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 boshi-xixixi/TraeSkill --skill copilot-usage-metricsgit clone --depth 1 https://github.com/boshi-xixixi/TraeSkillWrote 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/boshi-xixixi/traeskill/copilot-usage-metrics)<a href="https://agentmods.dev/skills/boshi-xixixi/traeskill/copilot-usage-metrics"><img src="https://agentmods.dev/badge/skills/boshi-xixixi/traeskill/copilot-usage-metrics/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/boshi-xixixi/traeskill/copilot-usage-metrics"><img src="https://agentmods.dev/badge/skills/boshi-xixixi/traeskill/copilot-usage-metrics.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 | $0.00029 | $0.00545 |
| Opus 5 | $0.00015 | $0.00272 |
| Sonnet 5 | $0.00006 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
copilot-usage-metrics 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 7d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- copilot-usage-metrics — 98% identical, 3 lines differ
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Usage Metrics
You are a skill that retrieves and displays GitHub Copilot usage metrics using the GitHub CLI (gh).
When to use this skill
Use this skill when the user asks about:
- Copilot usage metrics, adoption, or statistics
- How many people are using Copilot in their org or enterprise
- Copilot acceptance rates, suggestions, or chat usage
- Per-user Copilot usage breakdowns
- Copilot usage on a specific date
How to use this skill
- Determine whether the user wants organization or enterprise level metrics.
- Ask for the org name or enterprise slug if not provided.
- Determine if they want aggregated metrics or per-user metrics.
- Determine if they want metrics for a specific day (YYYY-MM-DD format) or general/recent metrics.
- Run the appropriate script from this skill's directory.
Available scripts
Organization metrics
get-org-metrics.sh <org> [day]— Get aggregated Copilot usage metrics for an organization. Optionally pass a specific day in YYYY-MM-DD format.get-org-user-metrics.sh <org> [day]— Get per-user Copilot usage metrics for an organization. Optionally pass a specific day.
Enterprise metrics
get-enterprise-metrics.sh <enterprise> [day]— Get aggregated Copilot usage metrics for an enterprise. Optionally pass a specific day.get-enterprise-user-metrics.sh <enterprise> [day]— Get per-user Copilot usage metrics for an enterprise. Optionally pass a specific day.
Formatting the output
When presenting results to the user:
- Summarize key metrics: total active users, acceptance rate, total suggestions, total chat interactions
- Use tables for per-user breakdowns
- Highlight trends if comparing multiple days
- Note that metrics data is available starting from October 10, 2025, and historical data is accessible for up to 1 year
Important notes
- These API endpoints require GitHub Enterprise Cloud.
- The user must have appropriate permissions (enterprise owner, billing manager, or a token with
manage_billing:copilot/read:enterprisescope). - The "Copilot usage metrics" policy must be enabled in enterprise settings.
- If the API returns 403, advise the user to check their token permissions and enterprise policy settings.
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.
- 7d ago First seen · 53 lines · 29 tokens per session scan A 5ebe9cf0fd07
copilot-usage-metrics is a skill published in the GitHub repository boshi-xixixi/TraeSkill (263 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 545 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 2026-09-03.
Other skills, from other repositories
<skill-name>
A template for defining a coding-agent skill, including its title, trigger situations, overview, workflow, common mistakes, and optional references.
spec-writing
A method for writing a software specification: a document that records decisions, reasons, boundaries, and ways to judge whether implementation succeeded. It first checks whether important unknowns require user clarification or technical research.
onboarding-unknown-codebase
A method for quickly understanding an unfamiliar codebase, meaning a software project whose structure and behavior you do not yet know. It builds a project map by examining overview files, directories, and one main execution path.
commit-message
A guide for writing clear, traceable Git commit messages using the Conventional Commits format, which labels changes such as features, bug fixes, documentation, and refactoring.
clarifying-questions
Guidance for clarifying vague or assumption-heavy requests before making changes.
debugging
A systematic method for finding the underlying cause of a software bug by observing the failure, forming a hypothesis, and testing it.