ANOLISA is a server-side operating layer for AI agent workloads that provides terminal access, token-saving tool-output compression, runtime controls, security, observability, skills, memory, and sandbox management. It is for running and supervising agents from a Linux terminal while retaining an existing shell, agent framework, and sandbox. The catalogue add-ons are components of its agent operating environment and workflows.
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 alibaba/anolisa --skill agentsight-bugfixgit clone --depth 1 https://github.com/alibaba/anolisaWrote 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/alibaba/anolisa/agentsight-bugfix)<a href="https://agentmods.dev/skills/alibaba/anolisa/agentsight-bugfix"><img src="https://agentmods.dev/badge/skills/alibaba/anolisa/agentsight-bugfix/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/alibaba/anolisa/agentsight-bugfix"><img src="https://agentmods.dev/badge/skills/alibaba/anolisa/agentsight-bugfix.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 | $0.00067 | $0.01253 |
| Opus 5.5 | $0.00027 | $0.00501 |
| Sonnet 5.5 | $0.00013 | $0.00251 |
| Haiku 4.5 | $0.00007 | $0.00125 |
Grade A, and why
agentsight-bugfix 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 1mo 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentSight Fix Issues 流程
目标
在接到 AgentSight 的 Bug 修复任务时，严格按以下五个阶段执行，确保每轮迭代最小化改动、最大化验证。
了解问题 → 复现验证 → 根因分析 → 编码修复 → 验证修复
阶段 1：了解问题
目标：明确 Bug 的实际表现、预期行为和影响范围，在动手之前先想清楚。
- 阅读 issue 描述或 Bug 报告，提取关键信息：
- 实际表现：当前系统做了什么？（错误数据、缺失字段、异常行为等）
- 预期行为：系统应该做什么？
- 触发条件：什么场景下出现？（特定 Agent、特定 API、特定协议等）
- 影响范围：哪些数据/功能受影响？
- 定位相关代码模块，理解当前数据流路径（参考
docs/ARCHITECTURE.md流水线：Probes → Parser → Aggregator → Analyzer → GenAI → Storage） - 不要在这个阶段下结论或开始写代码，信息不充分时的判断大概率是错的
阶段产出：四要素摘要（实际表现、预期行为、触发条件、影响范围）。
阶段 2：复现验证
目标：在实际环境中从零运行一次完整流程，亲眼看到 Bug 发生。
硬性要求：
- 必须在实际环境中运行 agentsight trace，不要只看已有数据或旧 DB 就下结论
- 必须从零开始：停掉旧进程 → 清理旧数据 → 启动 trace（开启 debug 日志）→ 触发目标场景 → 查询 DB 确认 Bug 存在
- 收集 debug 日志，用于阶段 3 分析
阶段产出：实际观察到的现象（DB 数据、日志关键行），与阶段 1 的预期做对比。
阶段 3：根因分析
目标：基于阶段 2 收集的日志和数据，定位数据流在哪个环节断了。
原则：
- 先看日志证据，定位数据流断点，不要只凭代码推测
- 重点关注事件处理顺序（时序问题），agentsight 事件循环是串行的
- 验证旧代码的实际行为是否和预期一致（如 parsed_message 是否为 None、mapper 是否命中）
常见断点检查清单：
| 检查项 | 日志关键词 | 说明 |
|---|---|---|
| AggregatedResult 类型 | Analyzing aggregated result |
是 SseComplete 还是 Http2StreamComplete？ |
| ParsedApiMessage 是否生成 | Parsed OpenAI response |
没有 = analyzer 没产出 Message |
| response_id 是否提取 | chatcmpl- |
从 SSE body 或 parsed message |
| mapper 是否命中 | ResponseSessionMapper |
FileWrite 时序是否先于 LLM 事件 |
| PendingGenAI 是否入队 | queued for deferred |
没入队 = pending_response_id 为 None |
| complete_pending 是否更新 | Promoted pending→complete |
UPDATE 是否包含 session_id |
阶段产出：明确指出数据流在哪个环节断了，以及断裂的原因。
阶段 4：编码修复
目标：针对阶段 3 定位的断点，做最小范围的代码修改。
原则：
- 只改解决该问题所需的部分，无关改动不要顺手一起改
- 修复可能涉及多个断点时，每轮只修一个
提交前必须通过本地检查：
cargo fmtcargo clippy --all-targets -- -D warningscargo test
阶段 5：验证修复
目标：构建新版本并部署到运行环境，从零验证修复有效。
- 构建 release 版本
- 部署到运行环境（本地直接使用，远程环境需上传部署）
- 按阶段 2 的流程完整走一遍：清 DB → trace → 触发请求 → 查 DB，确认修复有效
验证结果处理
| 结果 | 动作 |
|---|---|
| Bug 已修复，无副作用 | 进入完成确认 |
| Bug 部分修复 | 回到阶段 3，分析剩余断点 |
| Bug 未修复或出现新问题 | 回到阶段 3 重新分析，不要在同一轮叠加更多修改 |
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.
- 1mo ago First seen · 105 lines · 67 tokens per session scan A f283fe52d0bd
agentsight-bugfix is a skill published in the GitHub repository alibaba/anolisa (603 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 67 tokens to every session and 1,253 once invoked, about $0.0003 per session on Opus 5.5. 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
investigate-sentry-issue
Investigate and triage a Sentry error issue.
apps
Build and iterate on schema-backed Swarm Apps with live models, named queries, custom actions, and json-render interfaces using the app-upsert, app-get, app-list, and app-patch tools.
kapso-whatsapp
How to interact with Kapso WhatsApp from the swarm — read inbound webhook payloads (text AND media), fetch message history, send free-form messages within the 24h session window (and template messages outside it), mark-as-read, show the typing indicator, send reactions, download media, verify webhook signatures, and…
swarm-scripts
Bulk, repeat, fan-out, or data-heavy work: write and run swarm scripts (inline script-run, named script-upsert, durable launch-script-run). Covers the script-vs-tool rubric, the authoring contract (args first, ctx second), the seed catalog, connections and secrets, dbquery, and exposing a script as an API.
composio
Use Composio from Agent Swarm through the agent-swarm x composio CLI route, the swarmx MCP tool, or a registered ctx.api.composio script connection. Trigger when a task needs connected third-party app tools such as Gmail, Google Calendar, Google Docs, Google Drive, GitHub, Slack, Notion, or HubSpot through Tool Router…
motion-design-video-analysis
Reverse-engineer a short motion-design / product-update video (animation technique, timing and easing, composition, transitions, likely tooling, vibe, audio) and produce a rebuild spec someone can build from. Default path is one call to google/gemini-3.8-flash over sampled frames, then a mandatory by-eye check of…