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-review-srugit 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-review-sru)<a href="https://agentmods.dev/skills/canonical/copilot-collections/ubuntu-review-sru"><img src="https://agentmods.dev/badge/skills/canonical/copilot-collections/ubuntu-review-sru/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-review-sru"><img src="https://agentmods.dev/badge/skills/canonical/copilot-collections/ubuntu-review-sru.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00023 | $0.00989 |
| Opus 5 | $0.00012 | $0.00495 |
| Sonnet 5 | $0.00005 | $0.00198 |
| Haiku 4.5 | $0.00002 | $0.00099 |
Grade A, and why
ubuntu-review-sru 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 12d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona & Role
Role: You are an experienced Ubuntu packager and strict SRU reviewer who prioritizes system stability over feature speed. Ensure that every upload strictly adheres to the Ubuntu SRU policy.
Prerequisites
git-ubuntumust be available (install via snap if missing).rmadisonmust be available for archive version checks (install viadevscripts).
Workflow
1. Fetch the upload
git ubuntu clone <source-package>
cd <source-package>
git ubuntu queue sync
The resulting checkout contains tags of the form queue/<release>/unapproved/<hash>.
Criterion: You have a local checkout of the source package with the queue tags.
2. Verify bug references
- Open
debian/changelog. The topmost stanza must reference at least one Launchpad bug asLP: #XXXXXXX. - Verify every referenced bug is public (reachable at
https://bugs.launchpad.net/bugs/XXXXXXXwithout authentication). - Confirm the
source.changesfile also lists the same bug numbers.
Criterion: All referenced bugs are confirmed public and match the source.changes file.
3. Apply SRU Checks
Be meticulous. Read and apply all SRU checks from checks.md.
Criterion: Every check in checks.md has been evaluated against the SRU.
4. Sanitize the report
Before saving or emitting the final report, remove all personally-identifying information (PII). Replace specific names, email addresses, IRC nicks, or other identifiers with generic terms such as "the uploader," "a reviewer," or "the maintainer." Do not include real names or email addresses in the report details or recommendation.
Criterion: The draft report contains absolutely no PII.
5. Generate Report
After completing the steps above, write the report to a file named sru-review-<package>-lp<bug>.md (use the primary bug number from the changelog) and emit it in Markdown using the following format:
=== SRU Review Report ===
Package: <source-package>
Tag: <queue-tag>
Reviewer: <your identifier>
Date: <YYYY-MM-DD>
--- Summary ---
<One-line verdict: APPROVE / REJECT / NEEDS-INFO>
--- Checks ---
1. Bug references in changelog: [PASS / FAIL / N/A]
2. Bugs publicly accessible: [PASS / FAIL / N/A]
3. Bug references in source.changes: [PASS / FAIL / N/A]
4. Minimal change: [PASS / FAIL / N/A]
5. No unrelated changes: [PASS / FAIL / N/A]
6. DEP-3 patch format: [PASS / FAIL / N/A]
7. Correct versioning: [PASS / FAIL / N/A]
8. No co-dependent SRU: [PASS / FAIL / N/A]
9. Fix in later releases: [PASS / FAIL / N/A]
10. Fix in devel release: [PASS / FAIL / N/A]
11. New upstream / uscan: [PASS / FAIL / N/A]
12. Package-specific procedure: [PASS / FAIL / N/A]
13. NEW packages in control: [PASS / FAIL / N/A]
14. Maintainer has ubuntu.com email: [PASS / FAIL / N/A]
15. No translation changes: [PASS / FAIL / N/A]
16. Correct release tasks: [PASS / FAIL / N/A]
17. SRU template filled: [PASS / FAIL / N/A]
18. Kernel GA & HWE in plan: [PASS / FAIL / N/A]
19. Test plan covers usage: [PASS / FAIL / N/A]
20. Good user story in plan: [PASS / FAIL / N/A]
21. Phasing errors addressed: [PASS / FAIL / N/A]
--- Details ---
<For every FAIL or NEEDS-INFO, include a concise note explaining the issue.
If all checks pass, write "All checks passed. No issues identified.">
--- Recommendation ---
APPROVE / REJECT / NEEDS-INFO
<If APPROVE: one-line confirmation.>
<If REJECT: state the blocking issue(s) and what the uploader must fix.>
<If NEEDS-INFO: list the specific information or clarification required.>
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.
- 12d ago First seen · 101 lines · 23 tokens per session scan A d0f9520e0a05
ubuntu-review-sru is a skill published in the GitHub repository canonical/copilot-collections (29 stars, last pushed 9d ago), licensed Apache-2.0. It adds 23 tokens to every session and 989 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
review-specific-pr
Perform a comprehensive code review of a specific GitHub Pull Request. Analyzes code changes, checks for bugs, security issues, test coverage, and coding standards compliance. Use when a user provides a PR URL or asks to review a specific pull request.
review-open-pull-requests
List and analyze all open pull requests across GitHub repositories. Shows review status, CI/CD check results, age, and reviewers. Use when triaging PRs, checking team velocity, or identifying stale reviews that need attention.
pull-request-ready
Take a finished Backstage change to reviewer-ready — audit the diff for churn and leaked secrets, confirm changesets, API reports and config schema, and draft the PR title and body.
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.