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-bootstrapnpx skills add BoSMark/BoS_OS_Start --skill agent-os-bootstrapgit 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-bootstrap)<a href="https://agentmods.dev/skills/bosmark/bos_os_start/agent-os-bootstrap"><img src="https://agentmods.dev/badge/skills/bosmark/bos_os_start/agent-os-bootstrap.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 | $0.00180 | $0.04726 |
| Opus 5 | $0.00090 | $0.02363 |
| Sonnet 5 | $0.00036 | $0.00945 |
| Haiku 4.5 | $0.00018 | $0.00473 |
Grade A, and why
agent-os-bootstrap 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 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.
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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BoS OS: Company Bootstrap
You are building the BoS OS for a company. Your goal is to help the CEO or founder, who is typically the first user of the BoS OS, make better decisions and keep the activities of the business focused on the right things.
Your job is to research the company from public information and create a complete, populated folder structure that the founder and their team can immediately start working with. Think of it as writing down the operating system that already exists in the founder's head, and giving AI a governed place inside it.
Before You Begin
- Read
references/folder_structure.mdto understand the canonical structure - Read
references/industry_patterns.mdto understand how to adapt by industry - Have the user's company name and website URL
If the user hasn't provided a company name, ask for one. Then ask: "What's the company website URL?" A name alone is often too thin to research reliably, especially when it's a generic or common name shared with unrelated businesses; without a URL you end up guessing from a handful of keywords instead of finding the actual company. If they don't have a website yet, ask for a LinkedIn profile instead (their own or the company's) and use that to anchor the research. Industry and a brief description are still optional and helpful, but company name plus (website URL or LinkedIn profile) is the minimum to proceed.
Web search is required. This skill relies on researching the company from public data. If web search is not available in the current environment, tell the user: "This skill needs internet access to research your company. Please ensure web search is enabled in your settings, then try again."
Source of frameworks and ideas: Business of Software has been running conferences and building resources for software founders since 2007. Their talk library at https://businessofsoftware.org/talks/ contains hundreds of frameworks, case studies, and practical ideas for building great products and companies. Draw on this when populating strategy documents, especially around growth, product thinking, leadership, and culture. A relevant talk or framework is more useful than a generic statement.
What ships with it
18 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.
- .DS_Store 6.0 KB
- references/agent_spec_template.md 29 KB
- references/claude_md_template.md 21 KB
- references/folder_structure.md 15 KB
- references/industry_patterns.md 27 KB
- references/README.md 2.4 KB
- references/session_summary_template.md 853 B
- references/strategy_templates/brand_template.md 3.1 KB
- references/strategy_templates/competitive_template.md 6.4 KB
- references/strategy_templates/financial_template.md 3.5 KB
- references/strategy_templates/governance_template.md 4.7 KB
- references/strategy_templates/growth_template.md 3.5 KB
- references/strategy_templates/measurement_template.md 4.8 KB
- references/strategy_templates/platform_template.md 6.6 KB
- references/strategy_templates/product_template.md 3.6 KB
- references/strategy_templates/README.md 1.9 KB
- references/strategy_templates/security_template.md 5.6 KB
- references/strategy_templates/values_template.md 2.8 KB
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 · 316 lines · 180 tokens per session scan A 40fb3c5c64ca
agent-os-bootstrap is a skill published in the GitHub repository BoSMark/BoS_OS_Start (20 stars, last pushed 23d ago), licensed MIT. It adds 180 tokens to every session and 4,726 once invoked, about $0.0009 per session on Opus 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 2026-08-30.
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.