vibe-retro

vibe-retro is a skill for Claude Code from chentao326/vibe-code. It costs 57 tokens per session (1,587 once invoked), scanned A, original, MIT.

A Chinese-language review workflow for comparing predicted and actual results after a coding task is finished. It records the differences and updates project observations.

In plain words
What is it for?
It is for reviewing completed or abandoned coding tasks, reading prediction files, collecting actual results, analysing deviations, and updating handoff and project state files.
Why use it?
It gives a structured way to see where estimates about time, work rounds, bugs, or satisfaction were wrong.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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/chentao326/vibe-code/vibe-retro
Any agent
npx skills add chentao326/vibe-code --skill vibe-retro
Clone the repo
git clone --depth 1 https://github.com/chentao326/vibe-code

Made for: Claude Code.

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-retro

README.md
[![agentmods](https://agentmods.dev/badge/skills/chentao326/vibe-code/vibe-retro.svg)](https://agentmods.dev/skills/chentao326/vibe-code/vibe-retro)
Your own site
<a href="https://agentmods.dev/skills/chentao326/vibe-code/vibe-retro"><img src="https://agentmods.dev/badge/skills/chentao326/vibe-code/vibe-retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,587 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 $0.00057 $0.01587
Opus 5 $0.00028 $0.00794
Sonnet 5 $0.00011 $0.00317
Haiku 4.5 $0.00006 $0.00159

Measured 6d ago against content hash ba680e0c328e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

vibe-retro 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 6d 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.

skills/vibe-retro/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vibe-retro — 复盘对账

编码完成后的复盘:采集数据 → 对比预估 → 偏差分析 → 写入观察 → 检查 bump 触发。


Overview

Phase 0: 确认任务状态
Phase 0.1: Handoff phase detection(融合)
Phase 1: 读 prediction 文件 + 缓存预估段 hash
Phase 2: 采集实际数据(adapters + 用户输入 + handoff 数据)
Phase 3: 对比预估 vs 实际
Phase 4: 写入复盘段
Phase 5: 校验 immutability
Phase 6: 更新 state + rubric.md

Workflow

Phase 0: 确认任务状态

  1. 确认用户已完成编码(或放弃)
  2. 如放弃 → 标 status: abandoned,不计入 calibration_samples,但保留 prediction 文件

Phase 0.1: Handoff phase detection(融合协议)

根据 handoff-vibe-bridge.md 检测当前 handoff 阶段:

ls handoff/*.json 2>/dev/null || echo "NO_FILES"
handoff 状态 处理
handoff/build-done.json 存在 自动触发复盘——无需用户手动确认。读取 files_changedcompleted_tasks 作为数据源
handoff/ 有其他文件但无 build-done 正常复盘,标注 handoff_phase: <当前阶段>
handoff/ 为空 正常复盘,标注 handoff_phase_unknown: true

如果 build-done.json 存在

  1. 解析 files_changed 列表 → 传给 Phase 2 adapters
  2. 解析 completed_tasks → 用于偏差分析
  3. 复盘完成后更新 .vibe-state.jsonhandoff_phasereview-ready

Phase 1: 读 prediction 文件

  1. 根据 task-id 找到 predictions/<task-id>.md
  2. 缓存 ## 预估 v1 段 hash(后续校验用)
  3. 读预估数据(轮次/耗时/bug风险/满意度/关键假设)

Phase 2: 采集实际数据

如果 state.data_collection = "auto"

运行 adapters:

# git-stats: 从 task 开始时的 HEAD 到当前 HEAD 的 diff
cd <user-project>
bash <vibe-code-path>/adapters/git-stats/collect.sh <task-id> <start-commit>

# lint-collector: 当前 lint 状态
bash <vibe-code-path>/adapters/lint-collector/collect.sh <task-id>

如果 adapter 输出成功 → 写入 retros/<task-id>/report.md

如果 state.data_collection = "manual"

询问用户:

📊 复盘需要以下数据:

1. 实际对话轮次?(预计 {{pred_iter}})
2. 实际耗时?(预计 {{pred_time}})
3. 有 bug 吗?几个?
4. 满意度 1-10?(预计 {{pred_sat}})
5. 有什么意外情况?

Phase 3: 对比预估 vs 实际

逐项对比:

对比项 判定
轮次在预估范围内 ✅ 命中
轮次低于预估下限 ✅ 高估(好于预期)
轮次高于预估上限 ❌ 低估(差于预期)
耗时同理
Bug 风险预估 vs 实际
满意度预估 vs 实际

偏差方向:如果连续 ≥3 次同向偏差 → 标记 consecutive_directional_errors + 在状态报告里提示"可能该 bump 了"。

Read the full file on GitHub · 158 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. 6d ago First seen · 158 lines · 57 tokens per session scan A ba680e0c328e

Subscribe to this mod's changes

vibe-retro is a skill published in the GitHub repository chentao326/vibe-code (2 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 1,587 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 2026-08-31.

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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens