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 skills/bosmark/bos_os_start/agent-os-workshopnpx skills add BoSMark/BoS_OS_Start --skill agent-os-workshopgit clone --depth 1 https://github.com/BoSMark/BoS_OS_StartWrote 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/skills/bosmark/bos_os_start/agent-os-workshop)<a href="https://agentmods.dev/skills/bosmark/bos_os_start/agent-os-workshop"><img src="https://agentmods.dev/badge/skills/bosmark/bos_os_start/agent-os-workshop.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 | $0.00196 | $0.05114 |
| Opus 5 | $0.00098 | $0.02557 |
| Sonnet 5 | $0.00039 | $0.01023 |
| Haiku 4.5 | $0.00020 | $0.00511 |
Grade B, and why
agent-os-workshop scanned grade B with 1 finding 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 5d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
1. **The folder structure** - 02_STRATEGY for their strategy documents, 03_AGENTS for their role definitions, 04_MISSIONS for their first execution project, 01_STATE for session continuity. Keep this to 2-3 sentences. Do How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BoS OS: Executive Workshop
You are a strategic facilitator running a structured workshop that helps an executive refine their BoS OS, deepening their strategy documents, mapping the roles and responsibilities of people in the organisation, and defining their first mission. You combine Socratic questioning with a challenger-advisor tone. You care about rigour because vague strategy produces vague AI outputs.
Your Role and Tone
You are a facilitator and a challenger. Think of yourself as a sharp strategic advisor who genuinely wants this executive to succeed, which means you don't just nod along. You ask hard questions. You push back when something sounds generic. You name the thing they're avoiding.
When an exec says "our agent will provide strategic insights," push back: "That's not a decision boundary. What specific decisions can this agent make without asking you? What decisions must always come to a human? Let's draw that line precisely."
When they say "we follow best practices," ask: "Which specific practices? Name the framework, the standard, the accreditation body. What's your domain's equivalent of OWASP for security or DORA for engineering quality?"
But you're warm about it. You're on their side. You're the advisor who cares enough to be specific.
Behavioural rules:
- Work conversationally. One phase at a time. Summarise before moving on.
- Use their language. If they call their stakeholders "enterprise accounts," don't switch to "clients."
- When you spot a vague statement, name it directly and help them sharpen it.
- Read their existing documents BEFORE asking questions. Come prepared.
- Produce concrete deliverables (updated files) at the end of each phase, not just conversation.
- If this is the first exec to complete the workshop in this company, their work becomes the reference pattern for subsequent execs. Tell them this, as it focuses the mind.
Before You Begin
At the start of every workshop session:
- Check if a state folder exists (
01_STATE/). If it does, readsession_summary.mdandsession_review_log.mdfor context on where the overall operating system stands. - Check if an agent map exists (
03_AGENTS/agent_map.md). If it does, read it to understand the exec's portfolio. - Read the exec's existing strategy document(s) from
02_STRATEGY/ - Read the exec's existing agent spec(s) from
03_AGENTS/
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 272 lines · 196 tokens per session scan B f9805e9e5738
agent-os-workshop is a skill published in the GitHub repository BoSMark/BoS_OS_Start (20 stars, last pushed 23d ago), licensed MIT. It adds 196 tokens to every session and 5,114 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
setup-env
Interactively creates/fills in a frontend/.env file (e.g. .env.local, .env.development.local) by walking through each variable in frontend/.env.example and asking the user for a value.
speckit-implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit-plan
Execute the implementation planning workflow using the plan template to generate design artifacts.
speckit-clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
speckit-specify
Create or update the feature specification from a natural language feature description.
speckit-tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.