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/drgnnpx skills add chucklever/cel-kdev --skill drgngit 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 | $0.00115 | $0.02949 |
| Opus 5 | $0.00057 | $0.01474 |
| Sonnet 5 | $0.00023 | $0.00590 |
| Haiku 4.5 | $0.00012 | $0.00295 |
Grade B, and why
drgn scanned grade B 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo drgn -k How it starts
The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
drgn kernel debugger
Inspect running kernel state through /proc/kcore, or a crash
dump captured in a format drgn can read. Use for diagnosing
hangs, verifying data structure contents, tracing reference
counts, and examining queue states.
Invocation
Always use -k for live kernel debugging:
sudo drgn -k
Do NOT use -c /proc/kcore -s <path> -e vmlinux. The -e
flag is parsed as inline Python, not as a vmlinux path. The
-k flag handles symbol resolution automatically.
For one-shot commands:
sudo drgn -k -c 'print(prog["jiffies"])'
For multi-line scripts, materialize the script with the
platform's file-editing mechanism and then invoke drgn
against the resulting file in a separate shell step. Do
not use a cat <<EOF heredoc to create the script:
heredocs are harder for agent harnesses and hooks to
inspect and can bypass edit policies.
-
Create
/tmp/drgn-script.py, e.g.:from drgn.helpers.linux.pid import find_task task = find_task(prog, 1234) print(task.comm) -
Run it:
sudo drgn -k /tmp/drgn-script.py
Symbols from debuginfod under sudo
When kernel symbols come from debuginfod rather than a local
kernel-debuginfo package (e.g. Fedora caching under
~/.cache/debuginfod_client), plain sudo drgn -k can fail
with "missing debugging symbols" followed by an
ObjectNotFoundError for a core symbol such as super_blocks.
This is not a script bug: sudo's env_reset strips
DEBUGINFOD_URLS, so drgn's debuginfod client never fetches
vmlinux. Forward the variable:
sudo DEBUGINFOD_URLS="$DEBUGINFOD_URLS" drgn -k /tmp/drgn-script.py
The expansion uses the invoking shell's value, so an empty
$DEBUGINFOD_URLS there yields DEBUGINFOD_URLS="" and
reproduces the failure. Confirm echo $DEBUGINFOD_URLS is
non-empty before forwarding; set it (Fedora's value appears
below) when it is not.
sudo -E, or a root login whose environment already sets
DEBUGINFOD_URLS, works as well. The value is
distribution-specific -- https://debuginfod.fedoraproject.org/
on Fedora -- so forward the existing one rather than hardcoding
a URL. The root client resolves its own cache path; no
DEBUGINFOD_CACHE_PATH is needed. Before concluding the symbols
are unavailable, confirm DEBUGINFOD_URLS survived into the
sudo environment.
What ships with it
5 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 · 366 lines · 115 tokens per session scan B b3d072fc2220
drgn is a skill published in the GitHub repository chucklever/cel-kdev (2 stars, last pushed 4d ago), licensed MIT. It adds 115 tokens to every session and 2,949 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). 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.