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/mock-server/mockserver-monorepo/worktreegit clone --depth 1 https://github.com/mock-server/mockserver-monorepoWhat 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 | $0.00021 | $0.00500 |
| Opus 5 | $0.00010 | $0.00250 |
| Sonnet 5 | $0.00004 | $0.00100 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
worktree scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Follow the worktree workflow in .opencode/rules/worktree-workflow.md. This command does Step 1 of that flow:
- Ensure
.worktrees/is gitignored. If not, add.worktrees/to.gitignoreand commit that change to master first. - Pick a short ID:
SHORT_ID="$(date +%Y%m%d-%H%M%S)-$(uuidgen | head -c 6)". - Create the worktree based on the current
origin/master:git fetch origin master --quiet git worktree add --quiet -b "agent/${SHORT_ID}" ".worktrees/agent-${SHORT_ID}" origin/master - Record the worktree path so the session can resume:
mkdir -p .tmp && echo ".worktrees/agent-${SHORT_ID}" > .tmp/active-worktree - Change working directory into the worktree for the rest of the session. All subsequent commands run inside the worktree.
- Tell the user clearly:
- The worktree path.
- That worktree isolation is the default for an independent session: work proceeds inside the worktree, and
git status/git diffis the primary signal. - To merge work back to master, run
/worktree-merge, which runs the 4 verification gates and the locked rebase.
If .tmp/active-worktree already exists, reuse it only if this same session created it (e.g. you are resuming after a restart) — then report that existing path instead of creating a second one. If the pointer may belong to a different concurrent session (you did not create that worktree in this session), do NOT adopt it — create a fresh worktree (new SHORT_ID) with your own branch instead, because two sessions sharing one tree overwrite each other's uncommitted work and can rebase away each other's commits. When ownership is uncertain, create a fresh worktree. See .opencode/rules/worktree-workflow.md → Rule (One session, one worktree — never reuse or adopt another session's).
If the user provided additional instructions: $ARGUMENTS
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.
- 2d ago First seen · 26 lines · 21 tokens per session scan A ac24dfedfbc3
worktree is a command published in the GitHub repository mock-server/mockserver-monorepo (4,961 stars, last pushed today), licensed Apache-2.0. It adds 21 tokens to every session and 500 once invoked, about $0.0001 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 commands, from other repositories
write-fixtures
../../skills/write-fixtures/SKILL.md.
bench
Refresh model grades (capability + price, from benchlm.ai and OpenRouter) or measure route latency through the proxy. Nothing runs automatically — this is the manual refresh.
status
Show cc-proxy router status — proxy liveness, configured providers, GLM/OpenRouter quota, and recent routing decisions.
bmad-architecture
Produce the architecture: a lean spine of invariants that keeps everything built from it consistent, projected into whatever format the work needs. Use when the user says "create the architecture", "create technical architecture", "architecture spine", or "create a solution design".
bmad-advanced-elicitation
Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.
bmad-agent-analyst
Strategic business analyst and requirements expert. Use when the user asks to talk to Mary or requests the business analyst.