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 skills add daisyyang1109-super/mirror-viewer --skill summarize-sessionsgit clone --depth 1 https://github.com/daisyyang1109-super/mirror-viewerWrote 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/daisyyang1109-super/mirror-viewer/summarize-sessions)<a href="https://agentmods.dev/skills/daisyyang1109-super/mirror-viewer/summarize-sessions"><img src="https://agentmods.dev/badge/skills/daisyyang1109-super/mirror-viewer/summarize-sessions/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/daisyyang1109-super/mirror-viewer/summarize-sessions"><img src="https://agentmods.dev/badge/skills/daisyyang1109-super/mirror-viewer/summarize-sessions.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00085 | $0.00772 |
| Opus 5 | $0.00043 | $0.00386 |
| Sonnet 5 | $0.00017 | $0.00154 |
| Haiku 4.5 | $0.00009 | $0.00077 |
Grade A, and why
summarize-sessions 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 10d 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
Summarize-Sessions — 给所有 session 加摘要 + 标签
跑 DeepSeek 读完整 session,输出:
summary: 一句话(<= 50 字)说明 session 讨论了什么、落到什么结论tags: 3-5 个关键词标签(短词)
结果累积到 /tmp/mirror/summaries.json,mirror viewer index 表自动读取展示。
触发后的动作
1. 解析参数
$ARGUMENTS=--all→ 全量重跑(包括已有摘要的)$ARGUMENTS空 → 增量(只跑还没摘要的)$ARGUMENTS=--sid <session-id>→ 只跑指定 session
2. 跑主脚本
直接执行:
python3 ~/.claude/skills/summarize-sessions/summarize.py $ARGUMENTS
主脚本自给自足:
- 自动找 DeepSeek key(env DEEPSEEK_API_KEY → ~/.deepseek)
- 读
~/.claude/mirror/search-index.json拿每个 session 的 msgs - 读
~/.claude/mirror/summaries.json看已有(增量模式跳过) - 对每个待处理 session 调 DeepSeek API,提取 summary + tags
- 累积写回
/tmp/mirror/summaries.json - 跑完触发
python3 /tmp/jsonl2html.py --all /tmp/mirror重新渲染
3. 报告进度
跑完后给 Daisy 报:
- 处理了 N 个 session
- 跳过 M 个(已有摘要)
- 失败 K 个(列 sid)
- 总耗时 / 估计花费
4. 一致性约束
- 绝不在新文件里写 key(memory
feedback_warn_before_pasting_secrets.md) - 失败的 session 不阻塞已成功的(每条独立写盘)
- LLM 输出必须是合法 JSON,不合法重试 1 次后放弃
- 增量是默认,Daisy 不主动说
--all就别全量重跑(浪费 token)
成本预算
- 一次 backfill 28 个 session ≈ ¥0.4
- 单 session 增量 ≈ ¥0.015
- 一年 1000 session ≈ ¥15
失败 fallback
- DeepSeek API 挂了:报错,不污染已有 summaries
- key 找不到:报错让 Daisy 手动
export DEEPSEEK_API_KEY=xxx再跑 - search-index.json 不存在:让 Daisy 先跑
python3 /tmp/jsonl2html.py --all /tmp/mirror生成
What ships with it
2 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.
- 10d ago First seen · 67 lines · 85 tokens per session scan A 0a5230e8a0ff
summarize-sessions is a skill published in the GitHub repository daisyyang1109-super/mirror-viewer (5 stars, last pushed 2mo ago), licensed MIT. It adds 85 tokens to every session and 772 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
agents-md-improver
Audit and improve project-rules files (AGENTS.md, CLAUDE.md, .agents/instructions, local overrides) so the agent keeps accurate project context. Use when the user asks to check, audit, review, update, improve, or fix their AGENTS.md or CLAUDE.md, mentions "project rules maintenance" or "agent context optimization", or…
agents-md-revise
Capture learnings from the current session into the project-rules file (AGENTS.md, CLAUDE.md, or local override) so future sessions benefit. Use when the user says "revise the rules", "update AGENTS.md / CLAUDE.md with what we just learned", "save this to project memory", "remember this for next time", or at the end…
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.
egregore
Egregore mechanics as kernel functions — search shared memory, read team activity, create handoffs, save work, branch, and prepare notification plans without re-deriving bin/ CLI usage. Import and call directly; every function wraps the same runtime-neutral bin/ scripts the other harnesses use.
memorywhale
Query and write durable debugging memory recorded by MemoryWhale. Use when debugging a failure that may have happened before, when you need the exact error/flags/output from an earlier attempt, when the user asks "how did we fix this last time?", or once you've figured out why something failed / how a fix worked and…
init
Turn on Rekal memory in the current repository by running rekal init. Use when the user asks to initialize or set up Rekal here, or when a rekal command reported the repository is not initialized. Once per repository. Do not offer this merely because a repo lacks a .rekal/ store — most repos do not want one.