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 cross-worktree-spec-handoff-via-checkout-pathsgit 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/cross-worktree-spec-handoff-via-checkout-paths)<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/cross-worktree-spec-handoff-via-checkout-paths"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/cross-worktree-spec-handoff-via-checkout-paths/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/cross-worktree-spec-handoff-via-checkout-paths"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/cross-worktree-spec-handoff-via-checkout-paths.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 | $0.00079 | $0.03994 |
| Opus 5 | $0.00039 | $0.01997 |
| Sonnet 5 | $0.00016 | $0.00799 |
| Haiku 4.5 | $0.00008 | $0.00399 |
Grade A, and why
cross-worktree-spec-handoff-via-checkout-paths 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 12d 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 — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-worktree spec handoff via git checkout <branch> -- <paths>
Problem
You ran a brainstorming / design session in Claude Code session A. Output:
design spec doc, a handoff prompt, a vibe mockup HTML. You committed them
on branch worktree-spec-A in .claude/worktrees/spec-A/.
You then started Claude Code session B in a different worktree, on a fresh
branch feat/something-B branched from main. Session B is supposed to
consume the design spec — but the spec doc, handoff prompt, and mockup
files don't exist in B's working tree, because B's branch was cut from
main before A's commits landed and the commits never made it to main.
Session B reports: "the referenced design spec files don't exist in the handover. Let me look at what's available." → it's blocked.
The naive fix is "merge A's branch into main, then B pulls main". That needs a PR review cycle. Slow.
Context / Trigger Conditions
All of:
- Two (or more) Claude Code sessions are running in parallel, in
different worktrees of the same repo. (
git worktree listshows multiple paths.) - Session A (the producer) committed artefacts — design docs, plans, spec files, mockups, fixtures, prompts — on a branch that is not the base branch of session B.
- Session B (the consumer) is on a branch branched from
main(or any ancestor that predates A's commits) and cannot see A's files vialsor Read. - B reports a "file not found" / "doesn't exist" / "can't see the spec" symptom referencing files that you (or session A) know exist on disk somewhere else.
Smoking-gun signals:
- The missing file's path matches one you (or A) named in a recent message
("the spec is at
docs/plans/..."). git log --all --oneline -- <path>shows the file was committed on a branch that isn't an ancestor of B's branch.git worktree listshows 2+ worktrees; the file exists in one but not the other.
Note: this is distinct from [[multi-worktree-file-url-stale-content]] (browser opens stale file:// URL), [[subagent-bash-cd-wrong-worktree]] (subagent operates in the wrong cwd), and [[worktree-outer-ls-mistaken-for-main-state]] (parent dir listing not reflecting worktree state). Those are all "wrong working directory" issues; this one is "right working directory, file genuinely isn't there yet because it lives on a different branch."
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.
- 12d ago First seen · 334 lines · 79 tokens per session scan A 567c1d530644
cross-worktree-spec-handoff-via-checkout-paths is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 3,994 once invoked, about $0.0004 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.
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.
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.
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.