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/okwinds/miscellany/codeflow-analyzernpx skills add okwinds/miscellany --skill codeflow-analyzergit clone --depth 1 https://github.com/okwinds/miscellanyWhat 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 | $0.00109 | $0.01144 |
| Opus 5 | $0.00055 | $0.00572 |
| Sonnet 5 | $0.00022 | $0.00229 |
| Haiku 4.5 | $0.00011 | $0.00114 |
Grade A, and why
codeflow-analyzer 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 2d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Flow Analyzer
Systematically trace the complete call chain of any feature or process in a codebase, from entry point to the deepest dependency, and produce a structured analysis document.
When This Skill Applies
- "这个功能的调用链是怎样的？"
- "Trace the request flow from X to Y"
- "How does feature Z work under the hood?"
- "Map the data flow of this process"
- "I want to understand the full path from user input to final output"
- Any question about how layers connect: frontend → API → service → domain → storage
Core Approach: Layer-by-Layer Tracing
Real-world codebases are layered. Each layer has its own conventions for entry points, routing, and delegation. Instead of guessing the architecture, discover it empirically by following the actual code paths.
Phase 1: Identify Entry Point
Start from the user-facing trigger:
- Find the surface-level entry — UI component, CLI command, API endpoint, message handler, cron trigger, etc.
- Identify what it calls — the first cross-boundary call (HTTP request, function import, message publish, RPC call).
Techniques:
- Grep for keywords from the user's description (feature name, button label, route path, event name)
- Glob for files matching the feature name pattern
- Read the entry file to find outbound calls
Phase 2: Trace Through Each Layer
For each layer discovered, answer three questions:
- How does this layer receive the call? (route handler, message consumer, function signature)
- What does this layer do with it? (validation, transformation, delegation, side effects)
- Where does it hand off next? (outbound call, return value, event emission)
Repeat until you reach a terminal point (database write, external API call, file output, response return).
Parallel exploration strategy: When entering a new layer, launch multiple searches in parallel:
- Grep for the function/class/route name being called
- Glob for files matching the module/package name
- Read configuration files that might define routing or wiring
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.
- 2d ago First seen · 129 lines · 109 tokens per session scan A 4c9d145412ae
codeflow-analyzer is a skill published in the GitHub repository okwinds/miscellany (50 stars, last pushed 3mo ago), licensed MIT. It adds 109 tokens to every session and 1,144 once invoked, about $0.0005 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…