krypton

Name: krypton
Author: jturntdev

Pending

Stop AI agents from shipping plausible wrong work

73stars

0forks

Shell

Installation

# Add to your Claude Code skills
git clone https://github.com/jturntdev/krypton

Getting Started

Guides for using ai agents skills like krypton.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

README.md

Frequently Asked Questions

What is krypton?

krypton is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by jturntdev. Stop AI agents from shipping plausible wrong work. It has 73 GitHub stars.

Is krypton safe to use?

krypton's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.

How do I install krypton?

Clone the repository with "git clone https://github.com/jturntdev/krypton" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is krypton written in?

krypton is primarily written in Shell. It is open-source under jturntdev on GitHub, so you can review or fork the full source.

Are there alternatives to krypton?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh krypton against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

superpowers

by obra

An agentic skills framework & software development methodology that works.

234,966

foreman jarvis_ai

Krypton

Current version: 0.1.3

Stop AI agents from shipping plausible wrong work.

Krypton is an operator discipline for running Claude Code, Codex, and other AI coding agents against production-grade codebases.

The failure mode Krypton is built for is not bad syntax. It is the right-looking feature that compiles while living on the wrong layer, inventing a second source of truth, skipping cutover, or claiming success without proof from the real path.

Krypton forces the plan before the code:

truth owner
contract boundary
displaced path
cutover decision
acceptance evidence
review gates

Built for /goals, Claude Code skills/plugins, Codex skills, and operators who need agent speed without letting the codebase rot.

Why Operators Need It

Modern agents can create weeks of architectural debt in one enthusiastic session. Krypton turns "build this" into an operational contract before the agent touches code:

what product or engineering outcome the work serves
what current behavior is replaced, redirected, deleted, or demoted
who owns the truth
what contract crosses the boundary
what evidence proves the result from the target person's perspective
what kill criteria prevent duplicate paths from living forever

That contract is what lets an operator keep using agents on production systems without letting the codebase become a pile of current-looking alternatives.

Designed For `/goals`

Krypton is best used with /goals or any equivalent goal-based agent workflow. It is not meant to be a one-shot "please implement this" prompt.

The planning session creates the durable handoff:

docs/goals/<goal-slug>/PLAN.md
docs/goals/<goal-slug>/GOAL.md

PLAN.md is the source plan. GOAL.md is the compact /goal prompt. Start the execution session with that prompt, then load krypton-execution so the main agent preserves the plan's ownership, cutover, review, and evidence gates.

If your harness does not have /goals, paste the contents of GOAL.md into a fresh Codex or Claude session. The shape still works.

Install

Claude Code Plugin

Use the plugin route when you want Claude Code to manage Krypton as a plugin:

/plugin marketplace add jturntdev/krypton
/plugin install krypton@krypton-dev
/reload-plugins

Claude Code namespaces plugin skills, so invoke them as:

/krypton:krypton-planning
/krypton:krypton-execution

This repo includes the Claude plugin files Claude Code expects:

.claude-plugin/plugin.json
.claude-plugin/marketplace.json
skills/krypton-planning/SKILL.md
skills/krypton-execution/SKILL.md

Claude Code Manual Skills

Use manual install when you want the skills available as personal Claude Code skills without the plugin marketplace:

git clone https://github.com/jturntdev/krypton.git
mkdir -p ~/.claude/skills
cp -R krypton/skills/krypton-planning ~/.claude/skills/
cp -R krypton/skills/krypton-execution ~/.claude/skills/

Manual personal skills invoke without a plugin namespace:

/krypton-planning
/krypton-execution

Codex

For Codex skills:

git clone https://github.com/jturntdev/krypton.git
mkdir -p ~/.codex/skills
cp -R krypton/skills/* ~/.codex/skills/

Skills

krypton-planning: turn a request into an outcome contract, architecture slice, task plan, evidence gate, and /goal handoff prompt.
krypton-execution: execute an approved plan without drifting from ownership, cutover, or proof requirements.

How It Works

Load krypton-planning with a feature request, bug, refactor, migration, or architecture goal.
The agent produces a goal package:

docs/goals/<goal-slug>/PLAN.md
docs/goals/<goal-slug>/GOAL.md

PLAN.md is the full implementation plan. GOAL.md is the short /goal prompt or handoff prompt for the next session.
Paste or run the GOAL.md prompt in Codex or Claude.
Pair it with krypton-execution when you want the main agent to use the same ownership, cutover, review, and evidence discipline.
Finish only when the acceptance evidence is captured from the real route, artifact, payload, trace, browser state, or operator-visible output.

The workflow is intentionally two-stage:

rough request
  -> krypton-planning
  -> PLAN.md + GOAL.md
  -> /goal handoff
  -> krypton-execution
  -> main-agent implementation + review gates + acceptance evidence

Agent Roles

Krypton works best when the harness supports named agents:

explorer: read-only source-of-truth and architecture mapping
plan-reviewer: PRE and POST alignment checks
reviewer: runtime correctness, security, and evidence check
maintainer: codebase-shape, duplication, and cutover-debt check
verifier: focused proof from the real path

See docs/required-roles.md for the role expectations. If your harness does not support named agents, the main agent can still follow the same gates, but independent exploration and review will be weaker.

Prompt Files

Krypton keeps prompt templates individual instead of centralizing them into one large prompt file. Each skill owns the prompts it actually uses:

skills/krypton-planning/plan-reviewer-prompt.md
skills/krypton-execution/post-plan-reviewer-prompt.md
skills/krypton-execution/reviewer-prompt.md
skills/krypton-execution/maintainer-prompt.md

Example

Bad agent path:

"Add sentiment to the dashboard."

The agent adds frontend-only sentiment logic and calls it done.

Krypton path:

Truth owner: market intelligence producer
Contract boundary: typed sentiment payload
Cutover: dashboard reads producer output only
Evidence: API response plus browser state showing the real payload

See examples/ and tests/pressure-scenarios/ for more.

Status

This is the first public cut. It is intentionally small: two skills, individual prompt templates, agent role expectations, examples, pressure scenarios, and a validation script.

Versioning

Krypton uses SemVer-style versions while the public package stabilizes.

Version source of truth: VERSION
Plugin metadata must match: .codex-plugin/plugin.json, .claude-plugin/plugin.json, and .claude-plugin/marketplace.json
Release tags should use vX.Y.Z

Version policy:

Patch: README, examples, prompt wording, metadata, validation improvements
Minor: new skills, new gates, changed /goal workflow shape
Major: breaking skill names, removed gates, incompatible plan or goal format

Development

Run:

./scripts/validate.sh

The validator checks required files, skill metadata, JSON plugin metadata, and public-safety issues such as placeholders or private project references.

License

MIT