Borrowing it
Nothing to install: this file belongs to stevenflyai/llm-wiki-web. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/stevenflyai/llm-wiki-web/main/.claude/commands/retro.mdgit clone --depth 1 https://github.com/stevenflyai/llm-wiki-webWrote 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.
[](https://agentmods.dev/commands/stevenflyai/llm-wiki-web/retro)<a href="https://agentmods.dev/commands/stevenflyai/llm-wiki-web/retro"><img src="https://agentmods.dev/badge/commands/stevenflyai/llm-wiki-web/retro.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00408 |
| Opus 5 | $0.00000 | $0.00204 |
| Sonnet 5 | $0.00000 | $0.00082 |
| Haiku 4.5 | $0.00000 | $0.00041 |
Grade A, and why
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 7d 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.
What it actually says
/retro — 会话结束的复盘归档
End-of-session retro. Sort what was learned into the right home.
Step 1: Ask the user
这次会话有哪些值得保留的发现?分别属于哪一类?
Step 2: Categorize
For each learning, classify and propose where it goes:
| 类型 | 去向 |
|---|---|
| 项目级开发约定 | docs/dev/CLAUDE-DEV.md |
| 架构决策 | DECISIONS.md (新 ADR,永不改老的) |
| 可复用工作流 | .claude/commands/<name>.md |
| Wiki 内容/格式规则 | 根目录 CLAUDE.md (运行时契约) |
| Bug + fix 模式 | docs/lessons.md |
| 已完成 SPEC 的事实 | CHANGELOG.md 的 [Unreleased] |
Step 3: Propose, don't auto-commit
Show the user the proposed change for each file, diff-style. Wait for approval before applying.
Step 4: Check sizes
After applying:
- 如果
docs/dev/CLAUDE-DEV.md超过 200 行 → 警告用户拆分 - 如果
DECISIONS.md出现修改老 ADR 的尝试 → 拒绝,提示用 supersede - 如果
BACKLOG.md超过 50 项 → 建议清理一遍
Step 5: PLAN.md state
如果 SPEC 还没完成,确认 PLAN.md 反映了真实进度。
如果 SPEC 已完成,确认:
- CHANGELOG 已追加
- SPEC 文件已
git mv到archive/YYYY-MM-<slug>.md -
PLAN.md已清空或归档到archive/<slug>/PLAN.md
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.
- 7d ago First seen · 41 lines · 0 tokens per session scan A a4e11bcbf071
retro is a command published in the GitHub repository stevenflyai/llm-wiki-web (19 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 408 tokens. 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.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.
recall
Search past tool-call observations with BM25 ranking to answer "have I seen this before?" before re-deriving a fix or repeating a mistake. Enforces Law 1 (Research Before Executing).