아키텍처 결정: 왜 이렇게 만들었을까? (언어, 패턴, 구조)
- 사용자 경험 결정: 어떤 trade-off를 했을까?
- 독특한 접근법: 다른 툴과 다른 점은?
Phase 2 — Analyze & Write
분석 프레임워크
다섯 가지 질문에 답변:
- One-Liner: 이 툴을 한 문장으로 설명하면?
- 훔칠 Taste 결정 (1-3개): 이 툴의 제작자가 내린 결정 중, {{AGENT_NAME}}에 적용할 가치가 있는 것은?
- 아키텍처 인사이트: 구조적으로 배울 점은?
- {{AGENT_NAME}} 적용 가능성: 이 아이디어를 {{AGENT_NAME}}에 적용할 수 있는가? 어떻게?
- Leverage Score (1-5): 이 인사이트가 {{AGENT_NAME}}에 미칠 영향은?
Vault 저장
Path: P4-cortex/taste-reviews/YYYY-MM-DD-tool-slug.md
Frontmatter:
---
title: "Taste Review: Tool Name"
type: taste-review
tags: [taste-review, YYYY-MM]
created: YYYY-MM-DD
links:
- "[[trend-harvester]]"
- "[[@memory/growth/trend-harvester/analyzed/keep/xxxx.json]]"
- "[[@identity/brain/rules]]"
session: "YYYY-MM-DD taste-review"
trigger: "scheduled taste review"
---
Body:
# Taste Review: Tool Name
분석일: YYYY-MM-DD | 링크: [GitHub](url)
## One-Liner
...
## 훔칠 Taste 결정
### 1. [결정 제목]
- **무슨 결정인가:** ...
- **왜 taste가 필요한 결정인가:** ...
- **{{AGENT_NAME}}에 적용:** ...
### 2. ...
## 아키텍처 인사이트
...
## {{AGENT_NAME}} 적용 가능성
[Yes/No + 구체적 방법]
## Leverage Score: N/5
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.
- 4d ago First seen · 149 lines · 0 tokens per session scan A 7b61c861fb3a
taste-review is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 1,306 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…