loop-driven-engineering SKILL.md skillA

loop-driven-engineering from corvinlabs/corvinos is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add corvinlabs/corvinos/loop-driven-engineering@git:20260915.459047e

Pins git:20260915.459047e in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
corvinlabs/corvinos
Path
corvin_operator/bundle/skills/ldd/loop-driven-engineering/SKILL.md
Versions recorded
1
Latest version
git:20260915.459047e, committed Sep 15, 2026
Size
13,458 bytes
Repository stars
24
License
Apache-2.0

Use at the start of any non-trivial engineering task (feature, bugfix touching more than one file, refactor with observable behavior change, incident response). Orchestrates the three LDD loops — inner (code), refinement (deliverable), outer (method) — with hard iteration budgets, dispatches the specialist skills at the right moments, and forbids declaring "done" without a synced doc-level mental model.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Loop-Driven-Engineering

## Overview

Engineering is **three loops**, not one. You plan, you try, you measure, you diagnose, you try again — on the **code axis** (inner loop), the **deliverable axis** (refinement), and the **method axis** (outer loop). The thing that separates good engineering from flailing is choosing the right loop for the current loss, respecting each loop's budget, and not smuggling one loop's edits into another's.

**Core principle:** the loop closes when applicable gates are green **and** the doc-level mental model is current. Not when one test passes. Not when "it looks right." Not when the LLM sounds confident.

This skill is a **flexible pattern**, not a rigid procedure. Use judgment; adapt the structure to the task. But the budget, the escalation rule, and the loop-separation rule are hard.

See [`../../docs/ldd/convergence.md`](../../docs/ldd/convergence.md) for the three-loop model in full, and [`../../diagrams/three-loops.svg`](../../diagrams/three-loops.svg) for the picture.

## When to Use

Invoke at the **start** of any non-trivial engineering task:

- Feature touching ≥2 files or ≥1 public surface
- Bugfix where the cause is not yet identified
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add corvinlabs/corvinos/loop-driven-engineering@sha256:f56281039ec1fdce

The line at the top of this page pins the label git:20260915.459047e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_yi6u35tvlwic3dyr.svg)](https://markdownregistry.com/a/art_yi6u35tvlwic3dyr)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Sep 15, 2026.

versioncommittedcommitsizeaudit
git:20260915.459047e latest2026-09-15 459047e 13,458 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (13458 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

corvinlabs/corvinos · 24 stars · license Apache-2.0 · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_yi6u35tvlwic3dyr
GET https://markdownregistry.com/api/v1/resolve?ref=corvinlabs/corvinos/loop-driven-engineering
GET https://markdownregistry.com/api/v1/blob/f56281039ec1fdce3793861d04794207362603db4e92e7322c91c3effba7787e

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from corvinlabs/corvinos

CLAUDE.md CLAUDE.md file
corvinlabs/corvinos · CLAUDE.md
git:20261105.74f2594 · audit B · 24 stars
market_analyst SKILL.md skill
corvinlabs/corvinos · core/awpkg/tests/fixtures/dag_complex/src/skills/market_analyst/SKILL.md
git:20260831.ba2b871 · audit C · 24 stars
news_analyst SKILL.md skill
corvinlabs/corvinos · core/awpkg/tests/fixtures/dag_simple/src/skills/news_analyst/SKILL.md
git:20260831.ba2b871 · audit C · 24 stars
code_reviewer SKILL.md skill
corvinlabs/corvinos · core/awpkg/tests/fixtures/delegation/src/skills/code_reviewer/SKILL.md
git:20260831.ba2b871 · audit C · 24 stars
data_analysis SKILL.md skill
corvinlabs/corvinos · core/awpkg/tests/fixtures/full_pipeline/src/skills/data_analysis/SKILL.md
git:20260831.ba2b871 · audit C · 24 stars
quality_assessment SKILL.md skill
corvinlabs/corvinos · core/awpkg/tests/fixtures/full_pipeline/src/skills/quality_assessment/SKILL.md
git:20260831.ba2b871 · audit C · 24 stars
report_writing SKILL.md skill
corvinlabs/corvinos · core/awpkg/tests/fixtures/full_pipeline/src/skills/report_writing/SKILL.md
git:20260831.ba2b871 · audit C · 24 stars
quant_trading SKILL.md skill
corvinlabs/corvinos · core/awpkg/tests/fixtures/mixed/src/skills/quant_trading/SKILL.md
git:20260831.ba2b871 · audit C · 24 stars
risk_management SKILL.md skill
corvinlabs/corvinos · core/awpkg/tests/fixtures/mixed/src/skills/risk_management/SKILL.md
git:20260831.ba2b871 · audit C · 24 stars
os.delegation_router SKILL.md skill
corvinlabs/corvinos · core/skills/bundled/os_delegation_router_v1.0/SKILL.md · Route tasks to native OS, ACS, or TDE
v1.0.0 · audit A · 24 stars
adr_gate SKILL.md skill
corvinlabs/corvinos · corvin_operator/bundle/skills/ldd/adr_gate/SKILL.md · ADR Gate — evaluates after non-trivial tasks whether an ADR is warranted; creates it in the tenant knowledge base…
git:20261103.0105fa8 · audit A · 24 stars
concept_gate SKILL.md skill
corvinlabs/corvinos · corvin_operator/bundle/skills/ldd/concept_gate/SKILL.md · Concept Gate — evaluates after non-trivial tasks whether a reusable WORKING METHOD (not a decision, not a bug fix) is…
git:20261103.0105fa8 · audit A · 24 stars

Every file in corvinlabs/corvinos

Browse by kind, by grade A, or by owner.