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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/canonical/copilot-collectionsnpx agentmods add skills/canonical/copilot-collections/generate-agentWrote 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/generate-agent)<a href="https://agentmods.dev/skills/canonical/copilot-collections/generate-agent"><img src="https://agentmods.dev/badge/skills/canonical/copilot-collections/generate-agent/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/generate-agent"><img src="https://agentmods.dev/badge/skills/canonical/copilot-collections/generate-agent.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 | $0.00083 | $0.02585 |
| Opus 5.5 | $0.00033 | $0.01034 |
| Sonnet 5.5 | $0.00017 | $0.00517 |
| Haiku 4.5 | $0.00008 | $0.00259 |
Grade A, and why
generate-agent 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 1mo 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 — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Custom Agent Generator (Persona Factory)
Overview
This skill generates Custom Agent files that act as persistent specialized roles with:
- Identity: Job title, expertise domain, perspective
- Tool Set: Constrained capabilities (read-only by default, write when needed)
- Cognitive Architecture: Role-specific thinking process
Key distinction:
- Custom Agents (this skill) = Who (role, perspective, persona)
- Agent Skills (generate-agent-skills) = What (capability, workflow, task)
Example agents:
- Security Auditor (reads code, thinks like attacker, reports vulnerabilities)
- Documentation Writer (writes docs, enforces style, maintains consistency)
- Release Engineer (manages releases, validates readiness, updates changelogs)
- Code Reviewer (analyzes PRs, checks standards, suggests improvements)
Workflow
Step 1: Intent Validation
Confirm the user wants a Custom Agent (not a skill or instruction).
Decision tree:
- User wants a specialized role/perspective? → Continue to Step 2
- Examples: "Security Auditor", "Documentation Writer", "Release Manager"
- User wants a repeatable workflow/task?
- → STOP. Redirect to
generate-agent-skillsinstead - Explain: Skills are for capabilities (generate tests, refactor code)
- → STOP. Redirect to
- User wants file/directory-specific rules?
- → STOP. Redirect to
generate-path-instructionsinstead - Explain: Path instructions are for scoped rules
- → STOP. Redirect to
- User wants global repository rules?
- → STOP. Redirect to
generate-repo-instructionsinstead - Explain: Repo instructions are for project-wide standards
- → STOP. Redirect to
Proceed only if creating a role-based agent.
Step 2: Role Analysis
Goal: Define the agent's identity, expertise, and perspective.
Load the role analysis checklist:
cat references/role_analysis_checklist.md
Work through the checklist to define:
- Job Title - What is this agent's role?
- Expertise Domain - What does it specialize in?
- Primary Responsibilities - What does it do?
- Perspective - How does it think differently?
- Value Proposition - Why use this agent vs default?
What ships with it
4 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.
- 1mo ago First seen · 338 lines · 83 tokens per session scan A 0f032f8cd268
generate-agent is a skill published in the GitHub repository canonical/copilot-collections (31 stars, last pushed 7d ago), licensed Apache-2.0. It adds 83 tokens to every session and 2,585 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
incident-postmortem-report
Produce a thorough incident post-mortem report after an outage or customer-impacting event. Covers executive summary, impact, detailed timeline, root cause, contributing factors, corrective and preventive actions, and lessons learned. Use when the user asks to write, draft, or complete a post-mortem, blameless review…
documentation-search
Search the internal knowledge base for runbooks, architecture documentation, ADRs, best practices, and troubleshooting guides using RAG. Use when looking for internal documentation, deployment procedures, architecture decisions, or operational runbooks.
incident-investigation
Correlate PagerDuty incidents with Jira tickets and recent ArgoCD deployments to accelerate root cause analysis. Orchestrates multiple agents to build a timeline of events. Use when investigating active incidents, performing post-mortems, or correlating alerts with changes.
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.
oncall-handoff
Generate a comprehensive on-call handoff document by aggregating open incidents, ongoing issues, recent deployments, and systems to watch. Orchestrates Splunk On-Call (VictorOps), Jira, and ArgoCD agents. Use during on-call rotation changes or shift handoffs.
sprint-progress-report
Generate a comprehensive sprint progress report from Jira with velocity metrics, burndown analysis, blocker identification, and team workload distribution. Use when preparing sprint reviews, standups, or tracking sprint health mid-cycle.