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/canonical/charm-tech/cli-standardsnpx skills add canonical/charm-tech --skill cli-standardsgit clone --depth 1 https://github.com/canonical/charm-techWhat 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 | $0.00044 | $0.01609 |
| Opus 5 | $0.00022 | $0.00805 |
| Sonnet 5 | $0.00009 | $0.00322 |
| Haiku 4.5 | $0.00004 | $0.00161 |
Grade A, and why
cli-standards 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canonical CLI Standards
These standards define how Canonical CLI tools should look and behave. They originate from discussions with Canonical's senior tech leads and define best practice. All points must be strongly considered before contributing CLI code at Canonical.
For full do/don't examples of every rule, see examples.md.
Grammar + Vocabulary
Commands are verbs
Every command that acts on a primary object must be a verb (for example: install, refresh, login). Choose verbs that imply the object type they act on.
Commands are logically grouped
Group commands that act on the same object type or domain (for example: build lifecycle vs. store management).
Verb-noun form
When verbs alone are insufficient to distinguish objects, use verb-noun form:
snap set-quota
Listing secondary objects
Use the plural noun as shorthand instead of list-foobar:
snap services # not: snap list-services
snap list # for listing primary objects (snaps)
Showing state
- Use
statusovershow-status - Use
foobar-statusovershow-foobar-status - Use
foobarovershow-foobar
Standard commands
| Command | Purpose |
|---|---|
tool init |
Local initialisation |
tool bootstrap |
Distributed initialisation (cluster, VM, cloud) |
tool list |
Overview of all primary type instances |
tool foobars |
Overview of all secondary type instances |
tool show <id> |
Details for one primary instance |
tool status |
Current tool state |
tool start/stop |
Services, long-running processes |
tool enable/disable |
Primary type, feature |
tool get/set/unset |
Configuration |
tool create-foo <id> |
Create secondary object |
tool delete-foo <id> |
Delete secondary object |
tool help |
Show help |
tool version |
Show release version |
Sublevels
At most one sublevel may be used. Alternatively, split into separate tools with associated names:
cmd cluster config --secret "$(cat secret.txt)"
# OR
cmd-cluster config --secret "$(cat secret.txt)"
What ships with it
1 file 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 · 209 lines · 44 tokens per session scan A ece6028854d3
cli-standards is a skill published in the GitHub repository canonical/charm-tech (2 stars, last pushed 16d ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,609 once invoked, about $0.0002 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.
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…