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 b-scheduling-github-ci-fixesgit 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/b-scheduling-github-ci-fixes)<a href="https://agentmods.dev/skills/tracer-cloud/opensre/b-scheduling-github-ci-fixes"><img src="https://agentmods.dev/badge/skills/tracer-cloud/opensre/b-scheduling-github-ci-fixes/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/b-scheduling-github-ci-fixes"><img src="https://agentmods.dev/badge/skills/tracer-cloud/opensre/b-scheduling-github-ci-fixes.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 | $0.00062 | $0.01003 |
| Opus 5 | $0.00031 | $0.00502 |
| Sonnet 5 | $0.00012 | $0.00201 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
scheduling-github-ci-fixes 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scheduled CI repair
Demonstrate a real scheduled repair with a roughly four-minute target and a hard ten-minute budget covering setup through the final report. The tool owns the persistent repository name, fixture, deadline, cancellation, and cleanup.
Plan
Use update_plan to create the live plan from these five workflow steps.
Mark an already-selected scope completed. Send update_plan in the same
response as the next tool call, except before ask_user_choice, which must
be the only call in its response. Keep report delivery and follow-up as
separate steps.
- Step 1. Select the reusable demo or a specific PR with ask_user_choice.
- Step 2. Register or reuse the bounded run with schedule_ci_repair_loop.
- Step 3. Observe scheduled execution with get_ci_repair_loop.
- Step 4. Deliver the tool's structured outcome report as Markdown.
- Step 5. Offer the next workflow with ask_user_choice.
Workflow
Step 1. Select the scope
Use an explicit demo request or PR selection already supplied by the user.
Otherwise ask once with ask_user_choice: "Reusable private demo repository"
(recommended), or "Repair a selected PR". Collect the PR owner, repository,
and number only for the second choice. An explicitly requested organization
is the demo owner override; otherwise the tool uses the authenticated user.
Complete when the user selected the demo or a specific PR.
Step 2. Schedule the run
Call schedule_ci_repair_loop(demo=true) for the demo, adding owner only
for an explicit owner override. For an existing PR call
schedule_ci_repair_loop(owner="<owner>", repo="<repo>", pr_number=<number>).
This authorizes the background service and the selected repair scope. The
returned task id and deadline are authoritative. If reused is true, continue
observing that run; its original deadline remains unchanged.
Show the task id, next scheduled time, and /loops show <task_id> retrieval
command. Setup failures are terminal outcomes to report in Step 4. Repository
collisions stop setup; explain the tool's result without adopting another repo.
What ships with it
1 file 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.
- today Changed · -183 lines · -58 tokens per session scan C → A b7461909c0c4
- yesterday First seen · 286 lines · 120 tokens per session scan C 32c073f3516b
scheduling-github-ci-fixes is a skill published in the GitHub repository Tracer-Cloud/opensre (11,042 stars, last pushed today), licensed Apache-2.0. It adds 62 tokens to every session and 1,003 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.