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.
npx agentmods add skills/aisee-lab/aisee-plugin/aisee-reflectnpx skills add AISEE-LAB/aisee-plugin --skill aisee-reflectgit clone --depth 1 https://github.com/AISEE-LAB/aisee-pluginWrote 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/aisee-lab/aisee-plugin/aisee-reflect)<a href="https://agentmods.dev/skills/aisee-lab/aisee-plugin/aisee-reflect"><img src="https://agentmods.dev/badge/skills/aisee-lab/aisee-plugin/aisee-reflect.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 | $0.00144 | $0.01916 |
| Opus 5 | $0.00072 | $0.00958 |
| Sonnet 5 | $0.00029 | $0.00383 |
| Haiku 4.5 | $0.00014 | $0.00192 |
Grade A, and why
aisee: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 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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aisee:reflect
复盘当前会话，识别可复用经验，并把结论写成项目内可版本化、可审查的候选资产。
生成 reflect 文档时，frontmatter 字段合同统一遵循 plugins/aisee-plugin/references/planning-doc-frontmatter.md；这些文档只服务索引和候选沉淀，不提升为 OpenSpec 事实源。
aisee:reflect 默认只负责 反思、归纳、候选沉淀。aisee/docs/reflect/ 是候选区，不是规范事实源；aisee/memory/ 才是经用户确认后的长期项目记忆区。不要直接修改全局记忆、隐藏配置、OpenSpec baseline、active change artifacts 或其他技能目录，除非用户明确要求继续执行对应改动。
与 Compound 知识沉淀的边界
aisee:reflect 不替代 ce-compound、ce-compound-refresh 或 docs/solutions/：
ce-compound记录一个刚解决的具体工程问题、根因、解决方案和预防措施。ce-compound-refresh维护docs/solutions/，处理过期、重复、合并或删除。aisee:reflect负责会话复盘、分类、memory 候选、workflow/skill 改进候选，以及跨项目复用候选判断。
如果复盘中发现“具体已解决工程问题”适合写 solution，不要在 reflect 中重复生成 solution 正文；输出 follow-up：Suggested follow-up: run ce-compound for the concrete solution.。Reflect 可以引用 docs/solutions/... 作为证据来源，但不能复制或改写同一内容。
输出位置
| 产物 | 路径 |
|---|---|
| 会话复盘与 memory 候选 | aisee/docs/reflect/YYYY-MM-DD_<slug>.md |
| 新技能草案 | aisee/docs/reflect/skills/YYYY-MM-DD_<skill-name>.md |
| 现有技能优化建议 | aisee/docs/reflect/skill-patches/YYYY-MM-DD_<skill-name>.md |
| 工作流修复建议 | aisee/docs/reflect/workflow-fixes/YYYY-MM-DD_<slug>.md |
| 可复用知识候选 | aisee/docs/reflect/knowledge-candidates/YYYY-MM-DD_<slug>.md |
| 已确认长期记忆 | aisee/memory/arch/、aisee/memory/pref/、aisee/memory/ctx/、aisee/memory/stack/ |
文件名使用当天日期和短 kebab-case slug。默认使用用户语言；没有明确语言时使用中文。
工作模式
根据用户意图选择模式：
| 用户意图 | 行为 |
|---|---|
| 只说“reflect / 复盘 / 总结这次” | 先输出复盘报告，不写文件，等待用户确认 |
| 明确说“保存 / 写入 / 生成文档 / 全部落盘” | 输出报告后直接写入对应文件 |
| 明确说“写入 memory / 提升到记忆 / 更新 aisee/memory” | 转用 aisee:memory 工作流；优先通过 aisee memory add ... --json 写入项目记忆 |
| 明确要求“转成 skill / 优化某技能” | 生成技能草案或技能补丁，不把草案直接提升为活动技能 |
| 明确要求“跨项目复用 / 以后其他项目也用 / 避免重复犯错” | 生成 reusable knowledge candidate，不写全局知识库 |
| 会话很短或缺少可沉淀信息 | 说明发现有限，只列出有信号的事项 |
如果用户要求修改真实技能目录，应结合 skill-creator 工作流；本技能生成的草案默认只是审查材料。
边界
必须遵守：
aisee/docs/reflect/只存复盘记录、候选规则、技能草案、补丁建议和 workflow fix。aisee/memory/只有在用户明确要求“写入 memory / 提升到记忆 / 更新 aisee/memory”时才写。- 写入
aisee/memory/前必须运行aisee memory inspect --json；不存在时可由aisee memory add创建 canonical 结构，不要临时发明结构。 - 不写全局 memory、用户主目录 memory 或代理私有 memory，除非用户明确要求并确认影响。
- 不把 reflect 文档当作 OpenSpec change、baseline spec、SRS、UI Content、Architecture、tasks 或 source-map 的替代品。
- 不把 reflect 文档当作
docs/solutions/的替代品；具体问题解决方案应交给ce-compound。 - 不把一次性偶然事件写成长期规则；优先沉淀未来再次发生时会节省时间或降低风险的内容。
- 不写入 secrets、token、cookie、私密身份信息或生产凭据。
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 106 lines · 144 tokens per session scan A f3bd6fb81334
aisee:reflect is a skill published in the GitHub repository AISEE-LAB/aisee-plugin (11 stars, last pushed 2mo ago), licensed MIT. It adds 144 tokens to every session and 1,916 once invoked, about $0.0007 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
codex-sdd:archive
Preserve change artifacts (proposal, design, tasks) into structured archive and update knowledge base. Final phase of OpenSpec workflow.
obsidian-vault
Organize Obsidian vaults with MOCs, wikilinks, frontmatter/properties, dashboards, orphan-note checks, and cleanup workflows. Use ONLY when the user explicitly refers to Obsidian — by naming "Obsidian", an Obsidian "vault", or an Obsidian-specific feature such as wikilinks ("[[ ]]"), the Dataview or Bases plugins, or…
task-agent-eliza-bridge
Use when spawning a Claude Code, Codex, Gemini, Aider, or other CLI task agent whose work needs parent Eliza runtime context. Covers the read-only loopback bridge for character, room, memory, and active workspace state.
aatmf-t04-memory-manipulation
AATMF T4 — Multi-Turn & Memory Manipulation. Persistent memory injection, conversation-state poisoning, cross-session contamination, ghost-context leak.
kb-builder
Build an Obsidian-compatible knowledge base from public web sources using the TinyFish CLI. Use this skill when a user wants a builder-grade markdown knowledge base on a technical topic, asks for a structured research vault, or wants a topic compiled from live public sources into interlinked markdown files. Supports…
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.