vibe-dispatch-fix

vibe-dispatch-fix is a skill for Claude Code from OAI-Labs/vibe-flow. It costs 44 tokens per session (1,393 once invoked), scanned A, original, MIT.

A retry-and-escalation helper for a pull request that failed review or automated tests. It sends the same work back to a coding agent, or assigns a higher agent tier after repeated failures.

In plain words
What is it for?
Use it after requested review changes or failed continuous integration checks, when the issue is still suitable for automated repair.
Why use it?
It keeps review feedback and test failures connected to the existing branch instead of starting a separate task. After three failed escalation attempts, it asks a human to take over.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the vibe-flow plugin — 14 skills, 2 agents shipped together

Good fit Use it after requested review changes or failed continuous integration checks, when the issue is still suitable for automated repair.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oai-labs/vibe-flow/vibe-dispatch-fix
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.

Any agent
npx skills add OAI-Labs/vibe-flow --skill vibe-dispatch-fix
Clone the repo
git clone --depth 1 https://github.com/OAI-Labs/vibe-flow

Made for: Claude Code.

Or install vibe-flow, the plugin that ships this one along with the rest of its 14 skills, 2 agents.

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-dispatch-fix

README.md
[![agentmods](https://agentmods.dev/badge/skills/oai-labs/vibe-flow/vibe-dispatch-fix/github.svg)](https://agentmods.dev/skills/oai-labs/vibe-flow/vibe-dispatch-fix)
Your own site
<a href="https://agentmods.dev/skills/oai-labs/vibe-flow/vibe-dispatch-fix"><img src="https://agentmods.dev/badge/skills/oai-labs/vibe-flow/vibe-dispatch-fix/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for vibe-dispatch-fix

Your own site · 80×15
<a href="https://agentmods.dev/skills/oai-labs/vibe-flow/vibe-dispatch-fix"><img src="https://agentmods.dev/badge/skills/oai-labs/vibe-flow/vibe-dispatch-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,393 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00044 $0.01393
Opus 5 $0.00022 $0.00696
Sonnet 5 $0.00009 $0.00279
Haiku 4.5 $0.00004 $0.00139

Measured 9d ago against content hash 061d37b2d575, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

vibe-dispatch-fix 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 9d ago.

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.

plugins/vibe-flow/skills/vibe-dispatch-fix/SKILL.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vibe-dispatch-fix

Overview

Close the review-fix loop. Re-dispatch an agent (same or escalated tier) to fix review feedback or CI failures on the same branch.

Core principle: Failed once → maybe retry same tier. Failed twice → escalate. Failed thrice → ask human.

Announce at start: "I'm using the vibe-dispatch-fix skill to re-dispatch fixes."

When to use

  • Review returned request-changes or reject
  • CI failed after PR opened
  • User manually invokes with feedback

Do NOT use if:

  • Original review has only minor items (merge and file follow-up instead)
  • Issue is blocked waiting on human decision
  • 3 escalations already recorded (go to blocked)

The process

Step 1: Diagnose

Fetch:

  • Review feedback (<VIBE-REVIEW> block) from state.json or GitHub PR reviews
  • CI logs (if CI failed): gh run view <RUN_ID> --log-failed
  • Current tier of the issue (from state.json)

Classify failure:

Type Signal
Spec gap Review spec_compliance: fail
Correctness bug Critical items reference logic errors
Missing tests Critical items reference missing tests
Style/hygiene only Only minor + important (→ don't re-dispatch, just merge)
CI infra failure CI red but not due to code (flaky test, env)

Step 2: Decide strategy

If style/hygiene only → RETURN without dispatching
If CI infra failure → retry CI once (`gh run rerun <ID>`), if still red → treat as code issue
If tier < T3 AND (correctness or spec gap) → escalate tier +1
If tier == T3 AND second failure → try T3 + interactive brainstorm
If tier == T4 AND failure → ask user
If spec gap severe → create sub-issue for clarification, block parent

Step 3: Check escalation count

From state.json, count escalations for this issue.
If count >= 3 → mark blocked, STOP.
Else → proceed.

Step 4: Build fix prompt

Use references/prompt-templates.md section 7 (fix dispatch prompt). Fill:

  • {{ISSUE_SIMPLE_ID}}
  • {{REVIEW_CRITICAL}} — verbatim critical items
  • {{REVIEW_IMPORTANT}} — verbatim important items
  • {{BRANCH_NAME}} — same branch (continuation)
  • {{PR_URL}}

Read the full file on GitHub · 181 lines

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. 9d ago First seen · 181 lines · 44 tokens per session scan A 061d37b2d575

Subscribe to this mod's changes

vibe-dispatch-fix is a skill published in the GitHub repository OAI-Labs/vibe-flow (1 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 1,393 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

postmortem

Auto-generates a structured postmortem from a completed campaign. Reads the campaign file, telemetry logs, and feature ledger. Produces a documented analysis of what broke, what the safety systems caught, and what patterns emerged. Can also be invoked manually for any incident.

SethGammon/Citadel · 58 tokens

systematic-debugging

4-phase root cause analysis: observe, hypothesize, verify, fix. Enforces investigation before any code changes. Emergency stop after 2 failed fixes. Prevents shotgun debugging and fix cascades.

SethGammon/Citadel · 45 tokens

operating-cadence

Designs the rhythm an organization runs on — which reviews happen weekly, monthly and quarterly, what each one decides, who owns the numbers presented, and how a signal at the front line reaches the people who can act on it. Use this to set up a management operating system, fix a meeting calendar that produces no…

cbrock84/headcount · 95 tokens

analyze

Deep-dive codebase analysis that explains how things actually work — business rules, architecture patterns, auth flows, data models, integrations, and performance hotspots. Use whenever the user asks "how does X work", "map the Y flow", "what are the business rules for Z", "trace the auth path", "explore the codebase…

rsmdt/the-startup · 118 tokens

debug

Systematically diagnose and resolve bugs through conversational investigation and root cause analysis.

rsmdt/the-startup · 15 tokens

testing

Writing effective tests and running them successfully. Covers layer-specific mocking rules, test design principles, debugging failures, and flaky test management. Use when writing tests, reviewing test quality, or debugging test failures.

rsmdt/the-startup · 42 tokens