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 | $0.00046 | $0.00675 |
| Opus 5.5 | $0.00018 | $0.00270 |
| Sonnet 5.5 | $0.00009 | $0.00135 |
| Haiku 4.5 | $0.00005 | $0.00068 |
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 26d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI/CD onboarding
This master skill owns the onboarding question. The host opens its menu on
entry; the result's entry_menu reports whether it opened. If the current message
already answers it, continue directly to the selected child. Never ask the
onboarding question twice for one request.
Ask User
Read the entry_menu result before deciding what to do:
menu: queued: end the turn and wait for the selection. The host owns the menu; do not callask_user_choiceagain or repeat its options as text.menu: suppressed: no new menu opened. Continue the current request using the existing answer. If the user explicitly requests the demo menu again, callslash_invokewith/demo; a greeting does not request reopening.menu: unavailable: show Current demo choices as a numbered list and wait for a reply.- A hook error without a menu status: explain that the picker could not open and show Current demo choices as a numbered list.
Only a queued menu justifies telling the user to select from an open picker. The menu has no free-text row. Its last option opens the plain shell; the shell handles Skip and Escape without sending an answer to the model.
Follow the selected child
The next message carries the question and the user's answer. A local or cloud repair can also carry a second answer to Create a private demo repository?. That answer is the target decision. Do not ask it again and do not reopen this menu. Call skill_view
with the matching name, then follow its returned instructions in the same turn:
Use the generated Current demo choices below to match the answer to its skill. Load that skill before performing its workflow.
For a custom answer, treat that text as the user's request and act on it using the appropriate tools or skill. Do not reopen this menu or force a demo choice. After a child asks its own question, continue that child rather than returning to this master menu. Escape cancels onboarding; wait for a fresh user request.
What ships with it
14 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/SKILL.md 8.1 KB
- a-analyzing-github-ci-performance/test_workflow.py 17 KB runs code
- b-scheduling-github-ci-repairs/references/script-tools.md 882 B
- b-scheduling-github-ci-repairs/scripts/_demo_state.py 4.3 KB runs code
- b-scheduling-github-ci-repairs/scripts/write_demo_evidence.py 2.6 KB runs code
- b-scheduling-github-ci-repairs/SKILL.md 12 KB
- b-scheduling-github-ci-repairs/test_demo_scripts.py 5.2 KB runs code
- b-scheduling-github-ci-repairs/test_scheduling_workflow.py 11 KB runs code
- c-delegating-github-ci-repairs/SKILL.md 8.1 KB
- c-delegating-github-ci-repairs/test_delegating_github_ci_workflow.py 12 KB runs code
- d-connecting-slack/SKILL.md 2.8 KB
- test_onboarding_workflow.py 6.4 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.
- 26d ago Changed · +2 lines ac377c93ebef
- 1mo ago Changed · -6 lines ef183b5c8f6b
- 1mo ago Changed · -50 lines · -24 tokens per session b9b1244fec81
- 1mo ago 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 (12,575 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 675 once invoked, about $0.0002 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 2026-09-12.
Other skills, from other repositories
monitoring-alerting-commerce
Track store health in real time with dashboards for checkout success rate, payment failures, cart errors, and custom SLO alerting.
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.
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 operable Grafana dashboards with template variables, provisioning-as-code, and unified alerts wired to Prometheus/Loki; avoid high-cardinality panels agents love to ship.
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-logging
Application monitoring, logging systems, and alerting.