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/laternpx skills add jackfranklin/dotfiles --skill latergit 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 | $0.00046 | $0.00707 |
| Opus 5 | $0.00023 | $0.00353 |
| Sonnet 5 | $0.00009 | $0.00141 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
later 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use gh to manage backlog items as GitHub Issues in the current repo.
GitHub body safety — mandatory
Never pass issue Markdown through a shell-quoted --body argument. Markdown commonly contains backticks, $, or command examples; in double-quoted Bash strings those can execute shell command substitution and leak their output into GitHub.
- Always write issue bodies to a temporary file outside the repository with the file-writing tool, then use
gh ... --body-file /tmp/<descriptive>.md. - Never use
--body "...",--body "$(...)", backticks inside shell strings, or an unquoted heredoc for issue content. - If a shell heredoc is unavoidable, its delimiter must be single-quoted:
<<'EOF'. - After publishing Markdown, verify the stored body is literal Markdown. If it contains shell output or credentials, immediately delete or replace the comment, stop work, and tell the user to rotate exposed credentials.
Before anything else
Verify there is a GitHub remote: gh repo view --json nameWithOwner. If it fails, stop and tell the user there is no GitHub remote — they need to be in a GitHub-backed repo to use this skill.
Logging an item
Write /tmp/<repository>-issue-<slug>.md with the file-writing tool, then run:
gh issue create --title "<title>" --body-file /tmp/<repository>-issue-<slug>.md
Add labels if helpful (e.g. --label bug), but don't create labels that don't exist yet — only use labels already present in the repo.
Before creating, run gh issue list --search "<title>" to check for duplicates. If a near-match exists, show it to the user and ask whether to update that issue or create a new one.
Listing open items
gh issue list --state open
Viewing an item
gh issue view <number>
Never jump straight into implementation after reading an issue. After gh issue view, always: summarise the issue in your own words, investigate the relevant code enough to explain why it happens (root cause, not just symptoms), then present your thoughts — options, tradeoffs, a recommendation if you have one — and ask the user how they'd like to proceed. Only start editing code once the user has confirmed a direction. This applies even if the fix looks small or obvious.
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 · 64 lines · 46 tokens per session scan A fe2b86760f7e
later is a skill published in the GitHub repository jackfranklin/dotfiles (254 stars, last pushed 10d ago), licensed MIT. It adds 46 tokens to every session and 707 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…