Borrowing it
Nothing to install: this file belongs to neurarelay/relay-action-card. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/neurarelay/relay-action-card/main/AGENTS.mdgit clone --depth 1 https://github.com/neurarelay/relay-action-cardWrote 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/neurarelay/relay-action-card/agents-md)<a href="https://agentmods.dev/instructions/neurarelay/relay-action-card/agents-md"><img src="https://agentmods.dev/badge/instructions/neurarelay/relay-action-card/agents-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.
<a href="https://agentmods.dev/instructions/neurarelay/relay-action-card/agents-md"><img src="https://agentmods.dev/badge/instructions/neurarelay/relay-action-card/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00384 | $0.00384 |
| Opus 5 | $0.00192 | $0.00192 |
| Sonnet 5 | $0.00077 | $0.00077 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
relay-action-card 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 9d 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Relay Action Card Repository Instructions
Role and authority
This public repository is Neura's proof, schema, example, skill, adapter, and developer-verification surface for Relay Action Cards and related receipts.
It demonstrates public contracts and bounded integrations. It is not the authoritative private Relay runtime, Registry identity source, or downstream execution engine.
Runtime and verification
- Use Node 24 as the primary development and CI runtime.
- Preserve
package.jsoncompatibility with Node>=22.14.0unless a separate consumer-compatibility decision changes it. - Treat
npm run checkas the required local and CI verification entry point. - Run
npm audit --audit-level=highfor dependency changes and before remote review.
Change boundaries
- Preserve public examples as synthetic and free of private customer or Capital Guide data.
- Do not add public API-key issuance, public production token issuance, unprotected execution, downstream execution, raw private payloads, or secret values.
- Do not make adoption, official-provider, certification, endorsement, or production-readiness claims without verified evidence and separate approval.
- Package publication, release tags, public narrative changes, and repository settings require separate explicit scope.
- Do not change shared contract versions through maintenance work.
Documentation and history
- Update factual proof records when implementation or verification truth changes.
- Keep dated historical evidence intact unless a dedicated archival migration is explicitly scoped and verified.
- Use the workspace control layer at
/Users/roman/Drive/Business/Neura Agent Infrastructurefor portfolio strategy and cross-repository authority. - Do not present a local candidate as published, pushed, merged, or generally adopted.
External actions
Local inspection, edits, tests, and commits are allowed within the approved task. Pushing, opening or merging pull requests, changing repository settings, publishing packages, and creating releases require an exact consolidated external-action boundary.
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.
- 9d ago First seen · 34 lines · 384 tokens per session scan A 4dbd2c52ac0f
relay-action-card AGENTS.md is an instructions file published in the GitHub repository neurarelay/relay-action-card (2 stars, last pushed 16d ago), licensed MIT. It adds 384 tokens to every session, about $0.0019 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 2026-08-31.
Other instructions, from other repositories
plan-forge database.instructions.md
Database patterns for .NET — Dapper/EF Core, parameterized queries, migration strategy.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
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).
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.