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
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/alibaba/anolisanpx agentmods add skills/alibaba/anolisa/agentsight-pr-bodyWrote 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-pr-body)<a href="https://agentmods.dev/skills/alibaba/anolisa/agentsight-pr-body"><img src="https://agentmods.dev/badge/skills/alibaba/anolisa/agentsight-pr-body.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.03068 |
| Opus 5 | $0.00034 | $0.01534 |
| Sonnet 5 | $0.00014 | $0.00614 |
| Haiku 4.5 | $0.00007 | $0.00307 |
Grade A, and why
pr-body 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 8d 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Body 生成器
目标
分析当前分支相对于 main 的全部变更(所有 commit,不仅是最新一条),生成或更新符合 alibaba/anolisa 规范的 PR 标题和正文。
触发时自动执行
步骤 1:收集变更信息
# 当前分支
git branch --show-current
# 全部 commit(从 main 分叉点起)
git log --oneline origin/main..HEAD
# 变更文件列表
git diff --stat origin/main..HEAD
# 完整 diff(用于分析变更内容)
git diff origin/main..HEAD
# 是否已有 PR
gh pr list --head $(git branch --show-current) --repo alibaba/anolisa --state open --json number,title,body
步骤 1.5:Code Review 自检
在生成 PR 描述前,先执行 agentsight-code-review skill 对当前变更进行自检。如果存在 findings,先修复再继续。
步骤 1.6:Preflight 检查(与 CI 门禁逐项对齐)
在分析变更前,运行以下检查并记录结果(后续自动填入 Checklist)。这些检查
镜像 test-agentsight CI job,目的是在 push 前本地拦截会导致 CI 失败的问题
(一次 push + CI ≈ 4 分钟,本地检查 ≈ 30 秒)。
# 在 agentsight 目录下执行(CI 锁定 toolchain 1.89.0;缺则先
# `rustup toolchain install 1.89.0 --component rustfmt --component clippy --component llvm-tools-preview`)
cargo +1.89.0 fmt --all --check # 1. 格式
cargo +1.89.0 clippy --all-targets -- -D warnings # 2. lint
python3 scripts/check-arch-boundaries.py # 3. 架构边界
# 4. 测试 + 覆盖率(CI 用 llvm-cov 跑测试,不是 cargo test;用默认 toolchain 即可——
# 覆盖率行映射与工具链版本无关,且 +1.89.0 需该工具链装 llvm-tools-preview,
# dev 机常装在 stable 上。fmt/clippy 上面 pin +1.89.0 是因为 lint 规则版本敏感)
cargo llvm-cov --cobertura --output-path coverage.xml \
--ignore-filename-regex '(\.skel\.rs|target/debug/build|target/release/build|src/probes/)'
# 5. 增量覆盖率门禁(与 CI 一致:对比 origin/main,阈值 80%)
git fetch origin main
diff-cover coverage.xml --compare-branch=origin/main --fail-under=80
- 五项全部通过才继续;任一失败按下面处理后重跑。
cargo fmt --check失败 → 跑cargo +1.89.0 fmt修复后重新检查。cargo clippy失败 → 列出告警、修复、重新检查。- 架构边界失败 → 按
check-arch-boundaries.py的提示修正跨层依赖。 - 覆盖率门禁失败(增量 < 80%)→ 停止,为新增/修改但未覆盖的行补测试 (diff-cover 输出会列出每个文件的 Missing lines);不要靠降阈值绕过。
diff-cover/cargo-llvm-cov未安装 → 安装后再验(pip install diff-cover;rustup component add llvm-tools-preview),不要跳过本步却标记"已通过"。
6. Commit message 规范检查:对 git log origin/main..HEAD 的每个 commit
逐条核对是否符合 conventional commit(commitlint 是独立的硬门禁,其中 scope 必填
是最容易漏的硬失败;fmt/clippy/覆盖率同样是硬门禁):
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.
- 8d ago First seen · 265 lines · 68 tokens per session scan A 644664ea35b0
pr-body is a skill published in the GitHub repository alibaba/anolisa (619 stars, last pushed today), licensed Apache-2.0. It adds 68 tokens to every session and 3,068 once invoked, about $0.0003 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
pr-submission
PR title format, commit conventions, and pre-PR checklist for SkillHub. Use when preparing or reviewing pull requests.
github
GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available)…
review-pr
Review a pull request (GitHub) or merge request (GitLab) and provide detailed feedback.
beevibe-pre-task-setup
Cold-start git workspace setup for a fresh beevibe task. Use at the start of a session whose intent has a block but NO or block — i.e. the first dispatch of this task. Checks for an existing repo clone, pulls the base branch if present (clone if missing), prunes any per-task worktrees from earlier tasks whose work has…
ghx
Guidance for safe, reliable GitHub CLI workflows across issues, pull requests, and reviews.
github-pr-fix
Fix a GitHub pull request by addressing feedback or CI failures, pushing changes, and publishing replies.