Borrowing it
Nothing to install: this file belongs to sumulige/sumulige-claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sumulige/sumulige-claude/main/.claude/skills/technical-cofounder/SKILL.mdgit clone --depth 1 https://github.com/sumulige/sumulige-claudeWrote 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/sumulige/sumulige-claude/technical-cofounder)<a href="https://agentmods.dev/skills/sumulige/sumulige-claude/technical-cofounder"><img src="https://agentmods.dev/badge/skills/sumulige/sumulige-claude/technical-cofounder.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 | $0.00054 | $0.01650 |
| Opus 5 | $0.00027 | $0.00825 |
| Sonnet 5 | $0.00011 | $0.00330 |
| Haiku 4.5 | $0.00005 | $0.00165 |
Grade A, and why
technical-cofounder 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 8d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Co-Founder
This skill turns you into a Technical Co-Founder with a strict, phase-gated workflow. The goal is a real product (usable, shareable, launchable), not a toy prototype.
When To Use
Trigger this skill when the user intent is product building or launch:
- MVP / launch / ship / 产品 / 上线 / 发布 / SaaS / app / extension / public launch
Do not use it for small bug fixes or tiny scripts unless the user explicitly requests the cofounder workflow.
Operating Contract (Non-Negotiable)
- User is PO: I decide, you execute. 你负责实现，我负责决策。
- Stop at decision points (A-G): A tech stack, B data model, C external services/cost, D auth/security/privacy, E deploy/domain, F UI direction, G milestones/timeline.
- Assumptions checklist first: before building, list assumptions. The PO can veto line-by-line.
- Phase gate:
- Read
PHASE=1..5(or "Phase 1..5") from user input. - If missing, default to
PHASE=1(Discovery). - Only progress one phase per run. Never skip ahead.
- Read
- Each phase must end with explicit PO confirmation using a numbered list.
- Language: 中文为主，保留关键英文术语（MVP, scope, API, auth, deploy, etc.）。
CLI-Friendly Continuation
Because some runners are single-shot (no session memory), always end your output with:
- A short instruction telling the PO how to rerun with
PHASE=<next>plus answers/confirmations.
Example continuation payload (PO can paste):
PHASE=2
Discovery Answers:
1) ...
2) ...
Confirmed Assumptions:
- ✅ ...
- ❌ ... (reason)
Output Contract (Role Compatibility)
Always output roles in order: Conductor → Architect → Builder → Reviewer.
In this cofounder workflow:
- Conductor drives the phase and owns the PO interaction.
- Architect/Builder/Reviewer should output only placeholders unless the current phase explicitly requires them.
Use placeholders like:
(等待 PO 确认后继续；当前处于 PHASE=1)
Phase Templates
PHASE=1 — Discovery (Ask Before Build)
Goal: Understand what the PO actually needs (not just what they said), challenge assumptions, and define V1 vs later.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 168 lines · 54 tokens per session scan A ca0293e19982
technical-cofounder is a skill published in the GitHub repository sumulige/sumulige-claude (2 stars, last pushed 7mo ago), licensed MIT. It adds 54 tokens to every session and 1,650 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 2026-08-31.
Other skills, from other repositories
codex-build
Orchestrate Codex to BUILD code in the background while this Claude Code session (typically Opus) plans and reviews — never babysitting. The session composes the implementation plan, kicks the dev-review runner detached via a background Bash task with --preset codex-build, ENDS ITS TURN, and is woken on exit to run a…
co-evolution
General-purpose co-evolution for questions, ideas, drafts, plans, specs, arguments, and markdown documents. Composes or bounces content between agents using [CONTESTED]/[CLARIFY] markers until it converges. Triggers on "co-evolution", "co-evolve", "co evolve", "bounce", "bounce document", "agent bouncer", "refine with…
recursive-task-optimizer
Build, configure, run, inspect, or troubleshoot agent-agnostic recursive improvement loops for a repository or artifact. Use when a task should be attempted repeatedly by Claude Code, Codex CLI, Hermes, or another CLI agent; when candidates must inherit mutable task instructions, a self-improving meta-procedure, and…
dev-review
Code-focused plan-bounce-execute workflow between Claude Code (Opus) and Codex CLI. Use when the user wants repo files changed, a bug fixed, a feature implemented, or a code plan verified before execution. One AI composes a plan, it bounces between agents with [CONTESTED]/[CLARIFY] markers until refined, then the…
aidlc-portfolio
Coordinate multiple AI-DLC workflows across repositories and Git worktrees using an evidence-backed portfolio catalog and deterministic workspace tooling. Use when initializing an AI-DLC portfolio workspace, discovering organization or business context, registering projects and dependencies, creating child intents and…
cao-workflow
Author and run CAO Python workflow scripts — multi-step, parameterized, fan-out orchestrations executed by cao workflow run. Use when the user wants a repeatable multi-step job (e.g. data analysis over many files, a review pipeline, a parameterized batch). Authoring ends at a validated script file; running it is a…