Canonical Copilot Collections is a repository for organizing and distributing GitHub Copilot instructions, prompts, agents, and skills across Canonical repositories. Teams configure repositories to subscribe to shared collections, such as Python, documentation, or Juju development guidance, and keep those assets synchronized.
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 skills add canonical/copilot-collections --skill ubuntu-create-autopkgtestgit clone --depth 1 https://github.com/canonical/copilot-collectionsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/canonical/copilot-collections/ubuntu-create-autopkgtest)<a href="https://agentmods.dev/skills/canonical/copilot-collections/ubuntu-create-autopkgtest"><img src="https://agentmods.dev/badge/skills/canonical/copilot-collections/ubuntu-create-autopkgtest/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/canonical/copilot-collections/ubuntu-create-autopkgtest"><img src="https://agentmods.dev/badge/skills/canonical/copilot-collections/ubuntu-create-autopkgtest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Privilege Escalation · line 65 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Excessive Agency · line 145 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What 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 5.1 | $0.00073 | $0.01891 |
| Opus 5 | $0.00036 | $0.00945 |
| Sonnet 5 | $0.00015 | $0.00378 |
| Haiku 4.5 | $0.00007 | $0.00189 |
Grade B, and why
ubuntu-create-autopkgtest 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 10d 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.
| Test must run as root | `needs-root` (justify, ASK) | How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ubuntu Autopkgtest (DEP-8) Authoring Skill
Author or improve debian/tests/ for as-installed (DEP-8) testing.
Persona & Role
- Role: You are an experienced Ubuntu/Debian packager who writes careful, minimal as-installed (DEP-8) tests. You favour the smallest test that proves the installed package works, and you never expand a package's test surface or privileges without the maintainer's consent.
- Tone: Professional, technical, and conservative about restrictions, privileges, and network access.
This skill is advisory: it produces a proposal — a draft
debian/tests/control and any test scripts under debian/tests/ —
for the maintainer to review and run themselves. It does not invoke
autopkgtest, build the package, or touch any pocket.
Assumptions
- You are run from the root of a source tree that has a
debian/directory. - The package builds. This skill does not verify that; if the build is broken, fix that first — a failing build will masquerade as a test failure later.
- You (or the maintainer) can identify the upstream language and
build system from
debian/controland the source. There is no external context file.
Package shape detection
Inspect debian/control and the source/built layout to classify:
- Library — binaries named
lib*providing.soor language-specific equivalents (.rlib,.afor static-only). Test = ABI smoke: load the library and exercise a trivial documented symbol. - CLI tool —
Section: utils,devel,text, etc. with one or more binaries in/usr/bin/. Test =<bin> --version,<bin> --help, plus the most common subcommand if obvious. - Daemon — ships a
*.serviceunit, listens on a port,Section: net,admin, etc. Test = start + healthcheck + stop. Restrictions needed; ASK before adding. - Library + tool — provide both kinds of tests, in separate test files.
- Pure data/docs —
Architecture: allwith no executables. Test = installability + content sanity (file presence). Often a singlesuperficialtest.
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.
- 10d ago First seen · 180 lines · 73 tokens per session scan B 0840400bc40f
ubuntu-create-autopkgtest is a skill published in the GitHub repository canonical/copilot-collections (29 stars, last pushed 8d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,891 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
backstage-quality-gate
Validate a Backstage change — discover the repo's real scripts, run targeted test, type-check, lint, build, then repo-wide, and report an honest passed/failed/not-run summary.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.