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/install-deprecated)<a href="https://agentmods.dev/commands/restarter/lets-workflow/install-deprecated"><img src="https://agentmods.dev/badge/commands/restarter/lets-workflow/install-deprecated/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/install-deprecated"><img src="https://agentmods.dev/badge/commands/restarter/lets-workflow/install-deprecated.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 | $0.00013 | $0.01900 |
| Opus 5.5 | $0.00005 | $0.00760 |
| Sonnet 5.5 | $0.00003 | $0.00380 |
| Haiku 4.5 | $0.00001 | $0.00190 |
Grade C, and why
install-deprecated scanned grade C with 2 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 20d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/restarter/lets-workflow/main/scripts/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/restarter/lets-workflow/main/scripts/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Global Setup
One-time setup for new developers. Checks environment, installs plugins, then delegates to /lets:init for project setup.
Step 1: Check Environment
# Claude Code version
claude --version
# lets CLI binary (REQUIRED - hooks and statusline invoke it directly)
lets version 2>/dev/null || echo "lets CLI not found - install before continuing"
# GitHub CLI (optional)
gh --version 2>/dev/null || echo "gh CLI not found (optional - needed for LETS_PR_FLOW=github)"
gh auth status 2>/dev/null || echo "gh not authenticated (optional)"
If lets version is missing, the plugin's hooks and statusline will silently fail. Install before continuing:
# Curl one-liner — the usual end-user install (pulls a release archive, verifies the checksum)
curl -fsSL https://raw.githubusercontent.com/restarter/lets-workflow/main/scripts/install.sh | bash
which lets # verify $PATH
lets version
# Or from a clone — for contributors / source builds:
git clone https://github.com/restarter/lets-workflow && cd lets-workflow && make install
Still to come (tracked under epic lets-hdrdr): Homebrew (lets-odg13), winget+scoop (lets-hdrdr.1).
Step 2: Install Required Plugins
Install these plugins (check Claude Code docs for current installation method):
Required:
- beads - task tracking across sessions (by steveyegge) After installation, restart Claude Code.
Step 3: Global Settings
Disable Auto Compact
claude config set --global autoCompact false
Step 4: Initialize Current Project
Delegate to /lets:init for per-project setup (.lets/ structure, config, statusline, beads).
Run: /lets:init
Step 5: Explain Workflow
Session Flow
/lets:start -> Work -> /lets:check -> /lets:commit -> /lets:done -> /lets:end
Worktree: /lets:worktree create -> terminal -> /lets:start -> Work -> /lets:done -> /lets:end -> /lets:worktree remove
Team: /lets:team run -> one visible worker session per task -> each worker /lets:start ... /lets:done
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.
- 20d ago Changed 603244294aa2
- 23d ago Changed e06bd56de901
- 26d ago Changed 6686e9af9287
- 28d ago Changed 94e6a7a9e048
- 1mo ago Changed · +4 lines 841d09a74916
- 1mo ago Changed 9b72bb299ce5
- 1mo ago First seen · 167 lines · 13 tokens per session scan C 651dce503ad0
install-deprecated is a command published in the GitHub repository restarter/lets-workflow (17 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 1,900 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
todo
The quality-gated task list: tasks with real descriptions, testable acceptance criteria, and evidence — a task only closes when the controller agrees it is done.
develop
Implement skill development issues with TDD-governed workflow.
release-flow
Portable gated release flow — deterministic gate + vendor-agnostic independent reviewer, runnable from any harness.
triage-inbox
Sort application mail into the freehire tracker and drain the link queues.
retro
Score zforge's workflow performance on a feature.
audit-release
Diagnose release-readiness against the Starter Series quality bar — matched starter, version-vs-last-tag drift, CHANGELOG drift vs merged PRs, and publish-workflow kind. Read-only.