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/ryanb/dotfiles/walkthroughnpx skills add ryanb/dotfiles --skill walkthroughgit clone --depth 1 https://github.com/ryanb/dotfilesWhat 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 | $0.00057 | $0.00791 |
| Opus 5 | $0.00028 | $0.00396 |
| Sonnet 5 | $0.00011 | $0.00158 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
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 yesterday.
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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Walkthrough
Generate a walkthrough of the current branch's changes, organized from the user's perspective.
Step 1: Get the diff
Determine the base branch in this order:
- Use
$ARGUMENTSif the user specifies a branch - Use the tracked parent from
git config branch.$(git branch --show-current).parent, if set and it still resolves to a commit - Use
bin/base-branchif the script exists and is executable - Fall back to
develop
git diff origin/<base-branch>...HEAD --stat
git diff origin/<base-branch>...HEAD -- <non-test files>
Exclude test files, spec files, and doc files from the diff. Focus only on implementation.
Step 2: Identify user-facing entry points
Entry points are the highest-level changes to the existing system — the places where the diff first touches code that was already there. Trace from these points downward.
Look for:
- New or changed UI components, buttons, forms, modals, pages
- New routes or changed routes
- Changes to Liquid templates, translations
- New action handlers or event registrations
A component that hasn't changed in the diff is never an entry point, even if it renders the result of changed code. The entry point is the changed code that feeds it.
Step 3: Write the walkthrough
Organize the output as user flows, not by file or layer. Each flow starts with what the user sees and traces downward through the code.
Structure for each flow
-
Start with the UI change — what does the user see? A new button, a changed form, a new page? Describe the visible change and reference the file + line.
-
Trace what happens on interaction — when the user clicks/submits, what code runs? Follow the chain: event handler → action/service → API call → controller → model. Show each hop as a step.
-
At each step, only highlight:
- New behavior or changed behavior (not just moved code)
- Complex logic (conditionals, amount calculations, state management)
- Side effects (jobs enqueued, orders finalized, state mutations)
- Where data flows between systems (POS → server, server → gateway → redirect back)
What ships with it
1 file 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.
- yesterday First seen · 72 lines · 57 tokens per session scan A d6f663e26487
walkthrough is a skill published in the GitHub repository ryanb/dotfiles (2,399 stars, last pushed 12d ago), licensed MIT. It adds 57 tokens to every session and 791 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
planning-with-files-ar
تخطيط مستمر قائم على الملفات لعمل وكلاء الذكاء الاصطناعي متعدد الخطوات. يحتفظ بملفات taskplan.md و findings.md و progress.md على القرص، وتحقن خطافات دورة الحياة سياق التخطيط المحدد للمشروع. تقرأ الاستعادة التلقائية ملفات تخطيط المشروع فقط. يمكن للأمر الصريح session-catchup.py --metadata فحص بيانات وصفية لجلسات الوكيل…
kl-consistency-test
Write, calibrate, and debug the prefill-vs-decode logprob (KL) consistency tests in sglang -- the two independent conditions a zero requires (every operator batch-invariant, and the two paths computing the same function), which helper separates them, how to pick a threshold once they hold, and how to localize a…
i18n-localization
Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.
dsh-web-documentation
Use when adding or editing dsh-web README files, docs, AGENTS.md instructions, user-facing configuration text, or bilingual documentation pairs.
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…
indication-dossier
Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.