Borrowing it
Nothing to install: this file belongs to SCStelz/security-investigator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SCStelz/security-investigator/main/.github/skills/sentinel-ingestion-report/SKILL.mdgit clone --depth 1 https://github.com/SCStelz/security-investigatorWrote 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/scstelz/security-investigator/sentinel-ingestion-report)<a href="https://agentmods.dev/skills/scstelz/security-investigator/sentinel-ingestion-report"><img src="https://agentmods.dev/badge/skills/scstelz/security-investigator/sentinel-ingestion-report/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/scstelz/security-investigator/sentinel-ingestion-report"><img src="https://agentmods.dev/badge/skills/scstelz/security-investigator/sentinel-ingestion-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Agent Snooping · line 815 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- low Excessive Agency · line 584 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00134 | $0.16100 |
| Opus 5 | $0.00067 | $0.08050 |
| Sonnet 5 | $0.00027 | $0.03220 |
| Haiku 4.5 | $0.00013 | $0.01610 |
Grade A, and why
sentinel-ingestion-report 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 13d 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 — 819 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sentinel Ingestion Analysis Report — Instructions
Purpose
This skill generates a comprehensive Sentinel Ingestion Analysis Report covering workspace data volume, table-level breakdown, tier classification, ingestion anomalies, detection coverage, and optimization opportunities.
Entity Type: Sentinel workspace (from config.json)
| Scope | Primary Tables | Use Case |
|---|---|---|
| Workspace-wide (default) | Usage, SentinelHealth, SentinelAudit |
Full ingestion and cost analysis |
| Per-table deep dive | SecurityEvent, Syslog, CommonSecurityLog + any table |
Granular breakdown of high-volume tables |
What this report covers: Table-level volume breakdown with tier classification (Analytics/Basic/Data Lake), SecurityEvent/Syslog/CommonSecurityLog deep dives, ingestion anomaly detection (24h and week-over-week), analytic rule inventory with detection coverage cross-reference, rule health monitoring, tier migration candidates with DL-eligibility assessment, and license benefit analysis (DfS P2 and M365 E5).
Architecture
┌─────────────────────────────────────────────────────────────────┐
│ YAML query files PowerShell script LLM render │
│ queries/phase1-5/ ──→ Invoke-IngestionScan ──→ Phase 6 │
│ (23 .yaml files) .ps1 (~2600 lines) (SKILL- │
│ • az monitor (KQL) report.md) │
│ • az rest (REST API) │
│ • az monitor table list │
│ • Invoke-MgGraphRequest │
│ ↓ │
│ temp/ingest_scratch_<ts>.md │
│ (~50 KB, 64 sections) │
└─────────────────────────────────────────────────────────────────┘
Execution model:
- Phases 1-5 (data gathering): Fully automated by
Invoke-IngestionScan.ps1. KQL queries run viaaz monitor log-analytics query. Non-KQL data (analytic rules, tier classifications, custom detections) is gathered via REST API, Azure CLI, and Microsoft Graph. - Phase 6 (rendering): LLM reads the scratchpad +
SKILL-report.mdand renders the report. This is the only phase requiring LLM involvement.
What ships with it
54 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.
- Invoke-IngestionScan.ps1 159 KB runs code
- queries/phase1/Q1-UsageByDataType.yaml 676 B
- queries/phase1/Q2-DailyIngestionTrend.yaml 330 B
- queries/phase1/Q3-WorkspaceSummary.yaml 751 B
- queries/phase2/Q4-SecurityEventByComputer.yaml 867 B
- queries/phase2/Q5-SecurityEventByEventID.yaml 712 B
- queries/phase2/Q6a-SyslogByHost.yaml 877 B
- queries/phase2/Q6b-SyslogByFacilitySeverity.yaml 773 B
- queries/phase2/Q6c-SyslogByProcess.yaml 793 B
- queries/phase2/Q7-CSLByVendor.yaml 746 B
- queries/phase2/Q8-CSLByActivity.yaml 876 B
- queries/phase3/Q10-TableTierClassification.yaml 692 B
- queries/phase3/Q10b-TierSummary.yaml 1.3 KB
- queries/phase3/Q9-AnalyticRuleInventory.yaml 820 B
- queries/phase3/Q9b-CustomDetectionRules.yaml 661 B
- queries/phase4/Q11-RuleHealthSummary.yaml 1.1 KB
- queries/phase4/Q11d-FailingRuleDetail.yaml 553 B
- queries/phase4/Q12-SecurityAlertFiring.yaml 914 B
- queries/phase4/Q13-AllTablesWithData.yaml 336 B
- queries/phase5/Q14-IngestionAnomaly24h.yaml 1.4 KB
- queries/phase5/Q15-WeekOverWeek.yaml 965 B
- queries/phase5/Q16-MigrationCandidates.yaml 411 B
- queries/phase5/Q17-LicenseBenefitAnalysis.yaml 1.9 KB
- queries/phase5/Q17b-E5PerTableBreakdown.yaml 1.1 KB
- render_dashboard.py 40 KB runs code
- SKILL-drilldown.md 35 KB
- SKILL-report.md 62 KB
- slice_scratch.py 6.6 KB runs code
- svg-widgets.yaml 13 KB
- test-data/enterprise/ingestion-q1.json 3.6 KB
- test-data/enterprise/ingestion-q10.json 51 KB
- test-data/enterprise/ingestion-q10b.json 492 B
- test-data/enterprise/ingestion-q11.json 162 B
- test-data/enterprise/ingestion-q11d.json 1.2 KB
- test-data/enterprise/ingestion-q12.json 6.3 KB
- test-data/enterprise/ingestion-q13.json 6.5 KB
- test-data/enterprise/ingestion-q14.json 1.4 KB
- test-data/enterprise/ingestion-q15.json 1.7 KB
- test-data/enterprise/ingestion-q16.json 6.1 KB
- test-data/enterprise/ingestion-q17.json 16 KB
- test-data/enterprise/ingestion-q17b.json 2.8 KB
- test-data/enterprise/ingestion-q2.json 10 KB
- test-data/enterprise/ingestion-q3.json 233 B
- test-data/enterprise/ingestion-q4.json 4.6 KB
- test-data/enterprise/ingestion-q5.json 3.5 KB
- test-data/enterprise/ingestion-q6a.json 5.7 KB
- test-data/enterprise/ingestion-q6b.json 6.4 KB
- test-data/enterprise/ingestion-q6c.json 6.0 KB
- test-data/enterprise/ingestion-q7.json 1.3 KB
- test-data/enterprise/ingestion-q8.json 3.2 KB
- test-data/enterprise/ingestion-q9.json 61 KB
- test-data/enterprise/ingestion-q9b.json 9.9 KB
- test-data/enterprise/meta.json 99 B
- test-data/generate_enterprise_data.py 86 KB runs code
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.
- 13d ago First seen · 819 lines · 134 tokens per session scan A 612c130c4d5b
sentinel-ingestion-report is a skill published in the GitHub repository SCStelz/security-investigator (245 stars, last pushed 4d ago), licensed MIT. It adds 134 tokens to every session and 16,100 once invoked, about $0.0007 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…