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/zulwatha/vardiya/agents-mdgit clone --depth 1 https://github.com/Zulwatha/vardiyaWrote 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/zulwatha/vardiya/agents-md)<a href="https://agentmods.dev/instructions/zulwatha/vardiya/agents-md"><img src="https://agentmods.dev/badge/instructions/zulwatha/vardiya/agents-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 | $0.00677 | $0.00677 |
| Opus 5 | $0.00338 | $0.00338 |
| Sonnet 5 | $0.00135 | $0.00135 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
vardiya AGENTS.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 5d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent ownership map
vardiya is a SQLite-backed job queue for Node.js. One runtime dependency (better-sqlite3). This repo is split so several agents can work in parallel without stepping on each other.
Module owners
| Area | Path | Owner | Responsibility |
|---|---|---|---|
| Types / contract | src/types.ts |
Lead (frozen) | Shared interfaces and types. Do not edit. |
| Public API stubs | src/index.ts, src/vardiya.ts |
Lead (signatures frozen) | Export surface. Fill bodies only; do not change method signatures. |
| Utilities | src/util/ |
Shared | Small pure helpers (ids, sleep, typed emitter). |
| Storage | src/storage/ |
Agent A | SQLite schema, migrations, Storage implementation. |
| Worker | src/worker/ |
Agent B | Claim loop, handlers, concurrency, heartbeats, events. |
| Scheduler | src/scheduler/ |
Agent C | In-house cron parsing, repeatables, delayed promotion ticks. |
| Tests & benches | test/, bench/ |
Agent D | Vitest tests and benchmarks. |
Stay inside your directory unless you need a tiny shared helper in src/util/. Prefer asking for a util over inventing a second copy.
Frozen types rule
src/types.ts is frozen after the foundation task. If you believe a change is required, do not edit the definitions. Add a comment block like this near the call site or in your PR notes:
/*
* PROPOSED-CHANGE:
* What: add Storage.reclaimStale(now, staleAfterMs)
* Why: workers die mid-job and active rows need reclaim
* Suggested shape: reclaimStale(now: number, staleAfterMs: number): number
*/
The lead merges contract changes deliberately so parallel work does not break.
Stack reminders
- Node >= 22, TypeScript strict, dual ESM+CJS via tsup.
- Runtime dependency:
better-sqlite3only. Cron, backoff, and ids are in-house. - Lint/format with biome. Tests with vitest.
npm run build,npm run lint, andnpm testshould stay green.
Writing style
Binding for every agent and every file: code comments, TSDoc, READMEs, docs, commit messages, and error messages.
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.
- 5d ago First seen · 54 lines · 677 tokens per session scan A 1c7f5dd7f254
vardiya AGENTS.md is an instructions file published in the GitHub repository Zulwatha/vardiya (11 stars, last pushed 1mo ago), licensed MIT. It adds 677 tokens to every session, about $0.0034 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
bunqueue CLAUDE.md
Claude Code instructions for egeominotti/bunqueue, covering bunqueue, test isolation rules, architecture flow, directory structure and code guidelines.
bunqueue AGENTS.md
AGENTS.md instructions for egeominotti/bunqueue, covering agents.md, project overview, repository map, working rules and documentation.
PgQue CLAUDE.md
Instructions for NikolayS/PgQue, covering claude.md -- pgque, project, naming convention, architecture and stack.
platform AGENTS.md
AGENTS.md instructions for doka-guide/platform, covering agents.md — как работать с платформой доки, 1. правила работы, сначала подумай, потом пиши, минимум кода and правки хирургические.
zapo CLAUDE.md
Claude Code instructions for vinikjkkj/zapo: The contributor handbook for this repository lives in AGENTS.md. Read that file and follow it as your primary source of project conventions, architecture rules, performance constraints, and review anti-patterns.
Silex AGENTS.md
AGENTS.md instructions for silexlabs/Silex, covering agents.md, tech stack, run it locally, building the desktop app and when writing code for silex (editing source).