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 onboarding-github-cigit 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/onboarding-github-ci)<a href="https://agentmods.dev/skills/tracer-cloud/opensre/onboarding-github-ci"><img src="https://agentmods.dev/badge/skills/tracer-cloud/opensre/onboarding-github-ci/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/onboarding-github-ci"><img src="https://agentmods.dev/badge/skills/tracer-cloud/opensre/onboarding-github-ci.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 | $0.00070 | $0.01171 |
| Opus 5 | $0.00035 | $0.00585 |
| Sonnet 5 | $0.00014 | $0.00234 |
| Haiku 4.5 | $0.00007 | $0.00117 |
Grade A, and why
onboarding-github-ci 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI/CD onboarding
Resolve the user's demo choice and hand execution to its child skill. The child owns the work, its prerequisites, authorization, and follow-up.
Plan
The selected child owns the live plan and its update_plan calls. This
router's two steps below track selection and handoff only; leave the live
plan to the child. The host may pause for its entry menu before any model
step can run.
- Step 1. Resolve the demo selection from the request or the host's ask_user_choice menu.
- Step 2. Load the selected child's instructions with skill_view.
Workflow
1. Resolve selection
Use an explicit demo choice in the current request or the answer to the onboarding question. Carry the original request, including any repository, constraints, and existing approvals, into the handoff. The child determines its own prerequisites; analysis still follows its scan and repository picker.
When selection is unresolved, read the pre_execute result:
menu: queued: end the turn and wait for the answer. The host has opened the picker; neither another tool call nor a text copy of its options is needed.menu: suppressed: continue from an applicable existing answer. A greeting is an ordinary conversation turn. For an explicit request to reopen the demo menu, callslash_invokewith/demoand wait for its new selection.menu: unavailable, a hook error, or no menu result: explain that guided selection is unavailable in this session, invite a direct task request, and end onboarding. There is no replacement text menu.
An ambiguous CI request needs one focused clarification about the desired
outcome before selecting a child. Use ask_user_choice when available and
end the turn; otherwise follow the unavailable-picker behavior above.
Handle unrelated requests as the user's new task.
Skip and Escape end onboarding in the shell without an answer for the model.
An explicit /demo starts a fresh run: carry inputs from the new request,
and perform the selected workflow again rather than crediting earlier results
as completed work.
What ships with it
8 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.
- a-analyzing-github-ci-performance/references/benchmarks.md 1.7 KB
- a-analyzing-github-ci-performance/references/metrics.md 7.1 KB
- a-analyzing-github-ci-performance/SCRIPTS.md 4.7 KB
- a-analyzing-github-ci-performance/SKILL.md 6.4 KB
- a-analyzing-github-ci-performance/test_workflow.py 8.4 KB runs code
- b-scheduling-github-ci-fixes/SKILL.md 12 KB
- c-connecting-slack/SKILL.md 2.8 KB
- test_onboarding_workflow.py 5.6 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.
- today First seen · 115 lines · 70 tokens per session scan A 612adb8a325c
onboarding-github-ci is a skill published in the GitHub repository Tracer-Cloud/opensre (11,038 stars, last pushed today), licensed Apache-2.0. It adds 70 tokens to every session and 1,171 once invoked, about $0.0003 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 2026-09-12.
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.
datadog
Full-stack observability with Datadog APM, logs, metrics, synthetics, and RUM. Use when implementing monitoring, tracing, alerting, or cost optimization for production systems.
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.
grafana
Build Grafana dashboards and variables, configure data sources and alerting, and provision dashboards as code.