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/chucklever/cel-kdev/version-changelognpx skills add chucklever/cel-kdev --skill version-changeloggit clone --depth 1 https://github.com/chucklever/cel-kdevWhat 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 | $0.00207 | $0.01388 |
| Opus 5 | $0.00103 | $0.00694 |
| Sonnet 5 | $0.00041 | $0.00278 |
| Haiku 4.5 | $0.00021 | $0.00139 |
Grade A, and why
version-changelog 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
version-changelog
A reroll carries a changelog: what changed since the previous posting,
newest revision first, as terse bullets. b4 emits it under a Changes in vN: heading, with a Link to v(N-1): bullet beneath.
Patch count decides which message carries the block -- the cover
letter for a multi-patch series, the lone patch when there is only
one -- but it lands below a --- divider either way, so it stays
reviewer-facing and never enters git history. Which message is a
series-send/b4 concern rather than this skill's, and the content
rules below hold for both.
The kernel documentation calls this the "patch changelog"
(submitting-patches.rst), and uses "changelog" alone for the commit
message body that git keeps. This skill governs the first; the second
belongs to cel-prose:commit-message.
Bullet form
Each bullet is a single line of at most 72 columns. When a bullet runs long, tighten the wording or split it into two bullets -- do not let it wrap onto a second line. A line may exceed 72 columns only for an unbreakable token it must carry, such as a URL or a pathname (the "Link to" line is the usual case).
Every block ends with a Link to v(N-1): bullet pointing at the
prior posting, so a reviewer can pull it up and diff against it.
Revisions accumulate, newest first: a v3 posting carries the v3 block above the v2 block, both intact. A reviewer who last read v1 needs the rounds in between.
What earns a bullet
Every delta a reviewer would notice reading the new posting against the old one: a changed patch, an added or dropped patch, a reordering, a renamed identifier in the diff. A reroll that only rebases still earns its bullet: write "Rebase on v6.12-rc1, no functional change" rather than nothing, because a reviewer who sees a new version and no explanation goes looking for the change that is not there.
Ground every bullet in an actual diff of the prior version against
the current series, not in memory of what you meant to change. What
you remember changing and what the diff shows diverge in exactly the
cases a changelog exists to catch: a fix that got rebased away, a
rename that landed in only half the patches. Recover the real delta
with b4 diff <msgid of v(N-1)>, or git range-diff when both
versions are local branches (see cel-kdev:b4), and list what it
shows.
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 · 115 lines · 207 tokens per session scan A b3c24ffa378d
version-changelog is a skill published in the GitHub repository chucklever/cel-kdev (2 stars, last pushed 4d ago), licensed MIT. It adds 207 tokens to every session and 1,388 once invoked, about $0.0010 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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.