Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/zylMozart/ClaudeTeamnpx agentmods add skills/zylmozart/claudeteam/reflectWrote 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/skills/zylmozart/claudeteam/reflect)<a href="https://agentmods.dev/skills/zylmozart/claudeteam/reflect"><img src="https://agentmods.dev/badge/skills/zylmozart/claudeteam/reflect/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.
<a href="https://agentmods.dev/skills/zylmozart/claudeteam/reflect"><img src="https://agentmods.dev/badge/skills/zylmozart/claudeteam/reflect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00001 | $0.00951 |
| Opus 5 | $0.00000 | $0.00476 |
| Sonnet 5 | $0.00000 | $0.00190 |
| Haiku 4.5 | $0.00000 | $0.00095 |
Grade A, and why
reflect 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 11d 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
reflect — 反思并收拾团队共享经验库
何时用
团队共享经验(claudeteam recall --team)是一条条 append 出来的,时间一长会重复、矛盾、过时。这个 skill 把它从"越堆越乱的流水账"收拾成"少而准、全队常驻"的核心知识。什么时候跑:
- 周期性:每隔一段协作(一个里程碑 / 一天)由 manager 触发一次。
- 触发式:发现
recall --team里同一件事记了好几遍、新旧结论打架、或注入到身份里的置顶条已经不准。
核心约束:你在做语义判断,不是关键词去重。两条字面不同但说的是同一件事,要合并;一条曾经对、现在环境变了不再成立,要退役。靠你通读理解,不靠规则匹配。
输入
- 整个经验库:
claudeteam recall --team --limit 1000(拿全量,别只看尾巴)。 - 按主题抽取:
claudeteam recall --team --grep <关键词>。 - 你对当前仓库/团队现状的理解(判断某条是否还成立)。
步骤
-
通读全量。
claudeteam recall --team --limit 1000拉全部,从头读一遍,边读边归类:哪些是全队通用的硬事实、哪些是一次性细节、哪些重复、哪些过时/已被推翻。📌标的是当前置顶(常驻每个员工上下文)的条目。 -
合并重复。同一件事的多条,挑信息最全的一条
--update改成最准的措辞,其余forget --team --id退役:claudeteam remember <你的名字> <kind> "<合并后的准确说法>" --team --update E-3 claudeteam forget --team --id E-7 # 被合并掉的重复条 -
退役过时/错误。环境变了不再成立、或当时就记错的,直接退役:
claudeteam forget --team --id E-9 -
提炼并置顶核心。把全队都该常驻的少数硬事实(测试怎么跑、部署铁律、反复踩的坑)
--pin起来——只有置顶的才一直在每个员工上下文里;其余保持不置顶,各自需要时recall --grep现拉。置顶宁缺毋滥:越少越好用(身份文件越短,agent 越听指令)。claudeteam remember <你的名字> learning "本仓库测试用 python3 tests/run.py" --team --update E-1 --pin -
收尾。再
recall --team看一眼:置顶条是不是一眼就是"最该全队知道的那几条",列表里还有没有明显重复/矛盾。把这轮做了什么(合并 N、退役 M、置顶 K)简短汇报给老板或记一条 team 经验。
产物
一个更短、更准、置顶清晰的团队经验库:重复已合并、过时已退役、全队通用的少数条目已置顶常驻。做完的标志:recall --team 里没有明显重复/矛盾,每条置顶都是真·全队通用且当前成立。
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.
- 11d ago First seen · 50 lines · 1 tokens per session scan A 5a4958bec275
reflect is a skill published in the GitHub repository zylMozart/ClaudeTeam (232 stars, last pushed 1mo ago), licensed MIT. It adds 1 tokens to every session and 951 once invoked, about $0.0000 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 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.