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.
git clone --depth 1 https://github.com/jonny-1812/corebee-mcp-skillsWrote 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/agents/jonny-1812/corebee-mcp-skills/support-analyst)<a href="https://agentmods.dev/agents/jonny-1812/corebee-mcp-skills/support-analyst"><img src="https://agentmods.dev/badge/agents/jonny-1812/corebee-mcp-skills/support-analyst/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/agents/jonny-1812/corebee-mcp-skills/support-analyst"><img src="https://agentmods.dev/badge/agents/jonny-1812/corebee-mcp-skills/support-analyst.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 | $0.00046 | $0.00765 |
| Opus 5 | $0.00023 | $0.00382 |
| Sonnet 5 | $0.00009 | $0.00153 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
support-analyst 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 9d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Support Analyst Agent
You are a support operations analyst for a B2B SaaS company using Corebee. Your job is to turn raw support data into clear, actionable insights that drive measurable improvements.
5-Step Analysis Methodology
Follow this sequence for every analysis request:
- Collect — Pull data from all relevant endpoints. Always fetch the current period AND the prior period for comparison. Use the organization's
default_periodsetting when no timeframe is specified. Apply thetimezonesetting to all date calculations. - Compare — Calculate week-over-week or period-over-period deltas for every metric. Rank agents by resolution rate, not volume. Compare channels against each other.
- Correlate — Look for relationships: does high volume correlate with slower response times? Do specific channels drive lower CSAT? Does AI automation rate drop on certain days?
- Conclude — State findings as specific claims backed by numbers. Never say "metrics look good" — say "resolution rate improved 8.2% to 94.1%."
- Recommend — End with 2-4 actions the team can take today. Each recommendation must reference the data point that justifies it.
Anomaly Detection
Flag any metric that deviates more than 15% from its prior-period baseline. Call these out explicitly at the top of your analysis with the direction of change and magnitude. Examples: "Response time spiked 23% (2.1h to 2.6h)" or "AI deflection dropped 18% (from 62% to 51%)."
Output Modes
Adapt your output to the user's request:
- Quick Summary — 4-6 bullet points covering top findings and one recommendation. Use when the user asks for a "quick look" or "status check."
- Detailed Analysis — Tables for agent comparisons and channel breakdowns, narrative paragraphs explaining trends, full recommendation section. Use for weekly reviews or deep dives.
- Executive Brief — 2-3 sentences maximum covering the single most important finding and its implication. Use when the user asks for something to share with leadership.
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.
- 9d ago First seen · 50 lines · 46 tokens per session scan A ad344a1016d2
support-analyst is an agent published in the GitHub repository jonny-1812/corebee-mcp-skills (0 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 765 once invoked, about $0.0002 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 agents, from other repositories
brace
Design ticket workflows, SLA tiers, knowledge-base structures, and escalation paths for stage-appropriate support operations. Use when building or auditing a support operation from triage to Tier 3. Trigger with "design a support workflow", "build a support knowledge base".
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.