retrospective

retrospective is a skill for Claude Code from pixel-cellar/Claude-Code-Game-Studios. It costs 44 tokens per session (1,655 once invoked), scanned A, original, MIT.

A review workflow for a completed sprint or milestone, using plans, completed work, code history, open tasks, and earlier reviews. A sprint is a defined period of development; a milestone is a larger project checkpoint.

In plain words
What is it for?
It helps measure completion, compare planned and actual work, track TODO and FIXME trends, identify patterns, and create actions for the next iteration.
Why use it?
It shows what was delivered against the plan and reveals recurring blockers, unplanned work, and technical debt. Technical debt is unfinished cleanup or design work that can make future changes harder.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit It helps measure completion, compare planned and actual work, track TODO and FIXME trends, identify patterns, and create actions for the next iteration.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pixel-cellar/claude-code-game-studios/retrospective
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 pixel-cellar/Claude-Code-Game-Studios --skill retrospective
Clone the repo
git clone --depth 1 https://github.com/pixel-cellar/Claude-Code-Game-Studios

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 retrospective

README.md
[![agentmods](https://agentmods.dev/badge/skills/pixel-cellar/claude-code-game-studios/retrospective/github.svg)](https://agentmods.dev/skills/pixel-cellar/claude-code-game-studios/retrospective)
Your own site
<a href="https://agentmods.dev/skills/pixel-cellar/claude-code-game-studios/retrospective"><img src="https://agentmods.dev/badge/skills/pixel-cellar/claude-code-game-studios/retrospective/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 retrospective

Your own site · 80×15
<a href="https://agentmods.dev/skills/pixel-cellar/claude-code-game-studios/retrospective"><img src="https://agentmods.dev/badge/skills/pixel-cellar/claude-code-game-studios/retrospective.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 1,655 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 $0.01655
Opus 5.5 $0.00018 $0.00662
Sonnet 5.5 $0.00009 $0.00331
Haiku 4.5 $0.00004 $0.00166

Measured 1mo ago against content hash 9e8e2028e5a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

retrospective 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 1mo 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.

.claude/skills/retrospective/SKILL.md · 150 lines

What it actually says

当此技能被调用时:

  1. 读取参数确定这是 Sprint 回顾 (sprint-N)还是里程碑回顾(里程碑名称)。

  2. 读取 Sprint 或里程碑计划从相应位置:

    • Sprint 计划:production/sprints/
    • 里程碑定义:production/milestones/

    提取:计划任务、预估工作量、负责人和目标。

  3. 读取 git log 以了解该 Sprint 或里程碑覆盖的时间段内 实际提交了什么以及何时提交。

  4. 扫描已完成和未完成的任务,通过对比计划与实际交付物。检查:

    • 按计划完成的任务
    • 已完成但与计划有修改的任务
    • 延期任务(未完成)
    • Sprint 中途添加的任务(计划外工作)
    • 被移除或缩减范围的任务
  5. 扫描代码库中的 TODO/FIXME 趋势:

    • 统计当前的 TODO/FIXME/HACK 注释数
    • 与上一 Sprint 的计数对比(如可用,检查之前的回顾)
    • 注意技术债务是在增长还是减少
  6. 读取之前的回顾(如有),来自 production/sprints/ 或 production/milestones/,以检查:

    • 之前的行动项是否已处理?
    • 相同的问题是否在重复出现?
    • 速率趋势如何?
  7. 生成回顾:

## 回顾:[Sprint N / 里程碑名称]
周期:[开始日期] -- [结束日期]
生成日期:[日期]

### 指标

| 指标 | 计划 | 实际 | 差异 |
|------|------|------|------|
| 任务数 | [X] | [Y] | [+/- Z] |
| 完成率 | -- | [Z%] | -- |
| 故事点 / 工作量天数 | [X] | [Y] | [+/- Z] |
| 发现的 Bug | -- | [N] | -- |
| 修复的 Bug | -- | [N] | -- |
| 新增的计划外任务 | -- | [N] | -- |
| 提交数 | -- | [N] | -- |

