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.
npx agentmods add instructions/sx4im/chronos/claude-mdgit clone --depth 1 https://github.com/sx4im/chronosWrote 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/sx4im/chronos/claude-md)<a href="https://agentmods.dev/instructions/sx4im/chronos/claude-md"><img src="https://agentmods.dev/badge/instructions/sx4im/chronos/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 | $0.01450 | $0.01450 |
| Opus 5 | $0.00725 | $0.00725 |
| Sonnet 5 | $0.00290 | $0.00290 |
| Haiku 4.5 | $0.00145 | $0.00145 |
Grade A, and why
chronos 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 4d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Chronos
This file is read by Claude Code on every session. It is the project's working memory. Keep it accurate as the project evolves.
What this project is
Chronos is a Deterministic Simulation Testing (DST) framework for Node.js / TypeScript. It runs concurrent/distributed systems on a single controlled thread with virtualized time, seeded randomness, and a simulated network, so any bug — including rare races — reproduces exactly from a single integer seed. It's the FoundationDB/TigerBeetle technique, does not yet exist for JS/TS. (See docs/architecture.md and docs/technical-spec.md.)
THE PRIME DIRECTIVE (never violate)
Determinism is the product. The entire system has exactly one source of entropy (the seeded PRNG) and exactly one source of time (the virtual clock). In any code that runs inside a simulation, you must never use:
Date.now(),new Date(),performance.now(),process.hrtime()→ useclock.now()/env.now().Math.random()/cryptorandomness → use the simulator'sRng/env.random().- real
setTimeout/setInterval/setImmediatefor user timing → use the scheduler /env.sleep/env.setTimeout. (The only allowed real primitive is a singlesetImmediateused as the microtask-drain barrier inscheduler.ts.) - real sockets /
fs/ network → use the simulated network (env.net).
If the determinism guard test (packages/core/test/determinism.test.ts) ever fails or flakes, stop all other work and fix it first. It is bug class #1.
The core mental model (why DST works here)
V8's execution is already deterministic given identical inputs. Nondeterminism enters Node only through external entropy: wall clock, OS scheduling, network/disk completion order, and Math.random. Chronos removes all external entropy and serializes concurrency onto one thread, so the program replays identically. We do NOT reFibers — we let V8's deterministic microtask draining happen between scheduler steps (via the single setImmediate barrier). Read docs/architecture.md §2.3 before changing scheduler/async code.
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.
- 4d ago First seen · 69 lines · 1,450 tokens per session scan A 0e9b22e0c52f
chronos CLAUDE.md is an instructions file published in the GitHub repository sx4im/chronos (19 stars, last pushed 10d ago), licensed MIT. It adds 1,450 tokens to every session, about $0.0072 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
qq-music-api AGENTS.md
Instructions for Rain120/qq-music-api, covering 🤖 qq music api - ai agents 指南 (agents.md), 🎯 目录, 项目概览, 项目架构 and 1. 服务端主链路.
pi-extensions AGENTS.md
AGENTS.md instructions for narumiruna/pi-extensions, covering repository guidelines, documentation and communication, repository structure, commands and tooling and dependency safety.
sportsdataverse-js CLAUDE.md
Instructions for sportsdataverse/sportsdataverse-js, covering claude.md — sportsdataverse (node.js) development guide, package overview, commit convention, branches and build & development commands.
webiny-js AGENTS.md
AGENTS.md instructions for webiny/webiny-js, covering exploration, persist learnings, code, building and testing.
webiny-js CLAUDE.md
Claude Code instructions for webiny/webiny-js, covering context, claude project guidelines, reading code, development commands and install dependencies (suppress all output – it's noise).
webiny-js copilot-instructions.md
Copilot instructions for webiny/webiny-js, a project described as: Open-source, self-hosted CMS platform on AWS serverless (Lambda, DynamoDB, S3). TypeScript framework with multi-tenancy, lifecycle hooks, GraphQL API, and AI-assisted development via MCP server. Built for developers at large organizations.