Loki Seal logo

Loki Seal

CommunityPopular
asklokesh
loki-seal

Use when finishing any coding task in a repo with tests. Loki Seal runs the repo's real test suite and refuses to let you declare done while tests newly fail, or while tests or CI config were deleted, skipped, xfailed or weakened. Runs locally with no model calls.

Overview

Publisherasklokesh
Repositoryloki-mode
Skill nameloki-seal
Stars
1.1K
Forks
206
Bundled files
Instructions only
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 asklokesh on GitHub. Read the source before you install it.

Installation

Install the Loki Seal 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/asklokesh/loki-mode/tree/main/packages/loki-seal/skills/loki-seal
  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/asklokesh/loki-mode.git /tmp/loki-mode
mkdir -p .claude/skills
cp -r /tmp/loki-mode/packages/loki-seal/skills/loki-seal .claude/skills/loki-seal
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Loki Seal 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 Loki Seal 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 Loki Seal 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.

Loki Seal

The enforcing piece is the plugin's Stop hook (bin/loki-seal.js). This skill is advisory: it tells you what the hook checks so you do not trip it. It registers no hooks itself.

When you try to finish, the hook:

  1. Detects the runner (npm test with node --test/jest/vitest, pytest, go test, cargo test) and runs the real suite on the working tree.
  2. Blocks the stop when tests newly fail since session start (already-red tests are reported, not blamed, except that a request item whose tests fail now always blocks), when the run crashed or ran nothing, when the total test count dropped, or when, compared with the session baseline, a test file was removed, test declarations or assertions dropped, a skip/xfail/only marker was added, or a CI workflow test step was removed or softened.
  3. Reads the delivery contract from your first request (see README) and blocks while a request item (a must or bullet line of 2+ keywords) has no matching test that contains an assertion token and that the runner reported as passed (comments, docstrings, string, template and regex literals, skipped tests and tests in files the runner never ran never count), and always blocks while any test matched to a request item fails now: failing tests never count as covered. Only sentences opening with I, we, let me or let's (and tool-version or status notes) are dropped as chat and listed in the contract line; You, Our, My and Please sentences with a modal are requirement items. A spec file counts only when you mark it ("spec: docs/x.md"); when no contract can be derived the receipt says "NOT VERIFIED: no contract".
  4. Reports a 6-line receipt (outcome, runner and counts, tests-integrity, contract, tree hash, Verified by Loki link).

What to do when it blocks

Fix the production code. Do not delete, skip, xfail or weaken tests to get green; that is exactly what the hook detects. If a test is genuinely wrong, tell the user and let them decide.

Install

Install the plugin: claude plugin marketplace add <owner/repo or path>, then install loki-seal from the /plugin UI. Installing only this skill gives you the guidance but no enforcement.

Frequently asked questions

What does the Loki Seal AI skill do?

Use when finishing any coding task in a repo with tests. Loki Seal runs the repo's real test suite and refuses to let you declare done while tests newly fail, or while tests or CI config were deleted, skipped, xfailed or weakened. Runs locally with no model calls.

Why use Loki Seal on TypingMind?

Because you install it once and use it with any model. Loki Seal 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 Loki Seal in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/asklokesh/loki-mode/tree/main/packages/loki-seal/skills/loki-seal. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Loki Seal?

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 Loki Seal?

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

Is the Loki Seal AI skill free?

It is published on GitHub by asklokesh. Check the repository for licensing terms. 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 👇