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 wan-huiyan/agent-traffic-control --skill conflicted-pr-starts-no-ci-run-push-resolution-firstgit clone --depth 1 https://github.com/wan-huiyan/agent-traffic-controlWrote 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/wan-huiyan/agent-traffic-control/conflicted-pr-starts-no-ci-run-push-resolution-first)<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/conflicted-pr-starts-no-ci-run-push-resolution-first"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/conflicted-pr-starts-no-ci-run-push-resolution-first/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/wan-huiyan/agent-traffic-control/conflicted-pr-starts-no-ci-run-push-resolution-first"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/conflicted-pr-starts-no-ci-run-push-resolution-first.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 | $0.00369 | $0.03245 |
| Opus 5.5 | $0.00148 | $0.01298 |
| Sonnet 5.5 | $0.00074 | $0.00649 |
| Haiku 4.5 | $0.00037 | $0.00325 |
Grade A, and why
conflicted-pr-starts-no-ci-run-push-resolution-first 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A Conflicted PR Starts No CI Run — Push the Resolution First
Problem
Your pull request is conflicted. Someone — a coordinator, a landing script, or you — reads its status and sees three fields:
#1234 DRAFT UNKNOWN (git: CONFLICTED vs origin/main abc1234de) gates=failure auto-merge=NOT armed
Two of those three are non-facts. The required check is red because the PR
is a draft (in repos where a draft's required context is deliberately red) or
because the newest run on that SHA is a stale one that died — either way it is
not the blocker. UNKNOWN is not "not conflicted": the provider invalidates
mergeability for every open PR each time the base moves and returns UNKNOWN
until it recomputes, which is the usual cause on a busy base. The only fact in
the line is the parenthesis, which came from git merge-tree.
The expensive half is what is missing: no NEW run is created for as long as
the conflict stands. A pull_request workflow runs against the synthetic
merge ref, and the provider rebuilds that ref whenever either side moves — so
when the two genuinely conflict there is nothing to check out and no run is
created. Waiting produces nothing. update-branch cannot fix a conflict. An
empty commit does nothing for one either.
And the run list is probably not empty, which is the part that misleads.
The head keeps whatever run it earned when it was first pushed, before the
base moved and the conflict arose. Measured on the incident below: the
conflicted head's run list held exactly one run, created the previous day, whose
changes job had SUCCEEDED and whose only red job was the draft's designed-red
aggregator. So the queue script's gates=failure was a true reading of a run
that had nothing to do with the conflict, and a session checking
total_count gets a reassuring non-zero answer. What is diagnostic is the run's
AGE, not the count — compare the newest run's created_at against the base
branch's last merge.
Context / Trigger Conditions
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 · 247 lines · 369 tokens per session scan A 415b67745c73
conflicted-pr-starts-no-ci-run-push-resolution-first is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed 1mo ago), licensed MIT. It adds 369 tokens to every session and 3,245 once invoked, about $0.0015 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 2026-09-18.
Other skills, from other repositories
cloudflare-workers-ci-cd
Complete CI/CD guide for Cloudflare Workers using GitHub Actions and GitLab CI. Use for automated testing, deployment pipelines, preview environments, secrets management, or encountering deployment failures, workflow errors, environment configuration issues.
babysit
PR babysitter: monitors CI status, auto-rebases when behind, auto-fixes CI where possible, delegates review comment handling to dlc:pr-check, and re-requests review after fixes. Designed for /loop usage with Remote Control.
abd-devops
ABD DevOps agent: scaffolds CI/CD, validates .env.example coverage, checks Dockerfile hygiene, and handles release tasks.
claude-plugin-repo-ci-release
Wire up CI validation and automatic release-cutting for a Claude Code plugin or marketplace repo (a repo with a .claude-plugin/marketplace.json and plugins/). Adds two GitHub Actions — a structure validator that runs on every PR/push, and a release-on-version-bump job that cuts a GitHub Release whenever a VERSION file…
bun-sveltekit
Use when building or running SvelteKit apps on Bun, including SSR, adapters, and Bun-specific APIs.
blueprint-repo-ci
Find out whether GitHub Actions already runs the recorded gates on every pull request, and record what is missing. Change nothing: adding CI is the first change the person approves.