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 kensaurus/cursor-kenji --skill debug-sentry-monitorgit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote 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/kensaurus/cursor-kenji/debug-sentry-monitor)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/debug-sentry-monitor"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/debug-sentry-monitor/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/kensaurus/cursor-kenji/debug-sentry-monitor"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/debug-sentry-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 509 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00075 | $0.04219 |
| Opus 5 | $0.00037 | $0.02109 |
| Sonnet 5 | $0.00015 | $0.00844 |
| Haiku 4.5 | $0.00007 | $0.00422 |
Grade A, and why
debug-sentry-monitor 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.
How it starts
The opening of the file, as written. The whole thing — 510 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sentry Monitor
Degree of freedom: MIXED. Triage bucket and root cause [HIGH freedom];
resolve-only-after-verify [LOW freedom — run exactly].
Triage, fix, and audit Sentry on any project via the sentry MCP. Auto-detects config.
How to reason
- Observe — issue type, frames, users, first-seen, release
- Interpret — app frame vs extension noise; new vs regression
- Classify — Noise / Code Bug / Data Bug / Performance / Regression / Config Gap
- Severity — regressions and multi-user crashes first; never resolve Performance
Worked example
Observe: 80 events of
TypeError: undefined.emailon/account, started at release1.14.0. Interpret: app frames in the profile card; correlates with the onboarding PR. Classify: Data Bug + Regression — API null for incomplete profiles. Fix: handle null at the contract; do not resolve until the fix is committed and the loop is green.
Self-critique before reporting
- No resolve without proof — issue stays unresolved if the fix is unverified
- No band-aid —
?./ swallowed catch is not the sole fix - Bucket is one — Noise is not used to mute an app-frame crash
- Right owner — one named bug through PR →
workflow-fix-and-ship
Critical Rules
NEVER resolve an issue without a verified fix. Resolving means "this will not happen again." If you cannot prove that, leave it unresolved.
NEVER apply a band-aid fix. Wrapping code in try/catch, adding
?.chains, or guarding withArray.isArray()are symptom suppressors. Only use defensive coding after fixing the root cause, to harden against truly unpredictable external input.
Understand the WHY before touching any code.
Research before fixing non-trivial bugs. Use
firecrawl_search+firecrawl_scrapeto find best practices for the specific error pattern before implementing a fix.
Step 0: Auto-Detect Project Configuration
Before making any Sentry MCP calls, discover the project's Sentry setup.
What ships with it
1 file 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 · 510 lines · 75 tokens per session scan A 7d598d12f10f
debug-sentry-monitor is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 4,219 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering bugs, test failures, unexpected behavior, or any technical issue before proposing fixes.
firebase-crashlytics
Use when implementing crash reporting, capturing fatal/non-fatal errors, recording isolate/async exceptions, customizing reports, or uploading obfuscated symbols.
incident-triage-harness
Production-style incident triage workflow for logs, metrics, code, safe mitigations, and M3 multimodal visual evidence (screenshots, screen recordings). Use when debugging alerts, regressions, outages, or suspicious runtime behavior.
agent-self-verification
A code-change verification workflow that builds the project, checks the interface and logs, and repeats fixes when something fails.
fix-issue
Fix a GitHub issue end-to-end. Use when given an issue number to fix, implementing bug fixes, or addressing reported problems.
debug-issue
Systematically debug a reported issue.