vibe-run

vibe-run is a skill for Claude Code, Codex from brifl/coding-agent-orchestration. It costs 58 tokens per session (1,065 once invoked), scanned A, original, MIT.

A workflow that repeatedly works through a repository's Vibe backlog, a saved list of planned engineering tasks.

In plain words
What is it for?
It helps inspect a repository, create or refill .vibe/PLAN.md, implement backlog items, review checkpoints, and defer work that needs input or another dependency.
Why use it?
It keeps implementation, review, and handoff work moving while recording blocked tasks and avoiding unnecessary process.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/brifl/coding-agent-orchestration/vibe-run
Any agent
npx skills add brifl/coding-agent-orchestration --skill vibe-run
Clone the repo
git clone --depth 1 https://github.com/brifl/coding-agent-orchestration

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for vibe-run

README.md
[![agentmods](https://agentmods.dev/badge/skills/brifl/coding-agent-orchestration/vibe-run.svg)](https://agentmods.dev/skills/brifl/coding-agent-orchestration/vibe-run)
Your own site
<a href="https://agentmods.dev/skills/brifl/coding-agent-orchestration/vibe-run"><img src="https://agentmods.dev/badge/skills/brifl/coding-agent-orchestration/vibe-run.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,065 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.01065
Opus 5 $0.00029 $0.00532
Sonnet 5 $0.00012 $0.00213
Haiku 4.5 $0.00006 $0.00106

Measured 5d ago against content hash fccdc7a5cd86, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

vibe-run scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/vibe_run.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.codex/skills/vibe-run/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vibe Run

Run the Vibe workflow as an agent loop. Treat .vibe/PLAN.md as a durable execution backlog, not as a substitute for inspecting the repository.

Operating posture

$vibe-run is high-throughput scaffolding for complex work. It should keep Codex moving through design, implementation, review, and handoff without letting process become the product.

  • Use evidence as lightweight trust-but-verify receipts, not comprehensive proof.
  • Prefer one or two high-signal checks over broad verification when risk is low.
  • Let non-building loops earn their cost: they should reduce rework, backsliding, rediscovery, or shaky handoffs.
  • Keep moving when the next capability is safe; record useful non-blocking checks as concise backlog items instead of making them gate every loop.
  • If an issue, checkpoint, or stage is blocked but later independent work can safely proceed, mark it [DEFERRED], add a short reason plus unblock/revisit condition, and move on. Waiting on human feedback is a valid deferral reason.
  • Revisit [DEFERRED] items during design and consolidation; reactivate them when the unblock condition is true, otherwise keep the note compact.

Start

  1. Read AGENTS.md, .vibe/STATE.md, and .vibe/PLAN.md in that order.

  2. From the repository root, dispatch with the explicit vibe-run workflow:

    python3 .codex/skills/vibe-loop/scripts/agentctl.py --repo-root . --format json next --workflow vibe-run
    

    In this orchestration source repo, use python3 tools/agentctl.py ... instead; the .codex dispatcher script is generated during install.

  3. Fetch recommended_prompt_id from the returned prompt_catalog_path:

    python3 .codex/skills/vibe-prompts/scripts/prompt_catalog.py <prompt_catalog_path> get <recommended_prompt_id>
    

    In this orchestration source repo, use python3 tools/prompt_catalog.py ... instead.

  4. Follow the fetched prompt as the current loop. Inspect and edit the repository yourself; scripts/vibe_run.py is a terminal/headless helper, not a replacement for Codex executing the work.

  5. Emit and record the prompt's LOOP_RESULT, then dispatch again.

Read the full file on GitHub · 101 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 101 lines · 58 tokens per session scan A fccdc7a5cd86

Subscribe to this mod's changes

vibe-run is a skill published in the GitHub repository brifl/coding-agent-orchestration (20 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 1,065 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens