Borrowing it
Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/.claude/commands/begin-orchestration.mdgit clone --depth 1 https://github.com/bredmond1019/claude-sdk-rsWrote 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/commands/bredmond1019/claude-sdk-rs/begin-orchestration)<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/begin-orchestration"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/begin-orchestration/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/commands/bredmond1019/claude-sdk-rs/begin-orchestration"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/begin-orchestration.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 | $0.00039 | $0.09164 |
| Opus 5.5 | $0.00016 | $0.03666 |
| Sonnet 5.5 | $0.00008 | $0.01833 |
| Haiku 4.5 | $0.00004 | $0.00916 |
Grade A, and why
begin-orchestration 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 556 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Begin Orchestration — Open one lane of a multi-repo roadmap run
Wraps /orchestrate with the context a lane agent needs and the rules a concurrent run depends on.
/orchestrate knows how to drive a chain; it does not know which chain, why, what may not be
delegated, or who else is running right now. This command supplies that, then hands off.
One /begin-orchestration session drives one repo. Run several at once — that is the lane model.
Variables
$ARGUMENTS — flags, any order. --roadmap is required, plus one of --lane or --blocks.
Everything else resolves to a default.
--roadmap is mandatory on purpose. An earlier version inferred it from whichever epic was
focused, which is correct during a single-initiative week and silently wrong the moment two
initiatives overlap — the case where a lane driven against the wrong roadmap is hardest to notice.
Naming it costs one flag and removes a hidden coupling to epic status.
| Flag | Required | Default | What it does |
|---|---|---|---|
--roadmap <path|slug> |
yes | — | The roadmap this lane belongs to. A path is absolute or relative to BRAIN_ROOT and is honoured as given; a bare slug is resolved per Step 1C. |
--lane <path|name> |
one of | — | Lane record. A bare name (gtm) resolves to <roadmap-dir>/lane-<name>.json, authored against .claude/workflows/lane.schema.json (D71). |
--blocks <id ...> |
one of | — | Inline block IDs instead of a lane file. Space- or comma-separated. |
--repo <slug> |
no | inferred from cwd | Override only when inference is wrong. |
--isolation <worktree|no-worktree|auto> |
no | auto |
auto applies the policy table below. |
--plan-file <path> |
no | — | Spec source for /generate-tasks --from, when the blocks are not in master-plan.md. |
--engine <task|flow> |
no | per-block | Force one engine for the whole chain. |
--log <path> |
no | <roadmap-dir>/lane-log.jsonl |
Where to report integrated blocks. --log none disables. |
--execute |
no | off | Skip the dry-run confirmation and start immediately. |
--continue-on-fail |
no | off | Passed through to /orchestrate. |
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.
- 11d ago First seen · 556 lines · 39 tokens per session scan A e87f3ff72de0
begin-orchestration is a command published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 9,164 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 2026-10-26.
begin-orchestration compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| begin-orchestrationbredmond1019/claude-sdk-rs | Command | 23 | 1mo ago | Apache-2.0 | A | 39 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |