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 Arvo-AI/aurora --skill incidentiogit clone --depth 1 https://github.com/Arvo-AI/auroraWrote 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/arvo-ai/aurora/incidentio)<a href="https://agentmods.dev/skills/arvo-ai/aurora/incidentio"><img src="https://agentmods.dev/badge/skills/arvo-ai/aurora/incidentio/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/arvo-ai/aurora/incidentio"><img src="https://agentmods.dev/badge/skills/arvo-ai/aurora/incidentio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00024 | $0.00940 |
| Opus 5.5 | $0.00010 | $0.00376 |
| Sonnet 5.5 | $0.00005 | $0.00188 |
| Haiku 4.5 | $0.00002 | $0.00094 |
Grade A, and why
incidentio 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 today.
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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
incident.io Integration
Overview
incident.io integration for investigating incidents during Root Cause Analysis. Provides access to incident details, severity, roles, custom fields, timeline events, and alerts.
Instructions
Tool Usage (use in this order)
list_incidentio_incidents()-- Find recent or related incidents. Filter by status or severity.get_incidentio_incident(incident_id='X')-- Get full details including roles, custom fields, and duration.get_incidentio_timeline(incident_id='X')-- See the sequence of events, status changes, and human updates.list_incidentio_alerts()-- List recent alerts. Filter with status 'firing' or 'resolved'.get_incidentio_alert(alert_id='X')-- Look up one alert by an id from that list, an incident.io alert id, or a source-system id (Site24x7 and others store that as the deduplication key).
Investigation Patterns
- Find similar incidents:
list_incidentio_incidents(status='closed', page_size=10)to check for recurring issues. - Deep-dive current incident:
get_incidentio_incident(incident_id='...')for severity, responders, and custom fields. - Understand timeline:
get_incidentio_timeline(incident_id='...')to see what actions were taken and when.
RCA Investigation Workflow
Step 1 -- Context gathering:
list_incidentio_incidents(status='live') -- See what's currently happening.
Step 2 -- Incident details:
get_incidentio_incident(incident_id='...') -- Understand severity, who's responding, and what services are affected.
Step 3 -- Timeline analysis:
get_incidentio_timeline(incident_id='...') -- Reconstruct the sequence of events to find the trigger point.
Step 4 -- Pattern matching:
list_incidentio_incidents(status='closed', page_size=25) -- Check if similar incidents happened before.
Step 5 -- Cross-correlate: After incident.io analysis, correlate with infrastructure data from other connected tools (logs, metrics, deployments).
Alerts vs incidents
get_incidentio_incident only accepts an incident.io incident id. An id from an alert event, or from an upstream monitor such as Site24x7, is an alert id (or that source's id on deduplication_key).
- To see recent alerts, call
list_incidentio_alerts(). An incident id fromlist_incidentio_incidentsis not an alert id. - Call
get_incidentio_alert(alert_id='...')with an id from that list, or with a source-system id. - When the result includes an attached incident, use that incident id with
get_incidentio_incidentandget_incidentio_timeline. - A 404 from
get_incidentio_incidenton an id that came from an alert means callget_incidentio_alertinstead.
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.
- today Changed · +11 lines · +6 tokens per session 92fd7f9c5ac4
- 2mo ago First seen · 62 lines · 18 tokens per session scan A 3125d9e9d647
incidentio is a skill published in the GitHub repository Arvo-AI/aurora (455 stars, last pushed yesterday), licensed Apache-2.0. It adds 24 tokens to every session and 940 once invoked, about $0.0001 per session on Opus 5.5. 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.
incidentio compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| incidentioArvo-AI/aurora | Skill | 455 | yesterday | Apache-2.0 | A | 24 | Claude Code |
| tax-lawyer-software-interfaceselasticdotventures/_b00t_ | Skill | 16 | 13d ago | none | A | 54 | Claude Code |
| b00telasticdotventures/_b00t_ | Skill | 16 | 13d ago | none | A | 0 | Claude Code |
| terraform-infrastructure-as-codemanutej/luxor-claude-marketplace | Skill | 63 | 4mo ago | none | B | 36 | Claude Code |
| ak-add-integrationyaalalabs/agent-kernel | Skill | 192 | today | Apache-2.0 | A | 59 | Claude Code, Codex |
| isaac-automatorisaac-sim/IsaacAutomator | Skill | 270 | 12d ago | Apache-2.0 | A | 123 | Claude Code, Codex |
| analytics-opensearch-expertiseaws/tools-for-devops-agent | Skill | 137 | yesterday | Apache-2.0 | A | 136 | Claude Code, Codex |