init

A setup helper for creating or repairing ryk's repository policy file, .ryk/policy.yaml.

In plain words
What is it for?
Initialize a policy from a preset, validate it, or create a backup before replacing an existing policy.
Why use it?
It provides a starting policy when a project has none or when you need known safety defaults, while requiring validation and warning against silent overwrites.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/christopherkarani/ryk/init
Any agent
npx skills add christopherkarani/ryk --skill init
Clone the repo
git clone --depth 1 https://github.com/christopherkarani/ryk

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 334 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00334
Opus 5 $0.00000 $0.00167
Sonnet 5 $0.00000 $0.00067
Haiku 4.5 $0.00000 $0.00033

Measured 2d ago against content hash 5043cf88a71d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • ryk-init — 91% identical, 8 lines differ
integrations/claude-code-plugin/skills/init/SKILL.md · 54 lines

What it actually says

init

Create or repair an ryk policy for the current repository.

When to use

Use this skill when starting a new project, when .ryk/policy.yaml is missing, or when you want to reset to a known-good policy preset.

Commands

Initialize an ryk policy with the Claude Code preset:

ryk init --preset claude-code

Validate the resulting policy:

ryk policy check .ryk/policy.yaml

Preset fallback

If the claude-code preset is not available in your ryk build, use the closest plugin-safe preset:

ryk init --preset generic-agent

Or, for stricter defaults:

ryk init --preset strict-local

The generic-agent preset is a conservative starting point for local coding agents. Review the generated .ryk/policy.yaml before trusting it.

Safety rules

  • Do not silently overwrite .ryk/policy.yaml. If a policy already exists, review it first.
  • If you need to recreate it, back up the old file:
    cp .ryk/policy.yaml .ryk/policy.yaml.bak
    
  • Always run ryk policy check after creating or editing a policy.

Notes

  • This skill modifies only .ryk/policy.yaml in the current workspace.
  • No host configuration is changed.
  • The plugin does not collect telemetry. Release CLI commands may record only fixed anonymous metadata; see docs/telemetry.md.
  • The generated policy does not contain real secrets.
Changes

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.

  1. 2d ago First seen · 54 lines · 0 tokens per session scan A 5043cf88a71d

Subscribe to this mod's changes

init is a skill published in the GitHub repository christopherkarani/ryk (39 stars, last pushed 12d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 334 tokens. 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 2026-08-30.