toki: Instructions file for Claude Code

CLAUDE.md

toki CLAUDE.md is an instructions file for Claude Code from korjwl1/toki. It costs 210 tokens per session, scanned A, original, MIT.

Project instructions for toki, including rules for changing stored event and rate-limit data formats. Toki is a software project whose details are not provided here.

In plain words
What is it for?
Use it when changing database structures, stored data encoding, checkpoints, or rate-limit window formats in toki.
Why use it?
It helps prevent incompatible data changes and avoids deleting rate-limit information that cannot be recreated.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is korjwl1/toki's own configuration. It tells Claude Code how to work on toki 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 toki configures →

View source ↗ korjwl1/toki
Reuse

Borrowing it

Nothing to install: this file belongs to korjwl1/toki. 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/korjwl1/toki/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/korjwl1/toki

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 toki CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/korjwl1/toki/claude-md/github.svg)](https://agentmods.dev/instructions/korjwl1/toki/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/korjwl1/toki/claude-md"><img src="https://agentmods.dev/badge/instructions/korjwl1/toki/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for toki CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/korjwl1/toki/claude-md"><img src="https://agentmods.dev/badge/instructions/korjwl1/toki/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 210 This file is loaded in full into every session.
When invoked 210 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 $0.00210 $0.00210
Opus 5.5 $0.00084 $0.00084
Sonnet 5.5 $0.00042 $0.00042
Haiku 4.5 $0.00021 $0.00021

Measured 2mo ago against content hash 2e814c6e779f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

toki 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 2mo 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 · 21 lines

What it actually says

Project Rules

Schema Version

When modifying any of the following, you MUST increment SCHEMA_VERSION in src/db.rs:

  • StoredEvent struct fields (src/common/types.rs)
  • Existing event-DB key/value encoding or keyspace layout in Database::open (src/db.rs)
  • Dictionary encoding format (src/db.rs)
  • Checkpoint format (src/checkpoint.rs)

This triggers automatic reset of the rebuildable <provider>.fjall event DB on next daemon start. Users do not need to run toki daemon reset manually.

Rate-limit windows live in <provider>.windows.fjall under their own WINDOWS_SCHEMA_VERSION. Never use an event schema bump to wipe window data; window observations may not be reconstructable. An incompatible window change needs an explicit versioned decoder/migration and must preserve unknown data.

Do NOT bump for additive changes that leave existing event data readable. Bump only when the current event serialization/key interpretation becomes incompatible.

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. 2mo ago First seen · 21 lines · 210 tokens per session scan A 2e814c6e779f

Subscribe to this mod's changes

toki CLAUDE.md is an instructions file published in the GitHub repository korjwl1/toki (21 stars, last pushed 2mo ago), licensed MIT. It adds 210 tokens to every session, about $0.0008 per session on Opus 5.5. 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

toki CLAUDE.md compared with instructions from other repositories

toki CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
toki CLAUDE.mdkorjwl1/tokiInstructions file212mo agoMITA210Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode