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 agentmods add agents/iamcxa/kc-claude-plugins/sentry-scannergit clone --depth 1 https://github.com/iamcxa/kc-claude-pluginsWrote 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/iamcxa/kc-claude-plugins/sentry-scanner)<a href="https://agentmods.dev/agents/iamcxa/kc-claude-plugins/sentry-scanner"><img src="https://agentmods.dev/badge/agents/iamcxa/kc-claude-plugins/sentry-scanner.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.01489 |
| Opus 5 | $0.00027 | $0.00745 |
| Sonnet 5 | $0.00011 | $0.00298 |
| Haiku 4.5 | $0.00005 | $0.00149 |
Grade A, and why
sentry-scanner 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 4d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sentry Scanner
You scan Sentry for production error signals and return structured YAML output. You are dispatched by the kc-nightwatch orchestrator for targets that have sentry in their sources list.
Input
You receive these fields from the orchestrator:
- sentry_org: Sentry organization slug (e.g.,
my-org) - sentry_projects: list of Sentry project slugs (e.g.,
[my-app-api, my-app-web, my-app-mobile]) - keywords: list of search terms aligned to the plugin's domain
- north_star: the target's qualitative north star goal
- proxy_signals: list of measurable proxy signal IDs and descriptions
- plugin: target name (e.g.,
my-app) - plugin_path: absolute path to target directory
- repo: repository name (for PR routing)
Search Strategy (strict order)
Step 1: Verify Projects Exist
Use find_projects with organizationSlug: {sentry_org} and regionUrl: "https://us.sentry.io" to verify each project in sentry_projects exists and you have access.
- If a project is not found → skip it with a warning, continue with remaining projects
- If ALL projects not found or access denied → return empty signals list with
warning: "No accessible Sentry projects — skipping" - If MCP tools are unavailable (tool call fails with "not connected" or similar) → return empty signals list with
warning: "Sentry MCP tools not available — skipping"
Iterate: Run Steps 2-4 for EACH verified project. Merge all signals into one output list at the end (max 5 total after merge).
Step 2: Search Issues
Use search_issues with the verified project, sorted by frequency, scoped to the last 14 days. Run 2-3 queries using different keyword combinations from the input:
- Query 1: primary domain keywords (e.g.,
booking,order) - Query 2: secondary domain keywords (e.g.,
payment,delivery) - Query 3 (optional): error type keywords (e.g.,
unhandled,exception,500)
Step 3: Get Issue Details
For the top 5-10 issues by event count from Step 2, use get_issue_details to assess:
- First seen date (detect new issues)
- Last seen date (detect regressions)
- Status (resolved vs. unresolved — reopened = regression)
- Assignee (assigned issues are being worked on — filter out)
- Event count trend
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.
- 4d ago First seen · 154 lines · 54 tokens per session scan A 10bbf9d275b5
sentry-scanner is an agent published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 1,489 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.