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/stgnpx skills add chucklever/cel-kdev --skill stggit 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 | $0.00063 | $0.12398 |
| Opus 5 | $0.00032 | $0.06199 |
| Sonnet 5 | $0.00013 | $0.02480 |
| Haiku 4.5 | $0.00006 | $0.01240 |
Grade A, and why
stg 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 — 1,017 lines — stays where its author put it; the contents beside it link to each section on GitHub.
stg: patch stack management
When stg is active on a branch, use stg commands instead of raw git for all commit operations. Check activation in two steps so each command stays simple and avoids unnecessary permission prompts:
git branch --show-current— get the branch namegit show-ref --verify refs/stacks/<branch>— check for the stg stack ref
A zero exit status on step 2 means stg is active; non-zero
means it is not. Do not combine these into a single shell
command: pipes, $(), and xargs are harder for hooks and
approval rules to inspect and can trigger prompts.
Once stg is active, orient before your first mutating
command (new, refresh, goto, push, pop, float,
sink): run stg series -d once to see the applied set --
the current top (>) and whether any - unapplied patches
sit below it. On a deep stack, probe the depth and scope
that call -- see "Scope orientation on a deep stack". Many
rules below turn on this state: where stg new lands,
whether stg push -a overshoots, and which patch a bare
stg refresh folds into.
Orient once per session, not before every command (see
"Token efficiency").
The block-raw-git.sh guard hook checks stg-activity against
the repo the command targets: a leading git -C <dir> retargets
the check at <dir> when <dir> resolves to a directory,
otherwise it falls back to the hook's cwd -- the session's
primary branch -- keeping the guard fail-closed. That fallback
blocks the command whenever the session's primary branch is
stg, even though the target repo is not, and the BLOCKED
message names the primary branch, not the target. The hook
cannot see a cd <repo> && prefix; the harness resets cwd
between calls. So when an stg session also touches a second,
non-stg repo, drive that repo with git -C <repo> <subcommand>
rather than a cd, giving <repo> as an absolute path or one
starting with ~/, $HOME/, or ${HOME}/. The hook inspects
the command text before the shell expands it and expands only
those three prefixes itself; ~user/ or any other variable in
<repo> is unresolvable and triggers the cwd fallback. The
guard then resolves <repo>, and once it confirms <repo>
carries no stg stack it permits raw git there. This is not a
license to bypass the guard on an actual stg branch.
What ships with it
6 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.
- 2d ago First seen · 1,017 lines · 63 tokens per session scan A 8e9072a6cae3
stg is a skill published in the GitHub repository chucklever/cel-kdev (2 stars, last pushed 4d ago), licensed MIT. It adds 63 tokens to every session and 12,398 once invoked, about $0.0003 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.