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 agentmods add skills/tlangridge/agent-swarm/git-worktreenpx skills add tlangridge/agent-swarm --skill git-worktreegit clone --depth 1 https://github.com/tlangridge/agent-swarmWhat 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 | $0.00031 | $0.00498 |
| Opus 5 | $0.00015 | $0.00249 |
| Sonnet 5 | $0.00006 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
git-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 3d 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
Git Worktree Isolation
Each agent works in a dedicated git worktree with its own branch. This prevents merge conflicts between agents working simultaneously.
Branch Convention
Your worktree branch follows the pattern: swarm/<agent-name>/<date>
For example: swarm/alice/20260304
Critical Rules
-
Do NOT switch branches. Your worktree is checked out to your assigned branch. Switching branches would break isolation. If you need to reference another branch, use
git difforgit logwith the branch name -- do not checkout. -
Do NOT run
git checkouton any branch other than your assigned one. The worktree system manages branches for you. -
Commit frequently. Since you are on your own branch, there is no risk of conflicting with others. Commit early, commit often.
Linking Branches to Tasks
When you start working on a task, link your branch:
swarm task update <id> --branch <your-branch>
This makes it visible in the dashboard which task is associated with which branch.
Creating Pull Requests
When your task is complete:
- Commit and push your branch
- Create a PR targeting the main branch
- Link the PR to your task:
swarm task update <id> --pr <number> --pr-url <url> - If working on a GitHub issue, link that too:
swarm task update <id> --issue <number> --issue-url <url>
Working with Other Agents' Branches
If you need to see what another agent has done:
git log swarm/<other-agent>/<date> --oneline -10
git diff main..swarm/<other-agent>/<date> -- <file>
Do NOT merge other agents' branches into yours unless explicitly instructed by the lead.
Handling Merge Conflicts
If your branch falls behind main and you need updates:
git fetch origin
git merge origin/main
Resolve any conflicts in your worktree. If conflicts are complex, notify the lead via swarm msg.
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.
- 3d ago First seen · 67 lines · 31 tokens per session scan A 92e676e2fd40
git-worktree is a skill published in the GitHub repository tlangridge/agent-swarm (5 stars, last pushed 6mo ago), licensed MIT. It adds 31 tokens to every session and 498 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…