Vibe Ci Supply Chain logo

Vibe Ci Supply Chain

OrganizationPopular
mistralai
vibe-ci-supply-chain

Git workflow, CI/GitHub Actions, and supply-chain pinning rules for Mistral Vibe. Use when changing CI pipelines, GitHub Actions, dependency pinning, container images, pre-commit hooks, git workflow, or external binary downloads.

Overview

Publishermistralai
Repositorymistral-vibe
Skill namevibe-ci-supply-chain
Stars
5.1K
Forks
732
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by mistralai on GitHub. Read the source before you install it.

Installation

Install the Vibe Ci Supply Chain AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/mistralai/mistral-vibe/tree/main/.agents/skills/vibe-ci-supply-chain
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mistralai/mistral-vibe.git /tmp/mistral-vibe
mkdir -p .claude/skills
cp -r /tmp/mistral-vibe/.agents/skills/vibe-ci-supply-chain .claude/skills/vibe-ci-supply-chain
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Vibe Ci Supply Chain in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Vibe Ci Supply Chain on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Vibe Ci Supply Chain is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Vibe CI & Supply Chain

Conventions for git workflow, CI configuration, and supply-chain security in Vibe.

Startup import cost

CI gates cold-start module count via vibe/scripts/check_startup_import_cost.py (budgets in vibe/scripts/startup_import_cost.vibe.toml).

  • When a change touches imports or module structure on the path of import vibe or from vibe.cli.textual_ui.app import VibeApp, run cd vibe && uv run scripts/check_startup_import_cost.py and confirm the count stays within budget.
  • Verify, do not bump. An overshoot is a regression to investigate (lazy import, drop the dependency, defer the import) — not a reason to raise the budget. Only widen for a deliberate, PR-justified increase, and set to observed count + ~10% headroom, never the exact count.

Git

  • Never use git commit --amend, git push --force, or git push --force-with-lease.
  • Always create new commits and push with a plain git push.
  • Reconciling with the upstream of the current branch (e.g. push rejected because origin/<current-branch> advanced): rebase the current branch onto its upstream — do not merge the upstream branch into the current one, never force-push.
  • Reconciling with the base branch (e.g. origin/main) once the PR is open: merge the base branch into the current branch — do not rebase, since rebasing rewrites already-pushed history and would require a force-push.
  • Run git commands through uv run (e.g. uv run git commit, uv run git push) so pre-commit hooks resolve the project's venv — bare git commit fails pre-commit with reportMissingImports because pyright can't find third-party packages.

CI / GitHub Actions

  • Pin every uses: to a full commit SHA with an exact version comment: uses: owner/action@<commit-sha> # vX.Y.Z.
  • Resolve to the commit, not the annotated-tag object: take the refs/tags/vX^{} line from git ls-remote --tags, or gh api repos/<owner>/<repo>/git/refs/tags/<tag> --jq .object peeled to a commit. Check with git cat-file -t <sha> → commit, not tag. Never pin a moving major tag (v9).

Supply-chain pinning

Every external input to the build, CI, or install path must be pinned to an immutable identifier — never a mutable tag or an unverified download. Add a human-readable comment next to each pin.

  • Container images: reference by @sha256:<digest>, never a bare tag (:latest, :8). Resolve the digest via the registry's Docker-Content-Digest header (curl -sI -H 'Accept: application/vnd.oci.image.index.v1+json' <registry>/v2/<repo>/manifests/<tag>). When the image lives inside a JSON matrix string, document the tag→digest mapping in an adjacent comment.
  • pre-commit hooks (.pre-commit-config.yaml): pin every rev: to a full commit SHA with a # vX.Y.Z comment. Run pre-commit autoupdate --freeze to refresh, and resolve to the peeled commit ref (refs/tags/vX^{}), not the annotated-tag object — same rule as uses: above.
  • Build-system deps (pyproject.toml [build-system] requires): pin hatchling, hatch-vcs, editables (and any addition) to exact == versions. These execute during source builds and are not covered by uv.lock.
  • External binary downloads (e.g. patchelf in scripts/ci/): never pipe an unverified download straight into tar/sh. Download to a temp file, verify sha256sum -c against a known-good hash keyed by version (and arch when relevant), then extract. Hard-fail when no hash is registered for the requested version/arch so a bump forces updating the hash.

Frequently asked questions

What does the Vibe Ci Supply Chain AI skill do?

Git workflow, CI/GitHub Actions, and supply-chain pinning rules for Mistral Vibe. Use when changing CI pipelines, GitHub Actions, dependency pinning, container images, pre-commit hooks, git workflow, or external binary downloads.

Why use Vibe Ci Supply Chain on TypingMind?

Because you install it once and use it with any model. Vibe Ci Supply Chain is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Vibe Ci Supply Chain in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mistralai/mistral-vibe/tree/main/.agents/skills/vibe-ci-supply-chain. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Vibe Ci Supply Chain?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Vibe Ci Supply Chain?

As many as you like. As long as a model supports skills, you can use Vibe Ci Supply Chain with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Vibe Ci Supply Chain AI skill free?

Yes. It is published on GitHub by mistralai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