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/bybren-llc/safe-agentic-workflow/start-workgit clone --depth 1 https://github.com/bybren-llc/safe-agentic-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/bybren-llc/safe-agentic-workflow/start-work)<a href="https://agentmods.dev/commands/bybren-llc/safe-agentic-workflow/start-work"><img src="https://agentmods.dev/badge/commands/bybren-llc/safe-agentic-workflow/start-work.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00525 |
| Opus 5 | $0.00000 | $0.00262 |
| Sonnet 5 | $0.00000 | $0.00105 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
start-work 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 4d 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
You are starting work on a new Linear ticket.
Workflow Authority: This harness command provides execution steps. CONTRIBUTING.md is the northstar for conventions (branch naming, commit format, SAFe patterns). Follow both:
Pre-Flight Checklist
-
Linear Ticket Exists?
- If no ticket number provided in arguments, ask user for Linear ticket number
- Verify ticket exists in Linear using
mcp__{{MCP_LINEAR_SERVER}}__get_issue - Confirm ticket is in appropriate status (Todo, In Progress)
-
Stop-the-Line: AC/DoD Check (MANDATORY)
- Verify ticket has Acceptance Criteria or Definition of Done
- If AC/DoD is missing or unclear:
- STOP - Do not proceed with implementation
- Route back to BSA/POPM to define AC/DoD
- Dev agents are NOT responsible for inventing AC/DoD
- Work begins ONLY when AC/DoD exists
-
Branch Naming
- Format:
{{TICKET_PREFIX}}-{number}-{short-description} - Must start with {{TICKET_PREFIX}}- and ticket number
- Use lowercase with hyphens
- Format:
-
Start from Latest Dev
- Ensure starting from clean dev branch:
git checkout dev && git pull origin dev - Verify no uncommitted changes
- Ensure starting from clean dev branch:
-
Create Feature Branch
- Create branch:
git checkout -b {{TICKET_PREFIX}}-{number}-{description} - Confirm branch created successfully
- Create branch:
Workflow
If argument provided ($1):
- Use as ticket number (e.g.,
/start-work 347→ {{TICKET_PREFIX}}-347) - Fetch ticket details from Linear
- Suggest branch name based on ticket title
- Execute checkout workflow
If no argument:
- Ask user for Linear ticket number
- Proceed with workflow
Success Criteria
- ✅ Linear ticket verified
- ✅ AC/DoD confirmed (Stop-the-Line gate passed)
- ✅ On latest dev branch
- ✅ Feature branch created with correct naming
- ✅ Ready to begin work
Report status and any blockers. If AC/DoD is missing, report blocker and route to BSA.
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.
- 4d ago First seen · 62 lines · 0 tokens per session scan A 11f5d5b2a9b5
start-work is a command published in the GitHub repository bybren-llc/safe-agentic-workflow (406 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 525 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 2026-08-30.
Other commands, from other repositories
help
Category: System Syntax: /help [command|topic].
translate-docs
翻译项目文档到指定语言.
review-tasks
审查任务的忠实度、可执行性、依赖关系与验证.
clarify
Reduce spec ambiguity via targeted questions with adaptive auto-invocation (planning is 80% of success).
tasks-to-issues
将现有任务转换为该功能的可操作 GitHub Issues.
ultrathink
Enter deep craftsman mode - question everything, plan like Da Vinci, craft insanely great solutions, then materialize to roadmap.