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 concurrent-session-checkout-clobbers-shared-worktreegit 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/concurrent-session-checkout-clobbers-shared-worktree)<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/concurrent-session-checkout-clobbers-shared-worktree"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/concurrent-session-checkout-clobbers-shared-worktree/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/concurrent-session-checkout-clobbers-shared-worktree"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/concurrent-session-checkout-clobbers-shared-worktree.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 | $0.00214 | $0.01817 |
| Opus 5 | $0.00107 | $0.00908 |
| Sonnet 5 | $0.00043 | $0.00363 |
| Haiku 4.5 | $0.00021 | $0.00182 |
Grade A, and why
concurrent-session-checkout-clobbers-shared-worktree 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Concurrent session's git checkout clobbers your shared working directory
Problem
Two Claude Code sessions (or any two agents/people) operate in the same
working directory on the same clone. git checkout / git switch changes
HEAD for the entire working tree — it is not per-session. When session B
switches branches, session A's tree changes underneath it:
- Uncommitted edits to tracked files may be carried across, reverted, or left in a confusing half-state.
- Untracked files (new files you created) stay on disk but risk being swept
into session B's next
git add -A. - Edits get silently lost — e.g. a config field you added disappears.
It is invisible until something breaks: a function you wrote is "gone", a test errors on a symbol you defined, or a harness emits "file was modified, either by the user or by a linter" for a file you didn't expect to change.
Context / Trigger Conditions
- A file you edited reverted to an older version with no action from you.
git branch --show-currentis not the branch you were working on.git statuslists changes or untracked files you don't recognize.- Decisive:
git reflogshowscheckout: moving from <yours> to <other>that you never performed.
Solution
Do not keep fighting inside the shared directory — you will collide again. Isolate into a git worktree.
- Confirm the collision —
git reflog -5reveals the foreign checkout.git log <your-branch> --onelineconfirms your committed work is still safe on its branch (commits survive a checkout; only uncommitted work is at risk). - Create a worktree for your existing branch (not a new branch):
Place it outside the repo (a sibling dir) to avoidgit worktree add /path/outside/repo/my-worktree <your-branch>.gitignoreedits that would themselves collide. - Migrate uncommitted work into the worktree:
- Copy untracked files (
cpthe new files you created). - Re-apply tracked-file edits in the worktree (apply them fresh; the worktree has the clean branch tip).
- Re-apply any edit that was clobbered — recover it from conversation context.
- Copy untracked files (
- Clean your pollution out of the shared dir so the other session gets it
back as expected:
git checkout <files-you-modified>andrmyour untracked files (you copied them already). - Switch your session into the worktree and continue there.
- Commit early and often to your feature branch — committed work cannot be clobbered by a foreign checkout.
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 · 132 lines · 214 tokens per session scan A c8e2652321cb
concurrent-session-checkout-clobbers-shared-worktree is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed today), licensed MIT. It adds 214 tokens to every session and 1,817 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.