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/jackfranklin/dotfiles/code-walkthroughnpx skills add jackfranklin/dotfiles --skill code-walkthroughgit clone --depth 1 https://github.com/jackfranklin/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 | $0.00033 | $0.00554 |
| Opus 5 | $0.00016 | $0.00277 |
| Sonnet 5 | $0.00007 | $0.00111 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
code-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 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Walkthrough
Use this skill when the developer wants to review and understand a set of code changes (either a draft diff in the workspace or a recently committed change) step-by-step.
The goal is to explain the "why" and "how" of the changes progressively, giving the developer space to ask questions or suggest modifications for each part before moving on.
Steps
1. Identify the Changes
Locate the diff to walk through:
- For uncommitted changes: use
git diff HEAD(or similar). - For a recent commit: use
git show <commit-hash>orgit diff HEAD~1 HEAD. - If the changes are already discussed in the context, use the context.
- If you are unsure, ask the user for confirmation.
2. Group into Logical Steps
Group the changes into logical steps to avoid overwhelming the developer.
- Group by file or by logical feature if changes are spread across files. Think about presenting the steps in chronological order to represent how the feature/fix was built out.
- Keep track of the current step index (e.g., "Step 1 of 3").
3. Progressive Walkthrough
For each logical group of changes:
- Present the Change:
- State the file path and what part of the code is changing.
- Show the relevant diff snippet or code block.
- Explain the Logic:
- Explain why this change was made (the bug it fixes or the feature it implements).
- Explain how it works (the mechanism of the change).
- Keep the explanation concise and direct (adhere to "No Bullshit" guidelines).
- Pause for Questions:
- Ask the developer if they have any questions or if they are ready to move to the next step.
- End your turn and wait for the developer's response.
4. Handle Feedback
- If the developer has questions:
- Answer them directly and clearly.
- Wait for their confirmation before moving on.
- If the developer suggests changes:
- Discuss the changes and implement them if agreed.
- Re-explain the updated change and ask for approval again.
- If the developer says they are ready:
- Proceed to the next step.
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 · 63 lines · 33 tokens per session scan A b87b4d0c4582
code-walkthrough is a skill published in the GitHub repository jackfranklin/dotfiles (254 stars, last pushed 9d ago), licensed MIT. It adds 33 tokens to every session and 554 once invoked, about $0.0002 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…