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/terry-mao/aicodingflow/pr-walkthroughnpx skills add Terry-Mao/AICodingFlow --skill pr-walkthroughgit clone --depth 1 https://github.com/Terry-Mao/AICodingFlowWhat 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 | $0.00053 | $0.03227 |
| Opus 5 | $0.00026 | $0.01614 |
| Sonnet 5 | $0.00011 | $0.00645 |
| Haiku 4.5 | $0.00005 | $0.00323 |
Grade A, and why
pr-walkthrough 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 3d 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pr-walkthrough
为当前分支或 GitHub PR 生成一个本地静态 HTML 讲解页,帮助 reviewer 快速理解 PR 涉及的系统、数据流、代码依赖和用户路径。此技能不是代码评审技能,不生成新的 review finding、approval 或 request-changes 结论。
输出
生成文件到临时目录下的统一 slug 目录。默认本地产物根目录为 ${TMPDIR:-/tmp}/pr-walkthrough(并去掉末尾 /);如果用户明确指定其他目录,可改用指定目录。
优先使用 PR number;无 PR number 时使用当前分支名:
$output_dir/graph.json
$output_dir/index.html
<short-sha> 是生成 walkthrough 时的 head commit 短 SHA。<sanitized-branch> 使用小写字母、数字和 -,把 /、空格和其他分隔符归一为 -。本地目录名和 GitHub Pages 路径必须使用同一个 slug。PR 更新后再次调用会因 short SHA 变化生成新目录;只有用户明确要求更新同一路径时才覆盖旧目录。不要把生成产物写入仓库目录,除非用户明确要求。
站点必须可以直接用 file:// 打开,不要求 dev server、打包器、安装依赖或构建步骤。优先生成单个自包含 HTML 文件,内联 CSS、JavaScript 和图数据;如果必须拆分资源,只使用相对路径,并避免用 fetch() 读取本地数据。
D3 使用固定版本的官方 CDN:
https://cdn.jsdelivr.net/npm/[email protected]/dist/d3.min.js
优先使用本技能自带脚本生成和验证页面:
python3 .agents/skills/pr-walkthrough/scripts/d3_canvas_runtime.py --template --data "$graph_json" > "$index_html"
python3 .agents/skills/pr-walkthrough/scripts/validate_d3_canvas.py --html "$index_html" --require-browser
视觉风格
不要套用任何公司视觉规范、专属字体、专属色或外部视觉规范技能。使用脚本内置的中性文档/工具界面样式即可。可以为四个视图使用不同的功能色,但颜色只表达信息类型,不表达品牌。
推荐视图颜色:
- System overview view:
#b7791f - Data flow graph:
#0f7b5f - Code dependency graph:
#2563eb - User action graph:
#7c3aed - Active/focus/selected node:
#2563eb
工作流
1. 建立 PR 上下文
识别仓库根目录、当前分支和比较 base。若用户 Prompt 明确给出 PR number、#<number> 或 PR URL,先把该编号记录为 pr_number。否则从当前分支的 GitHub PR 获取 pr_number,并优先使用 PR base、记录 PR URL 生成 diff links:
pr_number="${pr_number:-}" # 用户 Prompt 已明确给出 PR 编号时,先由执行者设置这个变量。
if [ -z "$pr_number" ]; then
pr_number="$(gh pr view --json number --jq '.number // empty' 2>/dev/null || true)"
fi
if [ -n "$pr_number" ]; then
gh pr view "$pr_number" --json number,baseRefName,headRefName,title,body,url,state,reviewRequests,reviews,files
else
gh pr view --json number,baseRefName,headRefName,title,body,url,state,reviewRequests,reviews,files
fi
若没有 PR,从远端默认分支或仓库约定推断 base:
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.
- 3d ago First seen · 290 lines · 53 tokens per session scan A 9d64edabcc6e
pr-walkthrough is a skill published in the GitHub repository Terry-Mao/AICodingFlow (165 stars, last pushed 5d ago), licensed MIT. It adds 53 tokens to every session and 3,227 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…