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.
git clone --depth 1 https://github.com/restarter/lets-workflowWrote 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/restarter/lets-workflow/hub)<a href="https://agentmods.dev/commands/restarter/lets-workflow/hub"><img src="https://agentmods.dev/badge/commands/restarter/lets-workflow/hub/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/restarter/lets-workflow/hub"><img src="https://agentmods.dev/badge/commands/restarter/lets-workflow/hub.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 | $0.00030 | $0.01212 |
| Opus 5.5 | $0.00012 | $0.00485 |
| Sonnet 5.5 | $0.00006 | $0.00242 |
| Haiku 4.5 | $0.00003 | $0.00121 |
Grade A, and why
hub 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hub
One session that looks across the projects Orca knows: which orchestrators exist, which are alive, a read-only answer from a stopped one, or waking one in a visible Orca terminal when the work needs a human at its gates. An Orca addon: it runs only with LETS_LAUNCHER=orca.
IMPORTANT: If the spec below invokes any deferred tool (e.g.
AskUserQuestion), you MUST load and call it as specified. Never skip the call, never substitute a default answer of your own — the tool invocation is part of the contract. This is critical.
Step 1: Preflight (before any lets call)
[ "{LETS_LAUNCHER}" = "orca" ] || echo HUB_NEEDS_ORCA
HUB_NEEDS_ORCA -> print one line /lets:hub is an Orca addon - pick the Orca launcher in /lets:init (LETS_LAUNCHER=orca) and stop. Otherwise:
lets orca status --json
Not running (status.running=false or a reason) -> orca_unavailable plus the reason; stop.
Step 2: List
lets peers who --orca-repos --json
Go validates every repo Orca lists and tags each row with repo_index; later calls pass --repo-index <n>, never a path. A project's orchestrators are the names recorded in its merge-branch task-state, and only when none of them is live the <repo>-orc[-<scope>] convention. Render one row per orchestrator - live ones from peers[], stopped ones from last_orchestrators[]:
| project (repos[index].name) | orchestrator | scope | alive | last seen |
Name every degraded[] entry in one line each. A project with several orchestrators lists each.
Step 3: Route the request
Pick the target: the orchestrator the user named; else, when the project has several:
AskUserQuestion(
questions=[{
question: "Which orchestrator of {project}?",
header: "Orchestrator",
options: [ /* up to 3: label = name, description = "{scope} - {alive | stopped}" */ ],
multiSelect: false
}]
)
Classify the request, and when unsure treat it as gated. Every message to a live orchestrator goes by its NAME from this run's listing, with via=hub: the orc skill sends outside the hub's own repo only to a row this hub run printed. A row marked duplicate_name cannot be addressed by name - say so and stop for it.
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 Changed · -1 lines 150c2dbc6818
- 1mo ago First seen · 85 lines · 30 tokens per session scan A d616e3564601
hub is a command published in the GitHub repository restarter/lets-workflow (17 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 1,212 once invoked, about $0.0001 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 2026-09-16.
Other commands, from other repositories
audit-security
Check baseline CI security hygiene against the Starter Series bar — gitleaks, CodeQL, dep audit, license check, --ignore-scripts, Dependabot grouped, secret-scanning, claude-code-security-review, claude-security-guidance. Read-only, complementary to Anthropic's in-session security guidance plugin.
code-quality-plan-creator
LSP-powered architectural code quality analysis - works with any executor (loop or swarm).
mr-description-creator
Generate and apply MR/PR description directly via gh or glab CLI (project).
agy-review
Send the current change set to Antigravity (agy) for a senior-reviewer code review.
review
Two-stage code review (spec compliance + code quality).
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.