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/vijayatechlabs/openstart/onboardgit clone --depth 1 https://github.com/vijayatechlabs/openstartWhat 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 | $0.00020 | $0.00297 |
| Opus 5 | $0.00010 | $0.00148 |
| Sonnet 5 | $0.00004 | $0.00059 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
onboard 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 2d 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 running the OpenStart onboarding flow for the current project.
Follow .ai/framework/ONBOARD.md exactly. It is the canonical, state-aware
pipeline: Discover → Plan → ⟨human approves⟩ → Apply → Verify.
Non-negotiable for this run:
- Make all mechanical decisions yourself; ask the human once — to approve the Plan (Phase 2) — surfacing only the 2–3 genuinely ambiguous choices with a recommended default each.
- Writes are scoped to
.ai/,.claude/commands,.claude/skills, and the root agent stubs. Never touch application code. - Work on branch
chore/onboard-openstart. Do not commit or push — leave a clean diff for the human to review. - Never invent facts; mark unknowns as
TODO:. - Use
.ai/framework/sync.sh --dry-runfor the Phase 2 preview and.ai/framework/sync.shfor the Phase 3 mechanics — don't hand-copy files.
If .ai/framework/ doesn't exist yet (brownfield), bootstrap per the
"Bootstrapping a brownfield project" section of .ai/framework/ONBOARD.md.
Start at Phase 0 now.
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.
- 2d ago First seen · 26 lines · 20 tokens per session scan A c797cde23e71
onboard is a command published in the GitHub repository vijayatechlabs/openstart (5 stars, last pushed 4d ago), licensed MIT. It adds 20 tokens to every session and 297 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
output-folder
Print + open the user-visible DMP output folder for a brand (/Documents/DigitalMarketingPro/{brand}/). Direct answer to "where did my engagement deliverables save?".
doctor
Per-action readiness diagnostic. Shows which campaign-audit and launch-campaign actions are live (manifest-ready) vs blocked (stub-unconfigured) in the current environment, with one-step setup hints for the blocked ones. Now includes model-registry freshness + Cowork+Drive routing status.
seo-audit
Run a comprehensive SEO audit — technical health, on-page, content gaps, E-E-A-T, link profile, and competitor benchmarking.
content-engine
Draft blog posts, ad copy, emails, social media, landing pages, and video scripts with brand voice and SEO.
performance-report
Generate a marketing performance report with KPI tracking, trend analysis, anomaly detection, and recommendations.
keyword-cluster
Build a pillar+spokes content cluster plan from seed keywords with SERP-overlap clustering, intent grouping, internal-link map, and a four-gate quality scorecard.