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/lessonsnpx skills add MasonEgger/bpe-claude-code-plugin --skill lessonsgit clone --depth 1 https://github.com/MasonEgger/bpe-claude-code-pluginWhat 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 | $0.00020 | $0.01180 |
| Opus 5 | $0.00010 | $0.00590 |
| Sonnet 5 | $0.00004 | $0.00236 |
| Haiku 4.5 | $0.00002 | $0.00118 |
Grade A, and why
lessons 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lessons Command
View and manage accumulated lessons from .ai-sessions/lessons.md.
Behavior
-
Read
.ai-sessions/lessons.md- If the file does not exist, inform the user: "No lessons file found. Run
/bpe:session-summaryat the end of a session to start capturing lessons." - If the file exists, proceed based on arguments.
- If the file does not exist, inform the user: "No lessons file found. Run
-
No arguments (
/bpe:lessons): Display the full## Recentsection and list available categories with their lesson counts. -
With search term (
/bpe:lessons $ARGUMENTS): Search the entire lessons.md for entries matching the argument. Display matching lessons grouped by category. If no matches, say so. -
Special arguments:
-
recent- Show the Recent section (default if no args) -
all- Display the entire lessons.md file -
categories- List just the category headings with counts -
prune- Review lessons.md for duplicates, outdated entries, or lessons that have already been incorporated elsewhere. Check all of the following for existing coverage:- The project's
CLAUDE.md - All global rule files in
~/.claude/rules/*.md ~/.claude/CLAUDE.md
For each lesson that is already covered, note where it exists. Present findings to the user grouped by status:
## Already incorporated - [lesson]: covered in ~/.claude/rules/python.md - [lesson]: covered in project CLAUDE.md ## Duplicates - [lesson]: duplicate of [other lesson] in lessons.md ## Outdated - [lesson]: reason it appears outdatedAsk the user to confirm before making changes. Pruned lessons are NOT deleted; they are moved to
.ai-sessions/lessons-pruned.mdwith a record of what happened to each one:## Pruned <date> - [lesson]: promoted to ~/.claude/rules/python.md - [lesson]: duplicate of [other lesson] - [lesson]: outdated: [reason]Append to the file if it already exists. Then remove the pruned lessons from lessons.md.
- The project's
-
promote- Identify lessons that appear broadly applicable or have been validated across multiple sessions. For each promotable lesson, classify its destination:
-
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 · 88 lines · 20 tokens per session scan A e1d2244f2f31
lessons is a skill published in the GitHub repository MasonEgger/bpe-claude-code-plugin (7 stars, last pushed 10d ago), licensed MIT. It adds 20 tokens to every session and 1,180 once invoked, about $0.0001 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…