Agentic Engineering
Run engineering work the agent way: eval-first execution, 15-minute decompositions, and cost-aware model routing.
- What
- Run engineering work the agent way: eval-first execution, 15-minute decompositions, and cost-aware model routing.
- Cost
- Free
- Needs
- Use "Agentic Engineering" with your Muse.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor: an operating manual for engineering workflows where AI agents do most of the implementation and humans enforce quality and risk controls. Four principles: define completion criteria before execution, decompose work into independently verifiable 15-minute units with one dominant risk each, route model tiers by task complexity (light models for classification and boilerplate transforms, top tier for architecture and root-cause analysis), and measure with capability plus regression evals. Includes a session strategy (continue the session for closely-coupled units, start fresh after major phase transitions, compact after milestones rather than mid-debugging) and a review checklist focused on invariants, edge cases, error boundaries, security and auth assumptions, and hidden coupling, instead of style-only disagreements that linters already enforce. By @affaan-m, listed here with credit to its creator. From the affaan-m/ECC repository (MIT). Honest caveats: pure guidance, nothing to install; the model tier names are Claude-oriented but the routing logic ports to any model family. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Copy the install package below, then paste it into MuseCommunity-built. Skill Harbor doesn't audit code — review the source before installing.
Use "Agentic Engineering" with your Muse. Prerequisites: the Muse app (mobile or web). No installation, no API key, no extra account. Pure guidance skill. 1. Open the skill: https://github.com/affaan-m/ECC/blob/main/skills/agentic-engineering/SKILL.md and copy the full SKILL.md text. 2. Paste it into a chat with Muse and add: "Run this engineering task the agentic way: [describe the task]. Start by defining completion criteria, then decompose into 15-minute verifiable units." 3. Ask Muse to route each unit to the right effort level, and to run the review checklist (invariants, edge cases, error boundaries, security assumptions) on every completed unit. Tip: the 15-minute unit rule is the whole game. If a unit is not independently verifiable, split it before starting. Safety: a skill is plain-text instructions; it runs nothing by itself. Never paste secrets into a chat, and review anything Muse proposes before it acts.
Saved to your recent installs. Find it anytime on /connect.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.