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 skills/ilert/ilert-cli/ilert-essentialsnpx skills add iLert/ilert-cli --skill ilert-essentialsgit clone --depth 1 https://github.com/iLert/ilert-cliWhat 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 | $0.00024 | $0.04161 |
| Opus 5 | $0.00012 | $0.02080 |
| Sonnet 5 | $0.00005 | $0.00832 |
| Haiku 4.5 | $0.00002 | $0.00416 |
Grade A, and why
ilert-essentials 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 yesterday.
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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ilert essentials
ilert skills list is the index of everything else — including the
migrate-from-* playbooks. Migrating an existing setup? Read this first, then
the relevant one: they cover the mapping, this covers the platform.
The object model in one pass
| Object | What it is |
|---|---|
| Event | What monitoring tools send. integrationKey routes it to an alert source |
| Alert Source | Receives events. Owns the escalationPolicy, the integrationKey / integrationUrl, and every parsing and grouping setting |
| Alert | The actionable thing: PENDING → ACCEPTED → RESOLVED, created by an alert source, driven by an escalation policy, triggers notifications to responders |
| Service | A business capability people subscribe to. Appears on status pages, carries outage history, is attached to sources and named on incidents. Owns no policy and receives no events |
| Incident | The coordination record above alerts (used on business impact) — multi channel responders, timeline, incident channel. It publishes nothing by itself |
| Status update | The public message posted from an incident. This is what reaches status pages and subscribers |
| Escalation Policy | Ordered rules with escalationTimeout, targeting users, schedules or teams. Also repeating / frequency, delayMin, routingKey |
| Schedule | STATIC or RECURRING; RECURRING carries scheduleLayers. Overrides go through PUT /schedules/{id}/overrides |
| Event Flow | A routing layer above alert sources with its own ingest URL. Nodes: ROOT, DEFINE_BRANCHES, ROUTE_EVENT, SUPPORT_HOURS, WAIT, TRANSFORM |
| Call Flow | The same idea for inbound phone calls: IVR_MENU, AUDIO_MESSAGE, SUPPORT_HOURS, ROUTE_CALL, PARALLEL_ROUTE_CALL, VOICEMAIL, PIN_CODE, CREATE_ALERT, BLOCK_NUMBERS, AGENTIC |
| Alert Action + Connector | Outbound automation. The Connector holds credentials, the Alert Action binds it to a source with triggerMode, triggerTypes and ICL conditions |
| Maintenance Window | Takes both services and alertSources — communication and suppression in one object |
| Deployment Pipeline / Event | Deploy traffic, on its own ingest endpoint and its own integration key. Not alert traffic |
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.
- yesterday First seen · 279 lines · 0 tokens per session scan A 9b9fb68e2a35
ilert-essentials is a skill published in the GitHub repository iLert/ilert-cli (2 stars, last pushed 12d ago), licensed Apache-2.0. It adds 24 tokens to every session and 4,161 once invoked, about $0.0001 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 skills, from other repositories
investigate
The entry point for any software problem -- deployment failures, infrastructure issues, performance degradation, errors, or anything going wrong. Use when the user wants to understand what's happening, check on issues, check on the status of an investigation, ask about their systems, query Antimetal's AI for context…
fix
Fix a software issue by applying Antimetal's remediation to your codebase. Use when the user wants to fix, resolve, patch, remediate, or apply changes for any issue—or when they say things like "how do I fix this", "what should I change", "apply the fix", "let's resolve it", or when investigation is done and the next…
antimetal-mcp-setup
Ensures the Antimetal MCP server is configured and ready to use. Run this before attempting to call any Antimetal MCP tools—if the API key is missing, tools will fail silently.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
golden-rss
Use when testing the rss golden build.
github-security-fix
Remediate GitHub security / Dependabot / CodeQL / code-quality alerts via fixgithubsecurityalert.