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 a-analyzing-github-ci-performancegit 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/a-analyzing-github-ci-performance)<a href="https://agentmods.dev/skills/tracer-cloud/opensre/a-analyzing-github-ci-performance"><img src="https://agentmods.dev/badge/skills/tracer-cloud/opensre/a-analyzing-github-ci-performance/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/a-analyzing-github-ci-performance"><img src="https://agentmods.dev/badge/skills/tracer-cloud/opensre/a-analyzing-github-ci-performance.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 | $0.00067 | $0.01935 |
| Opus 5.5 | $0.00027 | $0.00774 |
| Sonnet 5.5 | $0.00013 | $0.00387 |
| Haiku 4.5 | $0.00007 | $0.00194 |
Grade A, and why
analyzing-github-ci-performance 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 7d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI/CD analytics
Give the user a CI/CD reliability report for one repository from raw GitHub Actions records, including an estimate of CI waiting time on merged pull requests.
Use a 30-day window unless the request specifies another period.
Plan
After reading this skill, use update_plan to create or revise the live
CI/CD Reliability Progress plan using the five numbered workflow headings
below as its steps. Mark a step in_progress or completed in the same response as
that step's tool call.
Keep showing the table and offering the next step as separate plan items; update statuses as each step's completion condition is met.
Mark step 4 with deliverable: true in every update_plan call: its work is
the reply itself, and without that flag the host treats a text-only reply
before the plan is settled as a premature stop and does not show it.
- Step 1. Scan local repositories with scan_local_git_workspace.
- Step 2. Select a repository using ask_user_choice.
- Step 3. Collect the 30-day metrics with analyze_github_ci_reliability and prepare the metrics table from its result.
- Step 4. Show the metrics table as a text-only reply.
- Step 5. Use ask_user_choice to offer scheduling, Slack setup, or finish.
Workflow
1. Scan this machine
Call scan_local_git_workspace() with no arguments.
Complete when scan_local_git_workspace has returned in this turn, even
with an empty result; the example repository remains available in step 2.
2. Pick the repository
Call ask_user_choice with the title Which repository should I analyze?.
Offer up to 5 scanned repositories that have GitHub Actions workflows
as <owner/repo>, then Tracer-Cloud/opensre as an example option.
Offer the picker even when only one repository was found; a single scan
result is not a selection. When no scanned repository has GitHub Actions
workflows, offer up to 3 of the most active ones as <name> (local insights)
before the example option.
End the turn after calling ask_user_choice; the answer arrives as the
next user message.
What ships with it
3 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.
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.
- 7d ago Changed d53ed927e68d
- 11d ago Changed · +4 lines 6f2fa4332c1f
- 13d ago Changed · -4 lines e481a3df0da3
- 1mo ago Changed c85e95f28864
- 1mo ago Changed · +13 lines 134e7872621d
- 1mo ago Changed · -4 lines a52da6c9417c
- 1mo ago First seen · 155 lines · 67 tokens per session scan A b41f05436237
analyzing-github-ci-performance is a skill published in the GitHub repository Tracer-Cloud/opensre (11,969 stars, last pushed today), licensed Apache-2.0. It adds 67 tokens to every session and 1,935 once invoked, about $0.0003 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
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.