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 retrospective-artifactsgit 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/retrospective-artifacts)<a href="https://agentmods.dev/skills/canonical/copilot-collections/retrospective-artifacts"><img src="https://agentmods.dev/badge/skills/canonical/copilot-collections/retrospective-artifacts.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.01350 |
| Opus 5 | $0.00036 | $0.00675 |
| Sonnet 5 | $0.00015 | $0.00270 |
| Haiku 4.5 | $0.00007 | $0.00135 |
Grade A, and why
retrospective-artifacts 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 8d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retrospective Artifacts
Overview
Create durable, queryable retrospective artifacts under .retrospectives/ and provide deterministic retrieval of key learnings from prior artifacts.
This skill has two modes:
- CREATE mode: interview, gather context, and build a standardized retrospective folder.
- PARSE mode: read existing retrospective folders and return only the requested facts.
Routing
Use CREATE mode when the request asks to:
- run a retrospective
- capture session learnings
- build a retro artifact folder
- summarize current work and preserve context
Use PARSE mode when the request asks to:
- query previous retrospectives
- extract specific learnings/code snippets/logs
- shortlist
okb_worthyitems - find sessions needing context asset improvement
Workflow 1: CREATE mode
Follow these steps in order.
Step 1: Context triage
- Inspect current conversation and workspace context.
- Identify missing facts: catalyst, impact, investigation, resolution, and downstream signals.
- Use
references/context-intake-checklist.mdto drive coverage.
Step 2: Progressive interview
Ask 1-3 targeted questions to fill missing gaps. Always request relevant external links if available:
- GitHub issues/PRs/Actions logs
- Jira tickets
- Mattermost threads
- external incident docs
Before extraction, require a focus directive from the user to control what gets exported from large contexts. Accept examples like:
- "only moments where Copilot iterated 3+ times"
- "only failed attempts and workarounds"
- "only final solutions and why they worked"
- "exclude routine successful steps"
Do not proceed to generation until the required minimum context is present.
Step 3: External context acquisition
For each provided link:
- Prefer MCP integrations first (GitHub/Jira/Mattermost MCP servers when available).
- If MCP is unavailable for a source, use fallback scripts in
scripts/. - If retrieval fails or access is denied, state that clearly and request pasted text.
- Do not infer missing external content.
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.
- references/context-intake-checklist.md 2.4 KB
- references/external-context-acquisition.md 3.0 KB
- references/parse-query-patterns.md 1.4 KB
- references/retro-summary-template.md 1.9 KB
- scripts/fetch_github_context.py 7.8 KB runs code
- scripts/fetch_jira_context.py 8.4 KB runs code
- scripts/fetch_mattermost_thread.py 5.1 KB runs code
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.
- 8d ago First seen · 157 lines · 73 tokens per session scan A 2174e4c2d88e
retrospective-artifacts is a skill published in the GitHub repository canonical/copilot-collections (29 stars, last pushed 6d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,350 once invoked, about $0.0004 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
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
triage-issue
Intelligently triage bug reports and error messages by searching for duplicates in Jira and offering to create new issues or add comments to existing ones. When an agent needs to: (1) Triage a bug report or error message, (2) Check if an issue is a duplicate, (3) Find similar past issues, (4) Create a new bug ticket…
bug-triage
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.
browse-flows
Browse Power Automate environments and flows interactively. Use when the user wants to browse, list, or explore their flows and environments.
operating-cadence
Designs the rhythm an organization runs on — which reviews happen weekly, monthly and quarterly, what each one decides, who owns the numbers presented, and how a signal at the front line reaches the people who can act on it. Use this to set up a management operating system, fix a meeting calendar that produces no…
factory-triage
Triage a Factory work item's issue — trace history, understand architecture, diagnose root cause, then advance the stage.