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 update-starbasegit 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/update-starbase)<a href="https://agentmods.dev/skills/canonical/copilot-collections/update-starbase"><img src="https://agentmods.dev/badge/skills/canonical/copilot-collections/update-starbase/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/update-starbase"><img src="https://agentmods.dev/badge/skills/canonical/copilot-collections/update-starbase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00043 | $0.02878 |
| Opus 5.5 | $0.00017 | $0.01151 |
| Sonnet 5.5 | $0.00009 | $0.00576 |
| Haiku 4.5 | $0.00004 | $0.00288 |
Grade A, and why
update-starbase 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 13d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Starbase
Phase 1: Merge Starbase
Run the preparation script from the root of the child repository:
bash <path-to-skill>/scripts/prepare_merge.sh [BRANCH_SUFFIX]
BRANCH_SUFFIXis optional; defaults to today's date (work/update-starbase-YYYY-MM-DD).- The script handles steps 1–6: safe-state check, remote setup, fetch, work-branch creation, merge, and conflict detection.
- It prints a compact
STATUS=...block (BRANCH,BASE,CHANGED_FILES, and — when relevant —CONFLICTED_FILESandPLACEHOLDER_WARNINGS) for one of fourSTATUSvalues, then continue with the matching step below:STATUS=clean(exit 0): merge succeeded with no conflicts. Continue to Phase 2.STATUS=conflicted(exit non-zero): merge stopped with conflicts. Resolve each file inCONFLICTED_FILESperreferences/file_ownership.md, thengit addthe resolved files andgit merge --continuebefore continuing to Phase 2.STATUS=already-up-to-date(exit 0):starbase/mainhas no commits that aren't already in the branch. No work branch was created — there is nothing to sync or open a PR for. Stop here and report this to the user.STATUS=failed(exit non-zero):git mergefailed for a reason other than an ordinary conflict (e.g. untracked files that would be overwritten, a failing merge hook). The merge was aborted; fix the underlying issue from the git output above the status block, then re-run the script.
If the script cannot be run, follow references/manual_merge_steps.md instead.
Report one of: merge-clean, merge-conflicted (with the conflicted file
list), already-up-to-date, or merge-failed.
Conflict resolution
When resolving merge conflicts, consult
references/file_ownership.md for the
complete ownership map and decision rules, including:
- Conflict rule 1 – File ownership map (always take starbase, always take child, and mixed-ownership rules by file/section).
- Conflict rule 1b – Files that must be deleted; check every merge, clean or conflicted, since these deletions never raise a conflict.
- Conflict rule 2 – Python type annotation modernisation (when to apply
X | Y,tuple[X, Y], etc., and Python version caveats). - Conflict rule 3 – AGENTS template handling (library vs. application repositories).
What ships with it
7 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.
- 13d ago First seen · 246 lines · 43 tokens per session scan A 4e7e9c4c3441
update-starbase is a skill published in the GitHub repository canonical/copilot-collections (31 stars, last pushed 2d ago), licensed Apache-2.0. It adds 43 tokens to every session and 2,878 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-03.
Other skills, from other repositories
release-readiness-check
Verify all prerequisites are met before a release by checking PRs, CI/CD status, environment health, and blocking issues across GitHub, ArgoCD, and Jira. Use before cutting a release, deploying to production, or during release planning.
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.
agent-github-modes
Agent skill for github-modes - invoke with $agent-github-modes.
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
atmos-hooks
Atmos hooks: lifecycle events, hook kinds, command/store/git/security hooks, step/steps hooks, when: conditions, scoping and overrides, toolchain integration, --skip-hooks, and Atmos Pro/local output.