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-repairsgit 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-repairs)<a href="https://agentmods.dev/skills/tracer-cloud/opensre/b-scheduling-github-ci-repairs"><img src="https://agentmods.dev/badge/skills/tracer-cloud/opensre/b-scheduling-github-ci-repairs/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-repairs"><img src="https://agentmods.dev/badge/skills/tracer-cloud/opensre/b-scheduling-github-ci-repairs.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 | $0.00056 | $0.02944 |
| Opus 5.5 | $0.00022 | $0.01178 |
| Sonnet 5.5 | $0.00011 | $0.00589 |
| Haiku 4.5 | $0.00006 | $0.00294 |
Grade A, and why
scheduling-github-ci-repairs 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.
How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboarding for Scheduled CI fixes
Monitor one repository every 30 seconds and automatically edit, test, and push fixes to one failing PR branch per tick. A green PR does not stop monitoring.
The private demo uses the same repair policy and the same cadence.
Goal
Get the user to a running scheduled loop that repairs a failing PR, and show one real repair as fast as possible in well under five minutes.
Plan
Use update_plan to create the live plan from the workflow headings below. Mark a step in_progress or completed in the same response as that step's tool call. A response that only calls update_plan is not progress. For the private demo, plan three steps instead: run the demo with one run_ci_repair_demo call (verifies: true), respond with the outcome report (deliverable: true), then offer the follow-up with ask_user_choice: the hand-off after a successful repair, or the blocker question after a blocked or failed run.
- Check prerequisites: GitHub identity and scopes, then the scheduler.
- Select the repository, or the private demo, with ask_user_choice.
- Select the failing PR, or confirm the authorized demo scope.
- Run the demo with one
run_ci_repair_democall (demo only). - Schedule the bounded repair with schedule_ci_repair_loop and record its task id.
- Wait until the repair is terminal with one
get_ci_repair_loopcall and read its report. - Verify the repair with one
pr viewcall. - Save evidence, remove the demo loop, and verify with one
finish_ci_repair_democall. - Respond with the outcome report as Markdown.
- After the report is shown, offer the follow-up with
ask_user_choice: the hand-off after a success, the blocker question otherwise.
Workflow
Step 1. Check prerequisites
Skip this step for the private demo: run_ci_repair_demo checks the token and the scheduler itself. Otherwise, two calls, one per response:
confirm authentication and print token:
github_cli["api", "user", "--include"]— confirms authentication and prints the token'sX-Oauth-Scopesheader.
What ships with it
5 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.
- 11d ago Changed · +4 lines edfc57b44a5e
- 12d ago Changed 5a18de2648fa
- 13d ago Changed · -8 lines 4b46fa11a936
- 14d ago Changed · -1 lines 02c18dcd1cc1
- 16d ago Changed · -23 lines · -18 tokens per session f63e5065e3dd
- 1mo ago Changed · -1 lines 346d345c3b33
- 1mo ago First seen · 252 lines · 74 tokens per session scan A 7e502a006f17
scheduling-github-ci-repairs is a skill published in the GitHub repository Tracer-Cloud/opensre (11,969 stars, last pushed today), licensed Apache-2.0. It adds 56 tokens to every session and 2,944 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 2026-09-15.
Other skills, from other repositories
bitbucket
Bitbucket code repository integration for managing repos, branches, PRs, issues, and CI/CD pipelines.
renovate
Generate renovate.json covering all dependency file types used in a repo, emit a GitHub Actions workflow that validates renovate.json on every PR, or generate a pre-commit hook for local validation.
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.