OpenSRE is an open-source framework for building AI agents that investigate and resolve production incidents using operational data and tools. It is for site reliability engineers who want customizable incident-response workflows, training, and evaluation on their own infrastructure.
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 Tracer-Cloud/opensre --skill d-connecting-slackgit clone --depth 1 https://github.com/Tracer-Cloud/opensreWrote 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/tracer-cloud/opensre/d-connecting-slack)<a href="https://agentmods.dev/skills/tracer-cloud/opensre/d-connecting-slack"><img src="https://agentmods.dev/badge/skills/tracer-cloud/opensre/d-connecting-slack/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/tracer-cloud/opensre/d-connecting-slack"><img src="https://agentmods.dev/badge/skills/tracer-cloud/opensre/d-connecting-slack.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00100 | $0.00730 |
| Opus 5.5 | $0.00040 | $0.00292 |
| Sonnet 5.5 | $0.00020 | $0.00146 |
| Haiku 4.5 | $0.00010 | $0.00073 |
Grade A, and why
connecting-slack 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 11d 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.
What it actually says
Slack handoff
Verify or set up Slack, then explain how the team can hand off DevOps chores through a channel mention or a DM.
Workflow rules
- Never call Slack send/reply/react tools.
- Never invent that Slack is connected; trust only
cli_execverify results. - Never call
cli_execwithintegrations setup slack. That wizard is interactive andcli_execwill refuse it. - After setup (or a successful verify), explain in two sentences how to hand off a chore: mention OpenSRE in a channel it can see, or DM it.
Plan
Track progress with the update_plan tool, not with headers or prose:
- On entry, in the same response as the first workflow tool call
(
cli_exec), callupdate_planwith the steps below verbatim, the first stepin_progress, and a one-lineexplanation(this is not a diagnosis; no hypothesis table):Check Slack/Set up if needed/Explain the hand-off. MarkCheck Slackwithverifies: truein every call: it is the check the text-only last step relies on to close. - After a step's tool results, call
update_planmarking itcompletedand the next stepin_progress, in the same response as the next step's single tool call. When Slack is already connected, markSet up if neededcompleted without new tool calls instead of dropping it mid-run. - Do not narrate the plan or repeat step names in prose; the shell renders the checklist.
Workflow
1. Check Slack
Call cli_exec with payload integrations verify slack.
2. Set up if needed
If Slack is not configured, call slash_invoke with command
/integrations and args ["setup", "slack"], and stop. The shell queues that wizard on the
next prompt so it gets exclusive stdin. If Slack is already connected, say
so and skip setup.
3. Explain the hand-off
Two sentences: mention OpenSRE in a channel or DM it; do not post anything from this demo. Then stop.
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.
- 11d ago Changed · +1 lines c11b8a4a8fae
- 13d ago Changed d761fd2ca539
- 1mo ago First seen · 72 lines · 100 tokens per session scan A db8ac287c980
connecting-slack is a skill published in the GitHub repository Tracer-Cloud/opensre (11,969 stars, last pushed today), licensed Apache-2.0. It adds 100 tokens to every session and 730 once invoked, about $0.0004 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 2026-09-15.
Other skills, from other repositories
grafana-expert
Expert-level Grafana dashboards, visualization, data sources, alerting, and production operations. Use when the user mentions dashboards, visualization, monitoring, observability, or alerting, or when the task involves Grafana Architecture, Installation on Kubernetes, Data Sources, or Dashboard JSON.
host_bash
A read-only shell skill for examining files and running diagnostic commands in a restricted environment. A shell is a text interface for operating-system commands.
host_restart_service
A tool for restarting approved systemd services, which are background programs managed by Linux's service manager.
monitoring-expert
Expert-level monitoring and observability with Prometheus, Grafana, logging, and alerting. Use when the user mentions observability, Prometheus, Grafana, logging, metrics, or alerting, or when the task involves The Three Pillars of Observability, Monitoring Fundamentals, Prometheus Configuration, or Alert Rules.
datadog
Full-stack observability with Datadog APM, logs, metrics, synthetics, and RUM. Use when implementing monitoring, tracing, alerting, or cost optimization for production systems.
grafana
Build operable Grafana dashboards with template variables, provisioning-as-code, and unified alerts wired to Prometheus/Loki; avoid high-cardinality panels agents love to ship.