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/b4npx skills add chucklever/cel-kdev --skill b4git 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 | $0.00099 | $0.03323 |
| Opus 5 | $0.00049 | $0.01662 |
| Sonnet 5 | $0.00020 | $0.00665 |
| Haiku 4.5 | $0.00010 | $0.00332 |
Grade A, and why
b4 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 yesterday.
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 — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
b4 for kernel patch workflows
CRITICAL: stg interaction hazards
These b4 operations corrupt the stg stack. Never use them when stg is active on the branch.
| Prohibited | Why | Replacement |
|---|---|---|
b4 am <msgid> |
Runs git am, which moves HEAD behind stg's back |
b4 am -l -o /tmp/series.mbx <msgid> then stg import -M /tmp/series.mbx; a maintainer intake adds a step between the two (see "Applying patches from lore") |
b4 trailers -u |
Rebases commits to insert collected tags, breaking stg metadata | Avoid; run stg repair immediately after if unavoidable |
Check whether stg is active before choosing a command path. See the stg skill for the two-step activation check.
What b4 sees
b4 discovers the series as commits between the enrolled fork-point and HEAD:
fork-point (e.g., origin/master)
|
+ patch-a <- applied stg patch, visible to b4
+ patch-b <- applied stg patch, visible to b4
> patch-c <- HEAD, visible to b4
- patch-d <- unapplied, in refs/stacks/ only
- patch-e <- unapplied, NOT visible to b4
=> stg push -a before b4 send
Unapplied patches exist only in stg metadata and are
invisible to b4. Apply all patches with stg push -a
before running b4 send or b4 prep --format-patch.
Applying patches from lore
| Task | Command |
|---|---|
| Apply a series by message-id | b4 am <msgid> |
| Apply a series, write mbox only | b4 am -o <dir> <msgid> |
| Apply as stg patches | b4 am -l -o /tmp/series.mbx <msgid> then stg import -M /tmp/series.mbx |
| Cherry-pick specific patches (1-indexed, comma-separated, ranges ok) | b4 am -P 1-2,4 <msgid> |
| Show series diff between versions | b4 diff <msgid> |
| Retrieve thread as mbox | b4 mbox <msgid> |
The stg-import row is two steps, but a maintainer intake interposes a third between them. Read "The maintainer intake edit" below before importing.
<msgid> can be a Message-Id, a lore URL, or a lore
search query.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 314 lines · 99 tokens per session scan A b82738574103
b4 is a skill published in the GitHub repository chucklever/cel-kdev (2 stars, last pushed 4d ago), licensed MIT. It adds 99 tokens to every session and 3,323 once invoked, about $0.0005 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…