A workflow that watches the required checks on a GitHub pull request, which is a proposed code change, until they pass. When a check fails, it fixes the problem and checks again, up to five rounds.

Use it to monitor a pull request, find failing checks, apply fixes, and confirm that all required checks are green.

It removes the need to keep refreshing CI, meaning automated build and test checks, and manually repeat the fix-and-check cycle.

loop-on-ci — Skill for Cursor by fmflurry/settings-opencode

Install

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.

Any agent

npx skills add fmflurry/settings-opencode --skill loop-on-ci

Clone the repo

git clone --depth 1 https://github.com/fmflurry/settings-opencode

Made for: Cursor.

Or install fmflurry-harness, the plugin that ships this one along with the rest of its 21 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fmflurry/settings-opencode/loop-on-ci/github.svg)](https://agentmods.dev/skills/fmflurry/settings-opencode/loop-on-ci)

Your own site

<a href="https://agentmods.dev/skills/fmflurry/settings-opencode/loop-on-ci"><img src="https://agentmods.dev/badge/skills/fmflurry/settings-opencode/loop-on-ci/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fmflurry/settings-opencode/loop-on-ci"><img src="https://agentmods.dev/badge/skills/fmflurry/settings-opencode/loop-on-ci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 820 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00033	$0.00820
Opus 5.5	$0.00013	$0.00328
Sonnet 5.5	$0.00007	$0.00164
Haiku 4.5	$0.00003	$0.00082

Measured 13d ago against content hash ffad38010094, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

loop-on-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 13d 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.

plugins/fmflurry-harness/skills/loop-on-ci/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Loop on CI

If the current project has .claude/skills/loop-on-ci/SKILL.md or .opencode/skills/loop-on-ci/SKILL.md, read it and its references/; project specifics override this generic version.

Trigger

Need to watch a branch or PR and iterate on CI failures until all required checks are green.

Workflow

1. Resolve the PR

Extract metadata for the active branch:

gh pr view --json number,url,headRefName,baseRefName

2. Inspect Current Checks

List all PR-attached checks:

gh pr checks --json name,bucket,state,workflow,link

If checks already failed, diagnose those failures first using [[fix-ci]], then re-check after each fix.

If checks are pending, proceed to step 3 (watch mode).

3. Watch Required Checks

Use the gh pr checks command to watch and fail fast on the first failure:

gh pr checks --required --watch --fail-fast

This polls required checks and exits immediately when any fails or all pass.

4. On Failure: Fix and Repeat

When --watch --fail-fast exits with a failure, run gh pr checks --json … again to see the current state.
Dispatch [[fix-ci]] to diagnose and fix the failure (fix-ci derives routing from the workflow files).
After the fix is merged and pushed, re-run gh pr checks --required --watch --fail-fast to re-check.
Repeat until all required checks are green, or cap is reached (see Limits below).

5. On Green

Once all required checks pass, report:

Final PR URL
Iteration count
Any flaky checks detected (see Flaky Checks below)

Iteration Cap

Hard limit: 5 iterations of watch-fix-recheck. If required checks are still not green after 5 iterations:

Report the current state: failing check names, last error excerpt, and iteration count.
Stop and surface to the human; do not loop further.
Note any pattern (e.g., the same check fails repeatedly) and flag as likely infrastructure issue or environmental flake.

Flaky Checks

If a check fails and then passes without code changes (common for timeouts, race conditions, or external service hiccups):

Read the full file on GitHub · 101 lines

Changes

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.

13d ago First seen · 101 lines · 33 tokens per session scan A ffad38010094

Subscribe to this mod's changes

loop-on-ci is a skill published in the GitHub repository fmflurry/settings-opencode (171 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 820 once invoked, about $0.0001 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 2026-10-03.

CI and CD DevOps and cloud Git and workflow

loop-on-ci

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Loop on CI

Trigger

Workflow

1. Resolve the PR

2. Inspect Current Checks

3. Watch Required Checks

4. On Failure: Fix and Repeat

5. On Green

Iteration Cap

Flaky Checks

What this file has done since we first saw it

Other skills, from other repositories

deployment-patterns

agent-github-modes

baby-sit

chinese-git-workflow

atmos-hooks

atmos-pro