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/fusebase-dev/fusebase-flow/project-onboardingnpx skills add fusebase-dev/fusebase-flow --skill project-onboardinggit clone --depth 1 https://github.com/fusebase-dev/fusebase-flowWhat 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 | $0.00116 | $0.01154 |
| Opus 5 | $0.00058 | $0.00577 |
| Sonnet 5 | $0.00023 | $0.00231 |
| Haiku 4.5 | $0.00012 | $0.00115 |
Grade A, and why
project-onboarding 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Onboarding
Style: Mode-B-lite. Product Owner role.
Purpose
Capture the operator's project vision once, into durable artifacts that steer every later session. This is the engine that creates the Column-B artifacts the input-dependent skills read. Onboarding is operator-triggered and optional — if never run, Flow operates generically with zero project artifacts (no clutter).
When to invoke
- Operator runs
/onboardor says "onboard my project", "set up my project for my vision", "capture my North Star". - Operator drops research into
docs/**/research/and asks the PO to build project docs from it. - Re-run any time the vision evolves ("update my North Star").
Do not invoke when
- Ordinary ticket work (use
requirements-specification). - Writing application code (FR-01).
- On install / automatically — onboarding never auto-runs.
Required inputs
| Input | Where it lives | If missing |
|---|---|---|
| Operator answers to discovery questions | chat | ask in chat text (FR-19); do not invent |
| Optional research | docs/**/research/ |
proceed without; note it |
| Artifact scaffold | templates/north-star.md |
stop; template missing |
Procedure
- Adopt Product Owner role; self-attest (FR-01..FR-27). Do not write code.
- Adoption level — ask the operator (FR-19): (a) one-line North Star, (b) full discovery interview, (c) skip. Respect "skip" — create nothing.
- Discovery interview (chat text, one topic at a time): Who are you / your edge? · Audience: internal team vs external clients? · Product vision / the apps to build? · Domain / industry? · What does success look like? · Hard constraints?
- Ingest research if present in
docs/**/research/— summarize, cite; never invent domain facts. - Write
docs/north-star.mdfromtemplates/north-star.md, populated with the operator's answers +last_updated:today. Only write content the operator actually provided. - Fill
AGENTS.md§ Project-specific values (<placeholder>fields) where the operator gave concrete values. - Register for discovery: confirm
docs/north-star.mdis at a path the session-start scan globs (it is). No separate registry needed in v1. - Audience surfaces (if the operator defines them): write
docs/audience.mdfromtemplates/audience.md— the substrate theclient-vs-internalskill guards on (client-facing = simple/guided/trust-first; internal = robust controls). - Offer next (FR-17): "North Star captured — want to define audience surfaces, or start a ticket?" Do not over-create artifacts unprompted.
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 · 91 lines · 116 tokens per session scan A bd0eb1bc5f11
project-onboarding is a skill published in the GitHub repository fusebase-dev/fusebase-flow (9 stars, last pushed 7d ago), licensed MIT. It adds 116 tokens to every session and 1,154 once invoked, about $0.0006 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 skills, from other repositories
adobe-express-core
Adobe Express environment essentials, two-runtime architecture, project setup, and MCP server configuration. Use when starting add-on development, understanding iframe vs sandbox boundaries, configuring MCP servers, setting up local projects, or validating manifest configuration.
adobe-express-monetization
Monetize Adobe Express add-ons with subscriptions and payments. Use when designing checkout flows, defining subscription tiers, implementing webhook verification, managing entitlements, or securing backend billing logic.
adobe-express-spectrum-ui-ux
Build or review Adobe Express add-on panel UI with Spectrum patterns, stack selection guidance (raw SWC, swc-react, React Spectrum), Express theme setup, state and navigation design, and actionable UX quality checks. Use when implementing or auditing panel layouts, interaction states, multi-screen flows, and…
adobe-express-cors-and-backend
Diagnose and fix CORS errors between Adobe Express add-on UI and backend APIs across local development, private listing, and public listing stages. Use when browser requests fail with preflight, Access-Control-Allow-Origin, Access-Control-Allow-Headers, or OPTIONS issues; when moving from localhost to hosted add-on…
adobe-express-document-manipulation
Create and modify document content in Adobe Express add-ons using Document SDK. Use when planning document operations, inserting shapes/text/media, sequencing sandbox commands, or troubleshooting document edits.
adobe-express-oauth-authentication
Implement OAuth 2.0 and authentication flows for Adobe Express add-ons. Use when connecting to cloud providers (Dropbox, OneDrive, Google Drive), managing tokens, storing credentials, or designing login surfaces.