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/dmno-dev/varlock/agents-mdgit clone --depth 1 https://github.com/dmno-dev/varlockWhat 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 | $0.01700 | $0.01700 |
| Opus 5 | $0.00850 | $0.00850 |
| Sonnet 5 | $0.00340 | $0.00340 |
| Haiku 4.5 | $0.00170 | $0.00170 |
Grade A, and why
varlock 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 yesterday.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project conventions
Repo structure
This is a monorepo managed with bun workspaces and Turborepo:
packages/env-spec-parser— parser for the @env-spec language (PEG.js grammar ingrammar.peggy)packages/varlock— the main package: CLI + library for loading/validating.envfilespackages/varlock-website— docs site (Astro); docs content lives insrc/content/docs/packages/vscode-plugin— VSCode extension for @env-spec language supportpackages/integrations/*— framework integrations (nextjs, vite, astro, ...)packages/native-helpers/*— per-platform npm publishing shells for the native helper binaries (published as@varlock/native-helper-*, versioned in lockstep withvarlock); the binaries themselves are built frompackages/encryption-binary-swift(darwin) andpackages/encryption-binary-rust(linux/win32)packages/utils,packages/plugins— shared internalspackages/varlock-docs-mcp— docs MCP server for external varlock users; do not use it to look things up while working on this repo — read the docs source directly
Package manager
- This repo uses Bun as the package manager (
bun install,bun run, etc.) - Workspace deps use
workspace:*protocol - Use catalog for any potentially common dependencies
- CI workflows use
bun runto execute scripts andbunxfor one-off commands
Scripts
- Write any scripts which may end up being saved in TypeScript (
.ts), not JavaScript- throwaway/one-off code is fine in JS
- Execute scripts using
bun run, notnode- e.g.
bun run scripts/release-preview.ts - Bun runs
.tsfiles natively — no compile step needed
- e.g.
- Scripts in
scripts/at the repo root are monorepo-level utilities, while specific packages may have their ownscriptsfolder
Binary builds
- The varlock CLI binary is built using
bun build --compile(not Node SEA or pkg) bun run --filter varlock build:binarybuilds a local dev binary for the current platform atpackages/varlock/dist-sea/varlockpackages/varlock/scripts/build-binaries.tsbuilds cross-platform release binaries (or use--current-platformfor a single local binary)bun run --filter varlock test:binary:localbuilds the local binary and runs a smokeloadcheck (WSL-aware helper copy)bun run --filter varlock pack:localbuilds + packs a local tarball and prints a ready-to-pastefile:dependency
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.
- yesterday First seen · 84 lines · 1,700 tokens per session scan A 25cdd0837dab
varlock AGENTS.md is an instructions file published in the GitHub repository dmno-dev/varlock (4,238 stars, last pushed 2d ago), licensed MIT. It adds 1,700 tokens to every session, about $0.0085 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
tweakcc AGENTS.md
Instructions for Piebald-AI/tweakcc, covering agents.md, development commands, build, testing and linting & formatting.
code-abyss CLAUDE.md
Instructions for telagod/code-abyss, covering claude.md, project overview, commands, persona behavioral battery (opt-in eval) and ci / cd.
envault AGENTS.md
Instructions for Coding-Dev-Tools/envault, covering envault — agents.md, quick start, commands, development and install dev deps.
configdrift AGENTS.md
Instructions for Coding-Dev-Tools/configdrift, covering configdrift, purpose, build & test commands, architecture and conventions.
claude-calibration CLAUDE.md
Claude Code instructions for odere-pro/claude-calibration, covering claude-calibration — plugin development, what ships, what doesn't, pointers and agent routing.
cmds-llm-wiki AGENTS.md
Schema and harness document for the CMDS LLM Wiki vault. Defines the 3-layer architecture (Raw Sources / Wiki / Schema), ingest-query-lint operations, file conventions, and frontmatter standards. This is the single source of truth for LLM behavior in this vault.