An end-of-session review command that sorts useful discoveries into project documentation, architecture decisions, reusable workflows, lessons, or release notes.

Use it after a coding session to record conventions, decisions, bug fixes, completed specifications, and the current project plan.

It turns scattered session knowledge into proposed updates in the places where future work can find it, while requiring approval before changes are applied.

How stevenflyai/llm-wiki-web configures Claude Code

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/stevenflyai/llm-wiki-web/main/.claude/commands/retro.md

Clone the repo

git clone --depth 1 https://github.com/stevenflyai/llm-wiki-web

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/stevenflyai/llm-wiki-web/retro/github.svg)](https://agentmods.dev/commands/stevenflyai/llm-wiki-web/retro)

Your own site

<a href="https://agentmods.dev/commands/stevenflyai/llm-wiki-web/retro"><img src="https://agentmods.dev/badge/commands/stevenflyai/llm-wiki-web/retro/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.

Your own site · 80×15

<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="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 408 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00408
Opus 5.5	$0.00000	$0.00163
Sonnet 5.5	$0.00000	$0.00082
Haiku 4.5	$0.00000	$0.00041

Measured 2mo ago against content hash a4e11bcbf071, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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/commands/retro.md · 41 lines

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

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.

2mo ago First seen · 41 lines · 0 tokens per session scan A a4e11bcbf071

Subscribe to this mod's changes

retro is a command published in the GitHub repository stevenflyai/llm-wiki-web (19 stars, last pushed 5mo 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.

Memory and context

retro next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
retrostevenflyai/llm-wiki-web	Command	19	5mo ago	MIT	A	0	Claude Code
minutes-ideassilverstein/minutes	Command	1.6k	yesterday	MIT	A	48	Claude Code, OpenCode
learnReflexioAI/claude-smart	Command	791	3d ago	Apache-2.0	A	14	Claude Code
memory-storeverygoodplugins/mcp-automem	Command	66	yesterday	MIT	A	10	Claude Code
analyze-contextRohiRIK/OpenLtm	Command	29	8d ago	MIT	A	39	Claude Code
cc-memoryTheLobbi/claude	Command	21	7d ago	MIT	A	0	Claude Code
lians-recallLians-ai/Lians	Command	17	5d ago	Apache-2.0	A	19	Claude Code

llm-wiki-web: Command for Claude Code