Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

Journey Substrate

skill · butterbase-ai/butterbase-skillsMIT licenceAudited 14 Oct 2026 · source b9d383eb75ba

★ 535pushed 9 days ago
✓SAFEGrade B · 89/100 · 14 Oct 2026 · b9d383e
535repo stars · whole butterbase-ai/butterbase-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit b9d383eb75ba and found no filesystem, network or shell access and no hard-coded secrets. What it does: Use as the optional substrate-linking stage of the Butterbase journey, after deploy and before submit. Asks whether to connect the deployed app to the owner's substrate (so functions get ctx.substrate). Skipped by…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Journey Substrate (butterbase-ai/butterbase-skills)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/butterbase-ai/journey-substrate

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha b9d383eb75ba · 14 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherbutterbase-ai GitHub organizationOwner of the repository this skill is read from
  • Source folderbutterbase-ai/butterbase-skills/skills/journey-substrateThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdictb9d383eb75baA new audit runs when the source changes
  • Repository statusNot archivedLast push 9 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Use as the optional substrate-linking stage of the Butterbase journey, after deploy and before submit. Asks whether to connect the deployed app to the owner's substrate (so functions get ctx.substrate). Skipped by…

---
name: journey-substrate
description: Use as the optional substrate-linking stage of the Butterbase journey, after deploy and before submit. Asks whether to connect the deployed app to the owner's substrate (so functions get ctx.substrate). Skipped by default in hackathon mode.
---

# Journey Substrate Stage (optional)

Connect the deployed app to the owner's substrate so functions get `ctx.substrate` injected at cold start. Skip if the user has no AI-agent / memory use case.

## When to use

Invoke automatically when the journey orchestrator's cursor reaches `substrate`. The row is optional in the checklist; skip silently if the user declines.

## Procedure

0. **Refresh docs.** Call `butterbase_docs` with `topic: "substrate"`. If the plan mentions AI memory / agent state / cross-session knowledge, also WebFetch `https://docs.butterbase.ai/substrate`. Skip if `docs/butterbase/03b-docs-cache.md` already covers `substrate`.

1. **Confirm.** Ask the user:
   > "Connect `<app_id>` to your substrate? This lets the app's functions read/write your agent memory via `ctx.substrate`. You can disable later. (yes / skip)"

   Default: **skip**.

2. **On skip:** mark the row `- [x] substrate (skipped — no agent memory needed)` in `docs/butterbase/00-state.md`. Write `docs/butterbase/04b-substrate.md` with one line: `Skipped on <date>.` Return.

3. **On yes:**
   a. If `platform_users.substrate_provisioned_at` is NULL for the caller, call `POST /v1/me/substrate/provision` first (or invoke whatever MCP wrapper exists — check `butterbase_docs` topic `substrate`).
   b. Link the app. Use whichever surface you have:
      - **MCP:** `manage_app` with `{ action: "link_substrate", app_id: "<app_id>" }`.
      - **CLI:** `butterbase apps link-substrate <app_id>`.
      - **REST (curl):** `POST /v1/me/apps/<app_id>/substrate-link` with empty body and `Authorization: Bearer <bb_sk_*>` for the app owner. The route enforces caller == app owner and sets `apps.substrate_user_id` to the caller's id.
   c. Verify: `manage_app` with `{ action: "get_config", app_id: "<app_id>" }` and assert `substrate_user_id` is non-null.
   d. Smoke: invoke any HTTP function the app already has and check `ctx.substrate` is defined (if the function logs it). If no function exists yet, skip the smoke and note in the artifact.

4. **Write artifact.** `docs/butterbase/04b-substrate.md`:

   ```markdown
   ---
   linked_at: <ISO>
   app_id: <id>
   substrate_user_id: <id>
   ---

   # Substrate Linkage

   - App linked at <ISO>
   - Substrate user ID: <id>
   - Smoke: <pass / skipped — no function yet>
   ```

5. **Update state.** Tick the `substrate` row in `00-state.md`.

## Anti-patterns

- ❌ Auto-linking without asking. Substrate is a privacy-sensitive surface.
- ❌ Linking before the app has any function deployed. Wait until `journey-functions` has run.
- ❌ Forgetting to handle the "substrate not yet provisioned" case. Lazy provisioning is by design.

Excerpt, first 2,961 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit b9d383e

Download folder ↗
git clone https://github.com/butterbase-ai/butterbase-skills
git -C butterbase-skills checkout b9d383eb75ba

The author documents no install command, so this uses the repository directly. Our verdict covers commit b9d383eb75ba only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source b9d383eb75ba

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/butterbase-ai/journey-substrate/badge.svg)](https://modelsatlas.com/skills/butterbase-ai/journey-substrate/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

project-artifact✓SAFE

anthropics/claude-plugins-official

Generate and publish a project status artifact — an opinionated, tabbed status page for a project too big for one update (overview & success criteria, the workstream sequence, next steps, plus background, plan, risks &…

★ 46kGrade B
receipts✓SAFE

anthropics/claude-plugins-official

Generate a personal Claude Code usage & impact report ("receipts") from this machine's local session transcripts — for justifying Claude Code usage/spend to a manager, self-review, or "what have I been using this for"…

★ 46kGrade B
playground✓SAFE

anthropics/claude-plugins-official

Creates interactive HTML playgrounds — self-contained single-file explorers that let users configure something visually through controls, see a live preview, and copy out a prompt. Use when the user asks to make a…

★ 45kGrade B
claude-automation-recommender✓SAFE

anthropics/claude-plugins-official

Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving…

★ 45kGrade B
claude-md-improver✓SAFE

anthropics/claude-plugins-official

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report,…

★ 45kGrade B
Agent Development✓SAFE

anthropics/claude-plugins-official

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent",…

★ 37kGrade B

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/butterbase-ai/journey-substrate/badge.svg)](https://modelsatlas.com/skills/butterbase-ai/journey-substrate/)

Questions about Journey Substrate

What does the Journey Substrate skill do?
Plugin for Butterbase.ai
Is Journey Substrate safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Journey Substrate access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Journey Substrate work with?
Its documentation mentions cursor. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (b9d383eb75ba), read on 2026-10-14. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.