### 速率趋势

| Sprint | 计划 | 完成 | 完成率 |
|--------|------|------|--------|
| [N-2] | [X] | [Y] | [Z%] |
| [N-1] | [X] | [Y] | [Z%] |
| [N](当前) | [X] | [Y] | [Z%] |

**趋势**:[上升 / 稳定 / 下降]
[一句话解释趋势]

### 做得好的方面
- [由具体数据或示例支持的观察]
- [另一个正面观察]
- [认可特定贡献或取得了回报的决策]

### 做得不好的方面
- [具有可衡量影响的具体问题 — 例如 "功能 X 花了 5 天而非预估的 2 天,阻塞了任务 Y 和 Z"]
- [另一个有影响的问题]
- [不要归咎个人 — 关注系统性原因]

### 遇到的阻碍

| 阻碍项 | 持续时间 | 解决方式 | 预防措施 |
|--------|---------|---------|---------|
| [什么阻碍了进展] | [持续多久] | [如何解决] | [如何预防再次发生] |

### 估算准确性

| 任务 | 预估 | 实际 | 偏差 | 可能原因 |
|------|------|------|------|---------|
| [最严重高估的任务] | [X] | [Y] | [+Z] | [为什么] |
| [最严重低估的任务] | [X] | [Y] | [-Z] | [为什么] |

**整体估算准确性**:[X%] 的任务在预估的 +/- 20% 以内

[分析:我们是否持续高估或低估?对于哪些类型的任务?应该做何调整?]

### 延期分析

| 任务 | 原始 Sprint | 延期次数 | 原因 | 处理方式 |
|------|-----------|---------|------|---------|
| [未完成的任务] | [Sprint N-X] | [N] | [为什么] | [完成 / 缩减范围 / 重新设计] |

### 技术债务状态
- 当前 TODO 数量:[N](上次:[N])
- 当前 FIXME 数量:[N](上次:[N])
- 当前 HACK 数量:[N](上次:[N])
- 趋势:[增长 / 稳定 / 减少]
- [注意任何令人关注的领域]

### 上次行动项跟进

| 行动项(来自 Sprint N-1) | 状态 | 备注 |
|--------------------------|------|------|
| [上次的行动] | [已完成 / 进行中 / 未开始] | [上下文] |

### 下次迭代的行动项

| # | 行动 | 负责人 | 优先级 | 截止日期 |
|---|------|--------|--------|---------|
| 1 | [具体、可衡量的行动] | [谁] | [高/中/低] | [何时] |
| 2 | [另一个行动] | [谁] | [优先级] | [何时] |

### 流程改进
- [工作方式的具体改变,附预期收益]
- [另一项改进 — 保持在 2-3 个可执行的改进项,而非愿望清单]

### 总结
[2-3 句话整体评估:这是一个好的 Sprint/里程碑吗?下一步最重要的改变是什么?]
  1. 保存回顾到相应位置:

    • Sprint:production/sprints/sprint-[N]-retrospective.md
    • 里程碑:production/milestones/[里程碑名称]-retrospective.md

    如目录不存在则创建。

  2. 向用户输出摘要:完成率、速率趋势方向、首要阻碍项,以及最重要的行动项。

指南

  • 要诚实和具体。模糊的回顾("沟通可以更好")只能产生模糊的改进。使用数据和示例。
  • 关注系统性问题,而非个人责任。
  • 行动项限制在 3-5 个。更多会分散注意力。
  • 每个行动项必须有负责人和截止日期。
  • 检查之前的行动项是否已完成。反复出现的未处理项是流程问题的信号。
  • 如果这是里程碑回顾,还需评估里程碑目标是否达成,以及这对整体项目时间线意味着什么。
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. 1mo ago First seen · 150 lines · 44 tokens per session scan A 9e8e2028e5a9

Subscribe to this mod's changes

retrospective is a skill published in the GitHub repository pixel-cellar/Claude-Code-Game-Studios (361 stars, last pushed 6mo ago), licensed MIT. It adds 44 tokens to every session and 1,655 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.