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/entityprocess/allagents/worktreenpx skills add EntityProcess/allagents --skill worktreegit clone --depth 1 https://github.com/EntityProcess/allagentsWhat 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 | $0.00038 | $0.00392 |
| Opus 5 | $0.00019 | $0.00196 |
| Sonnet 5 | $0.00008 | $0.00078 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
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 yesterday.
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 Worktrees
Resolve this skill's directory, then invoke its bundled scripts/worktree.sh. Pass -C <repo> when the shell is not already inside the target repository.
Add
<skill-directory>/scripts/worktree.sh -C <repo> add <branch> [start-point]
The script:
- uses an existing local branch when present;
- creates a tracking branch when
<remote>/<branch>exists; - otherwise creates the branch from
start-point, the remote default branch, orHEAD; - prints the created worktree path.
Fetch the remote before adding when the worktree must start from its latest state:
git -C <repo> fetch origin
<skill-directory>/scripts/worktree.sh -C <repo> add feat/example origin/main
Worktrees default to <repo>__worktrees/<branch-with-slashes-as-dashes>. Set WORKTREE_ROOT to use another parent and WORKTREE_REMOTE to use a remote other than origin.
Remove
<skill-directory>/scripts/worktree.sh -C <repo> remove <branch-or-path>
<skill-directory>/scripts/worktree.sh -C <repo> remove --force <branch-or-path>
Normal removal preserves Git's dirty-worktree protection. Use --force only when discarding the worktree's uncommitted files is intended. Removal unregisters and deletes the worktree directory; it leaves the branch intact.
An add is complete when the script prints the new path and git -C <repo> worktree list contains it. A removal is complete when that path is absent.
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.
- yesterday First seen · 42 lines · 38 tokens per session scan A f40ac45cd029
worktree is a skill published in the GitHub repository EntityProcess/allagents (11 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 392 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 2026-08-30.
Other skills, from other repositories
purchasing
Create approved purchase orders with the create-purchase-order tool.
refunds
Check refund eligibility and use the refund-order tool safely.
document-service
This skill should be used when the user asks to "analyze this codebase", "document this service", "generate technical docs", "I inherited this code", "help me understand this system", "create docs for this project", "what does this system look like", "onboard me to this codebase", "this codebase has no docs"…
aws-step-functions
Build workflows with AWS Step Functions state machines using the JSONata query language. Covers Amazon States Language (ASL) structure, state types, variables, data transformation, error handling, AWS service integration, and migrating from the JSONPath to the JSONata query language.
hyperpod-version-checker
Check and compare software component versions on SageMaker HyperPod cluster nodes - NVIDIA drivers, CUDA toolkit, cuDNN, NCCL, EFA, AWS OFI NCCL, GDRCopy, MPI, Neuron SDK (Trainium/Inferentia), Python, and PyTorch. Use when checking component versions, verifying CUDA/driver compatibility, detecting version mismatches…
directory-management
Manages project directory setup and artifact organization. Use when starting a new project, resuming an existing one, or when a PLAN.md needs to be associated with a project directory. Creates the project folder structure (specs/, scripts/, notebooks/, manifests/, agentmemory/) and resolves project naming.