AgentStack
SKILL verified MIT Self-run

Adlc Loop

skill-davidvictor-adlc-skills-adlc-loop · by davidvictor

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

No reviews yet
0 installs
4 views
0.0% view→install

Install

$ agentstack add skill-davidvictor-adlc-skills-adlc-loop

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Adlc Loop? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

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.

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

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.