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 gh-pr-create-orchestration-cwd-wrong-headgit 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/gh-pr-create-orchestration-cwd-wrong-head)<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/gh-pr-create-orchestration-cwd-wrong-head"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/gh-pr-create-orchestration-cwd-wrong-head/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/gh-pr-create-orchestration-cwd-wrong-head"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/gh-pr-create-orchestration-cwd-wrong-head.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 | $0.00217 | $0.01639 |
| Opus 5 | $0.00109 | $0.00820 |
| Sonnet 5 | $0.00043 | $0.00328 |
| Haiku 4.5 | $0.00022 | $0.00164 |
Grade A, and why
gh-pr-create-orchestration-cwd-wrong-head 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 11d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gh pr create from orchestration worktree picks wrong head branch
Problem
In a parallel-execution setup, an orchestrator dispatches sub-agents to feature
worktrees (<repo>/.claude/worktrees/feature-A/, feature-B/, etc.) and waits
on their completion. When the orchestrator then runs gh pr create to open
the PR for one of those features, it gets opened against whatever branch is
currently checked out in the orchestrator's CWD — not the feature
branch the subagent committed to.
Result: a PR with the right title and body but the wrong head branch
(typically the orchestrator's docs/sNNN-handoff or main-tracking branch).
The PR's diff is unrelated to the change description, and the actual feature
work never gets a PR.
Trigger conditions
You're hitting this skill if all of:
- Your workflow has multiple worktrees: one orchestrator + N feature worktrees.
- You ran
gh pr create(with title + body via heredoc) from the orchestrator's working directory. gh pr view <N> --json headRefNamereturns your orchestrator's branch (e.g.docs/sNNN-handoff), NOT the feature branch (e.g.fix/issue-XXX).- The PR's diff in
gh pr diff <N>doesn't match the body text.
Optional secondary signal:
- A revived subagent later opens a SECOND PR on the correct branch (because
it ran
gh pr createfrom the feature worktree where its CWD was). Now you have two PRs.
Root cause
gh pr create defaults --head to the current branch in the CWD where you
invoked it. The orchestrator's CWD is typically a worktree that's checked
out on a different branch than the feature branch — that branch is what gets
pushed/used as head. The subagent's git commits in <repo>/.claude/worktrees/feature-X/
have NO effect on the orchestrator's CWD branch.
This is an easy trap because:
- The heredoc-supplied body looks right.
- The branch name doesn't appear in the
gh pr createinvocation, so there's nothing to visually trip on. - The PR opens successfully and reports a URL — looks like success.
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.
- 11d ago First seen · 170 lines · 217 tokens per session scan A e9f6a50c66b4
gh-pr-create-orchestration-cwd-wrong-head is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed 6d ago), licensed MIT. It adds 217 tokens to every session and 1,639 once invoked, about $0.0011 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 2026-08-31.
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.
claude-code-bash-patterns
Claude Code Bash tool patterns with hooks, automation, git workflows. Use for PreToolUse hooks, command chaining, CLI orchestration, custom commands, or encountering bash permissions, command failures, security guards, hook configurations.
bump-sdk-version
Bump the FutureSearch SDK version across all files. Use when releasing a new SDK version, updating version numbers, or the user says bump version, release, version bump.
pr-check
PR review compliance: fetch review comments from an open PR, categorize as resolved/unresolved/dismissed, critically evaluate fixable items, implement approved fixes, and reply inline. Pass --unattended to halt on human-judgment items (emitted as Pending-Human) instead of prompting via AskUserQuestion.
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.
git-ops
Git hygiene: clean up merged branches, prune stale remotes, and verify repository state.