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/lexfrei/ccc/lorenpx skills add lexfrei/ccc --skill loregit clone --depth 1 https://github.com/lexfrei/cccWhat 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 | $0.00109 | $0.01062 |
| Opus 5 | $0.00055 | $0.00531 |
| Sonnet 5 | $0.00022 | $0.00212 |
| Haiku 4.5 | $0.00011 | $0.00106 |
Grade A, and why
lore scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
lore.kernel.org is the public-inbox archive of the kernel lists. Everything below works with plain curl, no subscription and no local mail setup, but the archive sits behind bot protection that keys on the User-Agent. How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
lore.kernel.org is the public-inbox archive of the kernel lists. Everything below works with plain curl, no subscription and no local mail setup, but the archive sits behind bot protection that keys on the User-Agent.
User-Agent: the one thing that breaks everything
Default curl gets HTTP 403; browser-style agents (Mozilla/5.0 ...) get an Anubis JavaScript challenge page instead of content. Send --user-agent "lei/1.0" on every request — it works for mbox, atom, and search endpoints alike.
If a response starts with <!doctype html> and mentions "not a bot", you hit the challenge: fix the User-Agent, do not try to solve or bypass the challenge.
Fetch a whole thread
curl --silent --user-agent "lei/1.0" "https://lore.kernel.org/<list>/<message-id>/t.mbox.gz" | gunzip
<message-id> is bare, without angle brackets. Any message's ID pulls its entire thread — cover letter, patches, and every reply. This mbox is the source of truth for reply headers: take Message-ID:, From:, Cc:, and exact Subject: values from it, never reconstruct them from memory.
The list name in the URL scopes the archive (netdev, linux-kernel, linux-mm, ...); when the list is unknown, https://lore.kernel.org/all/<message-id>/ resolves from the cross-list index and https://lore.kernel.org/r/<message-id>/ is the canonical short form for citing a message in changelogs and Link: tags.
If the b4 tool is installed, b4 mbox <message-id> does the same fetch with retries; the curl form needs no tooling.
Check for new replies without refetching
curl --silent --user-agent "lei/1.0" "https://lore.kernel.org/<list>/<message-id>/t.atom" | grep -oE "<name>[^<]+</name>|<updated>[^<]+</updated>"
Read it as author/timestamp pairs. A new author entry with a fresh timestamp is a new message — fetch the mbox. A bumped <updated> with the same set of authors is lore reindexing the thread, not new mail; do not report it as a reply.
Search
curl --silent --user-agent "lei/1.0" "https://lore.kernel.org/<list>/?q=<url-encoded-query>&x=A"
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 · 61 lines · 109 tokens per session scan A 15033c144fb8
lore is a skill published in the GitHub repository lexfrei/ccc (9 stars, last pushed 2d ago), licensed BSD-3-Clause. It adds 109 tokens to every session and 1,062 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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…