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/plan-walkthroughnpx skills add jackfranklin/dotfiles --skill plan-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 | $0.00044 | $0.00739 |
| Opus 5 | $0.00022 | $0.00369 |
| Sonnet 5 | $0.00009 | $0.00148 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
plan-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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Walkthrough
Use this skill when the developer wants to review a proposed implementation plan (either saved as a GitHub Issue or draft plan in the current conversation context) step-by-step before beginning execution.
The goal is to explain the rationale, trade-offs, and critical decisions of the plan to the developer progressively, rather than presenting the entire plan to read in one go.
Steps
1. Locate the Plan
Identify the plan to walk through:
- If a plan is already saved as a GitHub Issue, fetch it:
gh issue view <number> --json title,body. - If a plan is only present in the current conversation context (e.g. drafted in previous messages), use the draft plan.
- If you are unclear which plan to use, do not assume. Ask for clarification.
2. Prepare the Walkthrough State
Identify all the individual steps/tasks in the plan.
- Keep track of the current step index (e.g., "Step 1 of 5").
- Maintain a list of any changes or feedback requested by the developer during the walkthrough.
3. Progressive Step Walkthrough
For each step in the plan:
-
Present the Step details:
- Step/Task title, target files to create/modify/test.
- A brief summary of what this step implements.
-
Explain the Rationale (Dynamic & Adaptive):
- Explain why you chose this approach. What is the core design decision?
- Alternatives Considered: If there were non-trivial alternative approaches, explain what they were and why they were rejected. (Skip if trivial).
- Risks/Assumptions: Identify any potential issues, dependencies, or assumptions that need verification. (Skip if none).
- Keep the explanation concise and focused, avoiding conversational fluff.
-
Pause for Feedback:
- Ask the developer if they approve this step or if they have any questions or feedback.
- End your turn and wait for the developer's response.
4. Handle Feedback & Updates
- If the developer asks questions or has concerns:
- Address their questions directly.
- If they suggest changes to the step, discuss the impact of those changes.
- Once changes are agreed upon, update your internal draft of the plan.
- Re-explain the updated step (if necessary) and ask for approval again.
- If the developer approves:
- 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.
- 3d ago First seen · 68 lines · 44 tokens per session scan A 36a857548da8
plan-walkthrough is a skill published in the GitHub repository jackfranklin/dotfiles (254 stars, last pushed 10d ago), licensed MIT. It adds 44 tokens to every session and 739 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.
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…