Borrowing it
Nothing to install: this file belongs to zpoint/vibe-seller. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zpoint/vibe-seller/main/.claude/skills/debug-ci/SKILL.mdgit clone --depth 1 https://github.com/zpoint/vibe-sellerWrote 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/zpoint/vibe-seller/debug-ci)<a href="https://agentmods.dev/skills/zpoint/vibe-seller/debug-ci"><img src="https://agentmods.dev/badge/skills/zpoint/vibe-seller/debug-ci.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.02446 |
| Opus 5 | $0.00013 | $0.01223 |
| Sonnet 5 | $0.00005 | $0.00489 |
| Haiku 4.5 | $0.00003 | $0.00245 |
Grade A, and why
debug-ci 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 6d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI Debug
Debug CI test failures by analyzing artifact logs, test code, and agent behavior.
Core Principle
We own the project, not just the PR.
Every CI failure has a root cause in code, config, or design — not in "flakiness." Even if a failure predates your current changes, you are responsible for finding the root cause and fixing it. Never dismiss a failure as "unrelated to this PR" or "intermittent" — those are descriptions of symptoms, not conclusions. The conclusion is the root cause and the fix.
Workarounds like increasing timeouts, adding retries, or loosening assertions are NOT acceptable. These mask the real problem. Find and fix the design flaw that the test exposed.
Fix from design, not from symptom
Before writing any fix, review the design that produced the bug. A failing test is one observation of a design that allowed a failure to be possible. Patching the observation doesn't change what's possible — only changing the design does.
Ask in this order, every time:
- What contract was violated? Which invariant did the failure
prove was unenforced? E.g., "the agent's
email_watermarkvalue must be a recent epoch" was an assumption, not an invariant, so the agent's wrong value was accepted. - Where does the design make the bug possible? Find the surface that lets a wrong value through — usually a missing guard, a non-deterministic input, or a contract expressed only in prose.
- Move the contract into code. The fix should make the bug class impossible to recreate from this surface, not just unlikely. Server-side validation, typed APIs, ownership invariants, single coroutine ordering — these are design fixes. Retries, sleeps, and "let's just hope the model gets it right next time" are not.
- Only after the design fix, ask: are tests pinning this invariant now? If not, add them. The test is the second line of defence, not the fix itself.
Symptoms that mean you skipped the design pass and went straight to a workaround:
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.
- 6d ago First seen · 240 lines · 25 tokens per session scan A c5d9056a4561
debug-ci is a skill published in the GitHub repository zpoint/vibe-seller (62 stars, last pushed 12d ago), licensed Apache-2.0. It adds 25 tokens to every session and 2,446 once invoked, about $0.0001 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
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
smoke-test
Health smoke tests + auto-fix for gbrain installs (and OpenClaw services when present). Run after machine/container restarts or whenever something seems broken. Tests critical services, auto-fixes bounded local issues, and reports worker topology without starting daemons. Extensible via user-defined test scripts in…
mcore-create-issue
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
debug-task
Diagnose and fix moon tasks that are broken, misconfigured, or behaving unexpectedly. Use this skill when a moon task is failing, not running, skipped, hanging, producing stale or wrong output, cached when it shouldn't be, re-running every time when it should be cached, or when outputs are empty or missing after a…
github-ci-fix
Fix failing GitHub CI / Actions checks via fixgithubprci and push to the existing PR head, or fix a branch's failing CI via a linked repair worktree.
github-ci-fix
Use when the user asks OpenSRE to fix failing GitHub CI, GitHub Actions checks, failing pull request checks, a broken PR branch, or CI on a named branch such as main.