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/m9tdev/verrex/agents-mdgit clone --depth 1 https://github.com/m9tdev/verrexWhat 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 | $0.03947 | $0.03947 |
| Opus 5 | $0.01973 | $0.01973 |
| Sonnet 5 | $0.00789 | $0.00789 |
| Haiku 4.5 | $0.00395 | $0.00395 |
Grade A, and why
verrex 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 2d 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
verrex — Effect-native UI framework
Purpose: a TypeScript UI framework where Effect's <A, E, R>
channels propagate from every leaf of the view tree to the root.
Forgetting to provide a service Layer becomes a compile-time
error that names the missing service; symmetrically, forgetting to
handle an error with a Catch boundary becomes a compile-time
error that names the unhandled error (mount requires
Effect<View<never>, never, R>). Errors live in two phases: construction
errors ride the Effect E; live errors a rendered subtree can still
produce ride the View<E> success — one Catch boundary discharges both.
Honest scope today: the construction channel is fully type-tracked —
a forgotten boundary on a failing build is a compile error. The live
channel is tracked wherever a rendered subtree can still fail: (1) an
Atom/AtomRef child that EMITS an Effect<View, E> — the fold's phase
switch puts that E on View<E> (this is how an atom(...)'s failure
escalates: <On value={user} Success={…} /> with no failure arm; a tag arm
or Failure handles it in place; partial handling narrows E, the residual
rides); (2) event handlers: an intrinsic's on* prop returning
Effect<_, E, R> stamps E on the element's View<E> and folds R; (3)
For rows and Catch fallbacks fold their E/R too. mount's
View<never> gate makes a missing boundary a compile error naming E.
Reactivity is effect-atom's API with R/E owned by the caller — see
"Reactivity model" in src/runtime/AGENTS.md.
The name is built from the channels of an Effect<View, E, R>:
V (View — the A, always the View here), E (Error), R
(Requirements), plus X, because the JSX/TSX syntax it borrows adds an
X too. V + E + R + X spells verx, stylized to verrex (and the
.vx source extension).
Status: experimental proof-of-concept. Not production-ready.
The constraint that shaped everything
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.
- 2d ago First seen · 291 lines · 3,947 tokens per session scan A 9804fc4803ca
verrex AGENTS.md is an instructions file published in the GitHub repository m9tdev/verrex (55 stars, last pushed 7d ago), licensed MIT. It adds 3,947 tokens to every session, about $0.0197 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
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
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.