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
- the Muse app (mobile or web). No installation, no API key, no extra account. Pure guidance skill.
- Level
- Beginner — the Muse app (mobile or web).
- 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:
Quick answer
Agentic Engineering is a free Muse skill for engineering work where AI agents do most implementation and humans enforce quality and risk controls. Its principles are defining completion criteria before execution, decomposing work into independently verifiable fifteen-minute units with one dominant risk each, routing model tiers by task complexity, and measuring with capability plus regression evals.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 4eb71d9Pinned version: install the code at commit 4eb71d92a39cab44ad40ac9d8a6a5ccb4029d6c2 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 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://raw.githubusercontent.com/affaan-m/ECC/4eb71d92a39cab44ad40ac9d8a6a5ccb4029d6c2/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.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 4eb71d9 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 21, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill 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 skill before installing it.