tyran: Instructions file for Claude Code

CLAUDE.md

tyran CLAUDE.md is an instructions file for Claude Code from jjanczur/tyran. It costs 1,811 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Tyran, a Claude Code plugin containing skills, agents, hooks, and Node scripts. They also define how documentation and releases must be maintained.

In plain words
What is it for?
They are for developing and documenting Tyran, updating both documentation surfaces, following its contribution and release rules, and validating factual claims in docs.
Why use it?
They prevent duplicated or conflicting guidance, keep the GitHub and website documentation aligned, and require claims such as test counts to be checked.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is jjanczur/tyran's own configuration. It tells Claude Code how to work on tyran itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tyran configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jjanczur/tyran. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jjanczur/tyran/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jjanczur/tyran

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for tyran CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jjanczur/tyran/claude-md.svg)](https://agentmods.dev/instructions/jjanczur/tyran/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jjanczur/tyran/claude-md"><img src="https://agentmods.dev/badge/instructions/jjanczur/tyran/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,811 This file is loaded in full into every session.
When invoked 1,811 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01811 $0.01811
Opus 5 $0.00905 $0.00905
Sonnet 5 $0.00362 $0.00362
Haiku 4.5 $0.00181 $0.00181

Measured 7d ago against content hash 5fd611c861a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

tyran CLAUDE.md 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 7d 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.

CLAUDE.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Tyran is a Claude Code plugin: skills, agents, PreToolUse hooks, and zero-dependency Node scripts. No build step, no runtime deps, Node ≥ 22.

Read CONTRIBUTING.md for the dev loop, the test commands and the enforced rules — they are not repeated here. This file is the rest: the places where the obvious move is the wrong one, and the procedures that have already cost someone a wasted release.

The house rule that shapes everything else: one answer lives in one place. Before adding a paragraph, look for where the answer already is and link to it. Three spellings of one rule is the defect this repo names ADR-21, and it has been found here more than once.

Two surfaces for every document

docs/*.md (GitHub) and site/src/content/docs/*.mdx (the docs site) publish the same claims. Change both, always. They were migrated from each other once and immediately diverged, because nobody re-reads a page they already reviewed. tests/unit/docs-claims.test.mjs checks both surfaces.

Prose in this repo is checkable on purpose:

  • numbers are claims. "47 unit tests" in a doc is verified against the actual count. Do not write a number you have not just measured.
  • docs/doctor.md's severity table must equal SEVERITY_BY_CODE in scripts/doctor.mjs, in both directions. Add a finding code, add the row.
  • no model name outside tiers:tests/unit/agents.test.mjs fails if haiku/sonnet/opus/fable appears in any agent or skill file.

Releasing — the version, not the commit

claude plugin update compares the version field, not the commit. A fix merged to main without a bump reports "already at the latest version" and reaches nobody. This has happened; it is the reason this section exists.

Bump all three in one commit — they are cross-checked by different tools:

file checked by
.claude-plugin/plugin.json what claude plugin update reads
.claude-plugin/marketplace.json claude plugin tag fails if it disagrees with plugin.json
package.json npm-publish.yml fails if it disagrees with the release tag

Read the full file on GitHub · 135 lines

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. 7d ago First seen · 135 lines · 1,811 tokens per session scan A 5fd611c861a1

Subscribe to this mod's changes

tyran CLAUDE.md is an instructions file published in the GitHub repository jjanczur/tyran (86 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,811 tokens to every session, about $0.0091 per session on Opus 5. 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.

Related

Other instructions, from other repositories