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 XyrusCode/ai-sync --skill rinse-and-repeatgit clone --depth 1 https://github.com/XyrusCode/ai-syncWrote 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/xyruscode/ai-sync/rinse-and-repeat)<a href="https://agentmods.dev/skills/xyruscode/ai-sync/rinse-and-repeat"><img src="https://agentmods.dev/badge/skills/xyruscode/ai-sync/rinse-and-repeat/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/xyruscode/ai-sync/rinse-and-repeat"><img src="https://agentmods.dev/badge/skills/xyruscode/ai-sync/rinse-and-repeat.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 | $0.00132 | $0.02008 |
| Opus 5.5 | $0.00053 | $0.00803 |
| Sonnet 5.5 | $0.00026 | $0.00402 |
| Haiku 4.5 | $0.00013 | $0.00201 |
Grade A, and why
Rinse and Repeat 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.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rinse and Repeat
Overview
A systematic loop for fixing CI/test failures: investigate the failure, apply a fix, push, poll the CI platform for results, and repeat until the pipeline passes or the retry budget runs out. When the budget is exhausted or the failure proves unfixable in the current session, hand over with a clear summary.
Core cycle: Investigate → Fix → Push → Poll → { Pass: done | Fail: repeat | Budget exhausted: handover }
When to Use
Engage this skill when:
- A CI pipeline is failing and the user wants to fix it iteratively
- Tests fail and the user asks to "keep fixing until green"
- The user explicitly invokes "rinse and repeat" or "CI loop"
- A PR has red checks and the user wants an automated remediation loop
- The user describes a test/CI failure and expects an investigative fix cycle
Do not engage for one-off fixes where the user explicitly wants a single attempt.
Operating Modes
Two modes, chosen at the start of each loop based on what is possible in the environment:
Full-Auto Mode
The agent polls the CI platform and retrieves logs automatically using the platform's CLI or API. Use when:
- The platform CLI is installed and authenticated (
gh,glab, oraz devops) - The agent can poll without exhausting rate limits
- The CI run ID or pipeline ID is known or discoverable
Workflow: investigate failure from fetched logs → fix → push → poll → repeat.
Semi-Auto Mode
The agent cannot reach the CI platform directly (no CLI, no auth, air-gapped, or the platform blocks automated log retrieval). The user acts as the relay for CI results.
Workflow:
- Agent applies a fix and pushes.
- Agent tells the user: "Pushed. Let me know when CI completes and paste the failure output if it fails."
- Agent waits. Do not poll or make repeated status calls.
- User pastes the CI output (logs, error text, screenshot description).
- Agent investigates the pasted output and either fixes again or reports success.
Ask upfront which mode to use if it is unclear. Default to full-auto when the platform CLI is available; fall back to semi-auto when any step (auth, discovery, polling) fails.
What ships with it
3 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.
- 1mo ago First seen · 178 lines · 132 tokens per session scan A 719ea2b1424b
Rinse and Repeat is a skill published in the GitHub repository XyrusCode/ai-sync (2 stars, last pushed 18d ago), licensed MIT. It adds 132 tokens to every session and 2,008 once invoked, about $0.0005 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 2026-09-04.
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.
quality-scan
Run a scoped, read-only quality scan and report exact-candidate evidence, failures and frozen debt. Use for an ad-hoc gate sweep or release preparation; a static scan is not full release acceptance.
e2e-testing
Use when reviewing CI coverage, automated checks, or test strategy related to Implement end-to-end testing. Focus on whether the rule is continuously verified, not just documented.
mirrord-prev-env
Help users create and manage mirrord preview environments — running a modified service as an isolated pod in a shared Kubernetes cluster, scoped by an environment key and HTTP/queue traffic filtering, so teams can validate and review changes against real traffic without affecting live services. Use when a developer…
ci
Configure Ginkgo for continuous integration — the recommended CLI flag set and the rationale for each flag (-r -p --randomize-all --randomize-suites --fail-on-pending --fail-on-empty --keep-going --cover --race --trace --json-report --timeout --poll-progress-after/-interval), invoking via go run to pin the CLI to…
test-setup
Scaffold the test framework and CI — tests/ directory, engine test runner, GitHub Actions workflow. Once, before the first sprint.