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 agentmods add skills/tracer-cloud/opensre/github_ci_fix_onboardingnpx skills add Tracer-Cloud/opensre --skill github_ci_fix_onboardinggit clone --depth 1 https://github.com/Tracer-Cloud/opensreWhat 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 | $0.00085 | $0.02766 |
| Opus 5 | $0.00043 | $0.01383 |
| Sonnet 5 | $0.00017 | $0.00553 |
| Haiku 4.5 | $0.00009 | $0.00277 |
Grade A, and why
github-ci-fix-onboarding 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 2d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub CI/CD Onboarding & Installation
Goal
Get the user from zero to a working local CI/CD loop with zero friction. Treat every missing prerequisite as a task the skill must fix. Continue until one real, same-repository pull request has completed an end-to-end CI fix cycle and its required checks are green.
When to use
- The user asks to set up, install, onboard, troubleshoot, or demo GitHub CI fixing in OpenSRE.
- Action-shaped wording such as "Can you onboard me on the CI/CD flow?" means run this setup; it is not a request to explain the CI/CD documentation.
fix_github_pr_ciis unavailable or reports a missing CLI, token, checkout, permission, or coding-agent prerequisite.- The user asks to "fix CI on this PR" but first-time readiness is unknown.
Do not use this onboarding flow when prerequisites are already known to pass and
the user only wants a CI failure fixed. Load github-ci-fix and call
fix_github_pr_ci directly.
Do not use it for an explicit explanation such as "How does the CI/CD flow
work?" when the user did not ask to set up, install, onboard, demo, or fix
anything.
Security rules
- Never run
gh auth status -t,gh auth token,env, or any command that prints a token. - Collect and persist the token only through the interactive GitHub integration setup prompt.
- Do not claim that
gh auth loginalone configures OpenSRE. OpenSRE must also be able to resolve a token from its GitHub integration or supported environment. - Never manufacture a failing workflow for a demo, weaken CI, push to a protected branch, or use a fork PR. Use an existing same-repository PR with a genuine failing check.
Ownership rules
This flow is action-owned from the first prerequisite check to the completion report. Once loaded, drive every step with action tools and conclude with your own reply:
- Keep this flow in the current agent turn — report progress, explain blockers, and summarize the final checks from the tool results. A generic answer does not know this workflow and will answer with unrelated GitHub status reads.
- Never call engineering-status gather tools (
generate_work_status_report,list_github_work_items,summarize_github_pr_status) here. Onboarding is not a status report. - When a prerequisite is blocked on the user (interactive login, PAT entry), conclude directly: state what passed, the exact command the user must run, and that you will rerun the failed check afterwards.
- When all prerequisites pass, do not stop to summarize readiness — continue to
the target-PR steps and
fix_github_pr_ciin the same flow.
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.
- 2d ago First seen · 276 lines · 85 tokens per session scan A 4979651d1d11
github-ci-fix-onboarding is a skill published in the GitHub repository Tracer-Cloud/opensre (10,985 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 2,766 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
host_bash
设备上跑只读 shell 命令做诊断探索（沙箱化 / read-only policy）.
host_restart_service
重启允许列表内的 systemd service（mutating，触发 reviewer 二审）.
file_inspector
Inspect files on the host filesystem.
edge_disk_audit
Audit disk usage on edge devices.
future_skill
A skill that uses fields ongrid does not yet recognize.
hello-world
Skill whose name uses a dash, expected to be normalized.