# Adlc Loop

> Run an iterative ADLC improvement loop with explicit criteria, gates, and stop conditions.

- **Type:** Skill
- **Install:** `agentstack add skill-davidvictor-adlc-skills-adlc-loop`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [davidvictor](https://agentstack.voostack.com/s/davidvictor)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [davidvictor](https://github.com/davidvictor)
- **Source:** https://github.com/davidvictor/adlc-skills/tree/main/skills/adlc/adlc-loop

## Install

```sh
agentstack add skill-davidvictor-adlc-skills-adlc-loop
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# ADLC Loop

Use this for bounded iterative improvement where one pass is unlikely to be enough.

## Process

1. Resolve effective ADLC paths from `.adlc/config.yaml`; use `adlc resolve-config` when the CLI is available.
2. Define the loop goal, criteria, maximum iterations, and stop conditions.
3. Read roadmap, rules, active plan, verification history, QA artifacts, and patches.
4. For workstream loops, attach the loop to the active Codex goal and current milestone before editing.
5. For each iteration, plan the smallest useful change, implement it through `adlc-implement` or `adlc-fix`, then run `adlc-verify` and relevant gates.
6. Record loop notes under the configured loops path or active workstream step.
7. Stop when criteria pass, risk rises, the iteration budget is exhausted, or a human decision is required.

## Output

Report iteration count, changes made, gates run, remaining gaps, stop reason, and the next command.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [davidvictor](https://github.com/davidvictor)
- **Source:** [davidvictor/adlc-skills](https://github.com/davidvictor/adlc-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-davidvictor-adlc-skills-adlc-loop
- Seller: https://agentstack.voostack.com/s/davidvictor
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.