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 gaelic-ghost/socket --skill coordinate-worktrees-and-threadsgit clone --depth 1 https://github.com/gaelic-ghost/socketWrote 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/gaelic-ghost/socket/coordinate-worktrees-and-threads)<a href="https://agentmods.dev/skills/gaelic-ghost/socket/coordinate-worktrees-and-threads"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/coordinate-worktrees-and-threads/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/gaelic-ghost/socket/coordinate-worktrees-and-threads"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/coordinate-worktrees-and-threads.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 | $0.00044 | $0.00379 |
| Opus 5.5 | $0.00018 | $0.00152 |
| Sonnet 5.5 | $0.00009 | $0.00076 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade A, and why
coordinate-worktrees-and-threads 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.
What it actually says
Coordinate Worktrees And Threads
Establish repository ownership before a worker begins. A thread is not a worktree, and a branch is not permission to make shared Git mutations.
Launch Record
For every worker, record the worker/task identity, coordinator, repository and base commit, worktree path, branch, read/write scope, allowed Git operations, validation lane, output/merge target, final report route, and retention or cleanup decision.
Rules
- Give parallel writers disjoint files or directories and separate worktrees.
- When a Codex-managed worktree versus a plain Git worktree is itself a
decision, hand that host-specific choice to
repository-skills:codex-gui-worktree-workflow; retain this skill's host-neutral ownership record in either case. - Serialize Git operations that change shared repository state. A worker must not assume it owns tags, merges, release branches, deletion, or cleanup.
- Serialize heavy build and test lanes unless the environment explicitly proves they are independent and safe.
- Keep final integration, conflict resolution, release, branch accounting, and cleanup with the coordinator unless the user explicitly assigns them.
- When a worker returns, report branch/worktree state, commits, validation, uncommitted changes, artifacts, and the recommended integration action.
Completion
The coordinator explicitly chooses whether to retain the worker thread or worktree for follow-up, merge/preserve its result, archive it, or remove it after branch accounting. Never delete a worktree or branch merely because a worker says it is done.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 40 lines · 44 tokens per session scan A 6c3b4f7f1494
coordinate-worktrees-and-threads is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 379 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
branch-and-worktree-workflow
Isolates feature work in its own branch or worktree and integrates it cleanly when done. Use this when starting work that should not disturb the current workspace, when several efforts must proceed in parallel on one repository, or when implementation is finished and the change needs merging, rebasing, or splitting…
craft
Use when a product idea is still vague and needs to become a clear definition of what to build — "let's craft an app like X", "help me define what I actually want", "clarify this idea before we plan it". Also use before planning or implementation when requirements, UX, domain behaviour, or technical preferences have…
agile-ledger-workspace
Owns the Agile-Ledger ledger repository — the separate repo that holds one folder per code repo, so code repos stay clean. Create the ledger repo, register repositories into it, migrate a pre-2.0 in-repo Agile-Ledger/ folder, discover repositories on a GitHub org (including ones nobody told you about), run a single…
pipeline
Use when the user asks to take a substantial feature from an initial idea through implementation in one mostly autonomous run.
turbo-pipeline
Use when the user wants a feature built end to end after answering one round of questions and then being left alone — "turbo", "ask me once, then just build it", "I'll answer up front, don't come back to me", "decide the rest yourself". Not for a run that wants a spec approval and no tests (superb:fast-pipeline), one…
pipeline-auto
Use when the user wants a substantial feature taken from idea through implementation in one run with as little interruption as possible ("just build it", "don't keep asking me"), or when controlling such a run and a worker question, quorum responses, the drift budget, a human decision, a review class or a completeness…