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 commands/captainme-ai/lead-dev-os/create-worktreegit clone --depth 1 https://github.com/CaptainMe-AI/lead-dev-osWhat 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 | $0.00000 | $0.00129 |
| Opus 5 | $0.00000 | $0.00064 |
| Sonnet 5 | $0.00000 | $0.00026 |
| Haiku 4.5 | $0.00000 | $0.00013 |
Grade A, and why
create-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
Follow these steps to create a git worktree.
-
Get the current project's folder name.
-
Create a folder adjacent to the current project's folder and name it {current project folder name}-worktrees. For example, if the current project folder is named myapp, create folder called myapp-worktrees. Both myapp and myapp-worktrees should have the same parent folder.
-
Create a git worktree and branch named $ARGUMENTS from the main project folder and save it inside the {current project folder name-worktrees folder that was created.
-
cd into the new $ARGUMENTS worktree folder
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 · 13 lines · 0 tokens per session scan A fceede2df375
create-worktree is a command published in the GitHub repository CaptainMe-AI/lead-dev-os (2 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 129 tokens. 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 commands, from other repositories
hf.audit-code
Run a comprehensive code quality audit across the entire repo. Dynamically analyzes source code for dead code, complexity, duplication, error handling gaps, type safety issues, class cohesion, and method size. Creates GitHub issues for findings so HydraFlow can process them.
hf.audit-tests
Run a comprehensive test quality audit across the entire repo. Analyzes test naming, structure, hygiene, factory usage, fluent builder patterns, anti-patterns, coverage gaps, and flaky patterns. Creates GitHub issues for findings so HydraFlow can process them.
hf.audit-integration-tests
Run a comprehensive integration test audit across the entire repo. Dynamically discovers external dependencies in source code, inventories existing integration tests, identifies coverage gaps, flags ugly/outdated tests, and creates GitHub issues for findings.
hf.issue
Take a rough description from the user, research the relevant codebase, and create a well-structured GitHub issue with full context, file references, and acceptance criteria.
hf.audit-hooks
Audit all Claude Code hooks (.claude/settings.json and .claude/hooks/.sh) for correctness, efficiency, and gating opportunities. Launch a single agent that reads everything and reports findings.
hf.memory
Scan the current conversation for architectural decisions, bug root causes, configuration choices, codebase patterns, and workflow preferences. Write each as a memory item to the local JSONL store for ingestion by the memory sync worker.