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/jack-referencesnpx skills add jackfranklin/dotfiles --skill jack-referencesgit 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 | $0.00112 | $0.01125 |
| Opus 5 | $0.00056 | $0.00562 |
| Sonnet 5 | $0.00022 | $0.00225 |
| Haiku 4.5 | $0.00011 | $0.00112 |
Grade A, and why
jack-references 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jack References
Personal technical reference library at ~/git/references. Each file is a focused Markdown cheatsheet for a library, API, or tool.
Shared Setup: Resolve Repo Path
First, resolve the absolute path to the references repo:
echo $HOME/git/references
Use the output of this command (e.g. /home/jack/git/references) as the literal path for all subsequent commands in this skill. Never use $HOME again after this step — always substitute the resolved absolute path.
Shared Setup: Clone/Pull
Check if the repo exists:
ls $HOME/git/references/.git 2>/dev/null && echo "exists" || echo "missing"
If missing: clone it:
mkdir -p $HOME/git
gh repo clone jackfranklin/references $HOME/git/references
If it exists: fetch and check if a pull is needed:
git -C $HOME/git/references fetch origin main --quiet
git -C $HOME/git/references rev-parse HEAD
git -C $HOME/git/references rev-parse origin/main
If the hashes differ, pull:
git -C $HOME/git/references pull --ff-only origin main
If they match, skip the pull.
Searching and Reading References
Parse search terms
The user provided: $ARGUMENTS
Split into individual search terms. If $ARGUMENTS is empty, infer relevant keywords from the current task or conversation context (e.g. the library, API, or technology being discussed).
Search for matching files
Run two searches and deduplicate.
Search A — filename match:
ls $HOME/git/references/*.md 2>/dev/null
A file matches if any search term appears in its name after treating hyphens as word separators. For example, "speech" matches browser-speech-to-text.md; "genai" matches google-genai.md.
Search B — content grep (case-insensitive, filenames only):
For each search term:
grep -ril "TERM" $HOME/git/references/
Combine results from A and B, removing duplicates. Keep only .md files.
If more than 4 files matched, prefer files that matched on both filename and content, then filename-only, then content-only. Read the top 4.
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 · 159 lines · 112 tokens per session scan A 922a1802f16f
jack-references is a skill published in the GitHub repository jackfranklin/dotfiles (254 stars, last pushed 10d ago), licensed MIT. It adds 112 tokens to every session and 1,125 once invoked, about $0.0006 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…