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/masonegger/bpe-claude-code-plugin/wtf-widnpx skills add MasonEgger/bpe-claude-code-plugin --skill wtf-widgit clone --depth 1 https://github.com/MasonEgger/bpe-claude-code-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/masonegger/bpe-claude-code-plugin/wtf-wid)<a href="https://agentmods.dev/skills/masonegger/bpe-claude-code-plugin/wtf-wid"><img src="https://agentmods.dev/badge/skills/masonegger/bpe-claude-code-plugin/wtf-wid.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00032 | $0.01112 |
| Opus 5 | $0.00016 | $0.00556 |
| Sonnet 5 | $0.00006 | $0.00222 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
wtf-wid 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WTF Was I Doing?
Print a tight context-recovery block so the user can re-enter the session without scrolling. The user has stepped away (overnight, days) and needs the current state surfaced fast. No preamble. No closing offer. Just the block.
Hard Output Constraints
- ≤ 30 lines total, including blanks. If over budget, drop optional sections (
Why,Open,Refs) first, then trim theStatusfile list. - ≤ 144 chars per line. Truncate paths, commit subjects, and quoted text with
…. - No prose framing in user-facing text: no "Here's where you were…", no "Hope this helps…", no follow-up questions, no "want me to continue?". Print the block, stop.
Source Priority
The user explicitly cares about the current session, not history. Read sources in this order and privilege the earlier ones:
- Current conversation transcript: your own memory of this session. Primary source. What did the user ask for? What were you doing in the last few turns? What was about to happen next? If the conversation has substantive content, it owns
Problem,Next,Why, andOpen. - Git state: run in parallel via Bash:
git rev-parse --abbrev-ref HEAD(branch)git status --short(modified/staged/untracked counts + paths)git log -1 --format="%h %s"(last commit, subject only)basename "$PWD"(repo dir name)
- bpe artifacts: supporting only when they reflect current intent, not historical work:
.ai-sessions/handoffs/*.md(most recent): if present, its focus is a strong signal forNexttodo.md: first unchecked- [ ]item, only if it matches what's actually in flightplan.md/spec.md: pullWhyif the conversation doesn't already supply it
- MEMORY.md: only if it adds load-bearing project context the conversation doesn't cover.
Do not synthesize a "current session" from .ai-sessions/session-*.md. Those are past sessions. If you must reference one (cold-start fallback only), label it prev: so the user knows it's historical.
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 · 75 lines · 32 tokens per session scan A a8e90bbcf76f
wtf-wid is a skill published in the GitHub repository MasonEgger/bpe-claude-code-plugin (7 stars, last pushed 11d ago), licensed MIT. It adds 32 tokens to every session and 1,112 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 2026-08-31.
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…