AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Vibe Loop

skill-brifl-coding-agent-orchestration-vibe-loop · by brifl

Run one deterministic Vibe dispatcher step and print the selected prompt body.

↗ Repository
— No reviews yet
0 installs
39 views
0.0% view→install

Install

$ agentstack add skill-brifl-coding-agent-orchestration-vibe-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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-brifl-coding-agent-orchestration-vibe-loop)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
○ 6mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Vibe Loop? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Purpose

Drive the Vibe workflow deterministically for a target repository.

This skill uses .vibe/STATE.md and .vibe/PLAN.md to recommend the next loop prompt and to validate invariants.

Inputs

  • Repo root path (default: current working directory)
  • Optional: --strict validation for CI-grade checks

Scripts

  • scripts/agentctl.py
  • scripts/vibe_next_and_print.py

How to use

  • Show current status:
  • Run: python3 scripts/agentctl.py --repo-root . --format json status
  • Recommend next loop:
  • Run: python3 scripts/agentctl.py --repo-root . --format json next
  • Recommend next loop using a named workflow (for example workflows/continuous-refactor.yaml):
  • Run: python3 scripts/agentctl.py --repo-root . --format json next --workflow continuous-refactor
  • Pass the workflow file stem (continuous-refactor), not the .yaml filename.
  • Validate invariants:
  • Run: python3 scripts/agentctl.py --repo-root . --format json validate
  • Strict mode (recommended in CI): add --strict
  • Record loop completion from emitted LOOP_RESULT:
  • Run: python3 scripts/agentctl.py --repo-root . --format json loop-result --line 'LOOP_RESULT: {...}'
  • Print the next loop prompt body directly:
  • Run: python3 scripts/vibe_next_and_print.py --repo-root . --show-decision
  • The helper uses the same CODEX_HOME-aware layout detection as tools/bootstrap.py so it works from both repo trees and global installs.

Intended usage pattern

1) Run next to obtain recommended_prompt_id. 2) Use the vibe-prompts skill to print the corresponding prompt body. 3) Execute that prompt loop in the agent session. 4) Record LOOP_RESULT via agentctl loop-result. 5) Select next loop from next. Repeat until dispatcher returns stop or blocking.

The vibe_next_and_print.py helper wraps agentctl.py and prompt_catalog.py, prints the decision JSON (when --show-decision is set), and then emits the prompt body from the catalog. It locates the installed vibe-prompts skill via the same CODEX_HOME-aware logic as tools/bootstrap.py so it works from both repo sources and global installs.

This skill intentionally does not implement product code by itself; it selects and gates the next action.

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.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills