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/north-starnpx skills add fusebase-dev/fusebase-flow --skill north-stargit 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 | $0.00127 | $0.01378 |
| Opus 5 | $0.00063 | $0.00689 |
| Sonnet 5 | $0.00025 | $0.00276 |
| Haiku 4.5 | $0.00013 | $0.00138 |
Grade A, and why
north-star 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
North Star
Style: Mode-B-lite. Artifact-gated skill — inert unless
docs/north-star.mdexists.
Purpose
Keep all work aligned to the project's vision. When a project has been onboarded (docs/north-star.md exists), this skill reads it and checks that tasks, decisions, and fixes serve that vision — catching drift before it compounds. It is the canonical example of the artifact-gated pattern: ship complete, stay dormant until fed.
When to invoke
docs/north-star.mdexists AND a task / decision / fix is in progress.- Operator says "check the north star", "is this on-vision", "does this drift".
- During Specify / Plan / Decisions / Tasks / a non-trivial fix (alongside FR-20 zoom-out).
Do not invoke when
docs/north-star.mddoes NOT exist → silent no-op by default. The one narrow exception is the one-time D5 offer (step 6, at most once, only when the operator is clearly doing project work); after it fires (or is declined) stay silent. Never prompt repeatedly, never create the file. (Project simply hasn't been onboarded; that's fine.)- Trivial mechanical edits.
Required inputs
| Input | Where it lives | If missing |
|---|---|---|
| Project North Star | docs/north-star.md |
Skill is a no-op (default) — the sole absence-path output is the one-time D5 offer (step 6). Do not create it. (Onboarding via project-onboarding / /onboard creates it.) |
| Current work | spec / decision / task / fix in progress | nothing to check; exit |
Procedure
- Existence gate (MANDATORY FIRST STEP). If
docs/north-star.mddoes not exist → this skill contributes no check: skip steps 2-5. Default is silent no-op; the ONLY sanctioned output on the absence path is the one-time D5 offer (step 6). Do NOT create the file. Do NOT nag. - Read
docs/north-star.md(vision, audience, in/out scope, success, constraints). - Align-check the current work: does it serve the vision; is it in-scope; does it fit the audience (internal vs client); does it respect the constraints?
- Flag drift — via the Required output block below. If the work diverges (out-of-scope, wrong audience, against a constraint), say so plainly and recommend the on-vision alternative.
- Ambiguity → ask the operator in chat (FR-19); do not silently reinterpret the vision.
- Offer-once (D5) — sole absence-path output. Applies only when step 1 found no
docs/north-star.mdAND the operator is clearly doing project work AND no prior offer was made (if unsure whether one was, do not offer). Offer once: "No North Star is set — want to capture one (/onboard)? Or continue without." Silence or decline → permanent silent no-op for the rest of the project.
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 · 95 lines · 0 tokens per session scan A 53d83bae6f55
north-star is a skill published in the GitHub repository fusebase-dev/fusebase-flow (9 stars, last pushed 7d ago), licensed MIT. It adds 127 tokens to every session and 1,378 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.