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 skills add humanerd-drew/opencode-drewgent --skill manyfastgit clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentWrote 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/manyfast)<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/manyfast"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/manyfast.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 | $0.00000 | $0.02267 |
| Opus 5 | $0.00000 | $0.01133 |
| Sonnet 5 | $0.00000 | $0.00453 |
| Haiku 4.5 | $0.00000 | $0.00227 |
Grade A, and why
manyfast 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 3d 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manyfast 아키텍처 분석 — 에이전트 시스템 내재화
Manyfast 핵심 분석
Manyfast는 제품 기획 협업 SaaS. 아래 구조를 가진다:
1. PRD 구성 (프로덕트 요구사항)
PRD
├── 개요 — 제품 목표, 비즈니스 배경 (한 줄 정의)
├── 핵심 가치 — 문제 정의 + 해결 방식 + 차별점
├── 타겟/시나리오 — 사용자 그룹 + 사용 스토리
├── 성공 지표 — KPI + 리스크 + 오픈 이슈
└── 속성 설정 — 카테고리, 사용자 역할, 서비스 환경
{{AGENT_NAME}} 적용 시: memories/concepts/ 또는 P4-cortex/knowledge/에 PRD 스키마 정의. Kanban task의 metadata로 PRD 필드 표현 가능.
2. Features 3-tier Hierarchy (핵심)
Requirement (요구사항)
├── Feature (기능)
│ ├── Specification (상세 기능)
│ └── Specification
├── Feature
│ └── Specification
└── Feature
└── Specification
각 단계 속성:
| 단계 | 설명 | 속성 |
|---|---|---|
| Requirement | 프로젝트 최상위 목표 | 설명 + Acceptance Criteria(체크리스트) |
| Feature | 논리적 기능 단위 | 설명 + 사용자 역할(PRD 역할 매핑) |
| Specification | 세부 동작/비즈니스 정책 | 설명 (개발/디자인 기준) |
중요도: 낮음/중간/높음 상태: 시작 전/진행중/완료/중단
{{AGENT_NAME}} 적용 시 — kanban task tree로 동일 구조 구현:
parent task (Requirement)
child task (Feature)
grandchild task (Specification)
metadata["requirement"]→ parent task titlemetadata["feature"]→ child task titlemetadata["specification"]→ grandchild task titlemetadata["acceptance_criteria"]→ QA gate criteria로 연동
3. AI 에이전트 Dual-Mode
Manyfast AI는 두 가지 모드:
설계 모드 (Design Mode)
— AI와 함께 계획을 구체화, 합의점 먼저 찾음
— 빠른 실행 대신 탐색/토의에 집중
실행 모드 (Execution Mode)
— 지시 즉시 실행, 기획 도구로 데이터 직접 수정
— 빠른 결과물 생성
{{AGENT_NAME}} 적용 시:
- kanban에
design_mode플래그 추가 - design mode: task를 분핧만 하고 실행은 보류
- execution mode: task 분해 후 바로 dispatcher로 실행 전달
kanban_create(mode="design"|"execution")파라미터로 구분
4. AI 수정 검토 workflow (핵심 패턴)
AI가 수정 제안
↓
사용자가 검토 (파란 화살표로 표시)
↓
개별 승인/거절 또는 일괄 승인/거절
↓
최종 반영
{{AGENT_NAME}} 적용 시 — QA gate와 유사:
- Agent가 task 결과를 제안
- QA gate에서
all_criteria_met확인 - 사용자가 승인/거절 (Discord/Telegram reaction 또는 명시적 승인)
5. MCP Integration (외부 AI 연동)
Manyfast MCP는:
매니패스트 기획 데이터 → AI coding agent (Cursor, Claude Code 등)
→ 코딩 결과 → 매니패스트에 반영
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.
- 3d ago First seen · 281 lines · 0 tokens per session scan A de7082cbece9
manyfast is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,267 tokens. 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.