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 ci_fixgit 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/ci_fix)<a href="https://agentmods.dev/skills/tracer-cloud/opensre/ci_fix"><img src="https://agentmods.dev/badge/skills/tracer-cloud/opensre/ci_fix/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/ci_fix"><img src="https://agentmods.dev/badge/skills/tracer-cloud/opensre/ci_fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.00585 |
| Opus 5.5 | $0.00019 | $0.00234 |
| Sonnet 5.5 | $0.00010 | $0.00117 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
operating-github-ci-fixer 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 1mo 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.
What it actually says
operating-github-ci-fixer
Use fix_github_pr_ci for GitHub CI remediation requests, not
github_cli or shell_run.
Rules:
- Pass
pr_urlwhen the user provides a GitHub pull request URL. - Pass
owner,repo, andpr_numberwhen the user names a repo and PR number. - Pass
branch(e.g.branch="main") when the user asks to fix a branch's failing CI itself; never combine it with a PR selector. Merged or closed PRs are refused — usebranchfor failures already on the base branch. - Omit
workspacefor a named repository or PR URL; the tool creates an isolated checkout. Pass a path only to edit that specific matching checkout. - If no repo is named, omit
ownerandrepo; the tool uses the current checkout's GitHub origin. - The tool inspects failing GitHub Actions checks, fixes the local checkout or a temporary linked git worktree, commits, pushes the PR branch or fresh repair branch, and waits for the checks triggered by that push. It does not open a new PR.
- Fork PR branches are refused by the tool because OpenSRE only pushes to branches in the same repository.
- Branch targets such as
mainare never pushed directly; OpenSRE pushes a freshopensre/ci-fix-*repair branch. - When the PR branch is behind its base branch, or GitHub reports it as
conflicted (checks never start), the tool merges the base branch into the PR
branch first, resolves the conflicts, regenerates lockfiles, and pushes. If
the pushed fix itself turns out to conflict, it merges the base once more
and re-verifies. A conflict it cannot resolve safely is reported with the
exact files and what a person must decide. Do not run
git mergearound it. - The tool owns CI log inspection, fix execution, branch checkout, commit, and
push plus post-push check verification. Do not run a raw
ghworkflow around it. - If the tool returns
response_text, output exactly that text and stop. - If no fix is produced, keep the reply to one short line from
error; do not say "next steps", add numbered options, list example commands, or ask a broad follow-up question.
What ships with it
19 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.
- __init__.py 131 B runs code
- base_merge.py 8.3 KB runs code
- context.py 21 KB runs code
- decision_marker.py 3.6 KB runs code
- errors.py 1.5 KB runs code
- gh.py 3.5 KB runs code
- ledger.py 5.6 KB runs code
- resume.py 1.7 KB runs code
- runner.py 30 KB runs code
- ship.py 7.2 KB runs code
- storage/__init__.py 45 B runs code
- storage/attempts.py 2.7 KB runs code
- storage/database.py 862 B runs code
- storage/ledger.py 2.7 KB runs code
- storage/migrations.py 515 B runs code
- timing.py 1.1 KB runs code
- tool.py 5.7 KB runs code
- verification.py 19 KB runs code
- worktree.py 5.8 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.
- 1mo ago Changed · +3 lines be3a31cd22a9
- 1mo ago Changed · +3 tokens per session 2de0b7fbe149
- 1mo ago Changed · +5 lines b3c700d93587
- 1mo ago First seen · 36 lines · 45 tokens per session scan A 3e64cdbbeaf5
operating-github-ci-fixer is a skill published in the GitHub repository Tracer-Cloud/opensre (12,005 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 585 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 2026-08-30.
Other skills, from other repositories
datadog
Full-stack observability with Datadog APM, logs, metrics, synthetics, and RUM. Use when implementing monitoring, tracing, alerting, or cost optimization for production systems.
dd-debugger
Live Debugger - inspect runtime argument/variable values in production by placing log probes on methods. Use when asked what values a function receives, what parameters look like at runtime, or to capture live data from running services without redeploying.
dd-triage-flaky-test
Load when investigating a specific flaky test. Gets history, failure pattern, and category, then recommends fix, quarantine, or escalate.
dd-unblock-pr
Load when investigating a failing PR CI pipeline or checking PR health. Attributes each CI failure as flaky, infra, or regression, proposes a targeted action, and reports code coverage.
dd-symdb
Symbol Database - search service symbols, find probe-able methods.
open_rca_diagnosis
A structured method for finding the root cause of failures in microservices by examining measurements, request traces, and logs. It uses thresholds and cross-checks to connect symptoms to causes.