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.
curl -O https://raw.githubusercontent.com/jjanczur/tyran/main/CLAUDE.mdgit clone --depth 1 https://github.com/jjanczur/tyranWrote 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.
[](https://agentmods.dev/instructions/jjanczur/tyran/claude-md)<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>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.
| Model | Per session | Once 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 |
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.
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 equalSEVERITY_BY_CODEinscripts/doctor.mjs, in both directions. Add a finding code, add the row.- no model name outside
tiers:—tests/unit/agents.test.mjsfails ifhaiku/sonnet/opus/fableappears 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 |
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.
- 7d ago First seen · 135 lines · 1,811 tokens per session scan A 5fd611c861a1
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.
Other instructions, from other repositories
plan-forge version.instructions.md
Version management — Semantic versioning, auto-increment, commit-driven version bumps, release tagging.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).