agentmods.dev

grix AGENTS.md

Agent instructions for Grix, covering its backend, frontend, administration, voice, and Kubernetes deployment areas. They also define required review and pre-push checks; Kubernetes is a system for running applications in containers.

In plain words
What is it for?
Use them when reviewing or changing Grix code, database migrations, security-sensitive work, deployment configuration, or interfaces between components.
Why use it?
They limit changes to the right parts of the repository and ensure important work is reviewed and validated before handoff.

Instructions file for CodexOpenCode

130 yesterday A scan 520 tokens original Apache-2.0
View the source file askie/grix
Install

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.

agentmods
npx agentmods add instructions/askie/grix/agents-md
Clone the repo
git clone --depth 1 https://github.com/askie/grix

Made for: Codex, OpenCode.

Per session 520 This file is loaded in full into every session.
When invoked 520 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00520 $0.00520
Opus 5 $0.00260 $0.00260
Sonnet 5 $0.00104 $0.00104
Haiku 4.5 $0.00052 $0.00052

Measured yesterday against content hash a98a24f52a79, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

grix 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.

AGENTS.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grix Agent Guide

Repository boundaries

  • Keep changes inside the existing backend, frontend, admin, voicebridge, and k8s boundaries unless the task explicitly changes the architecture.
  • Treat README.md, CONTRIBUTING.md, code, migrations, and tests as current facts. Decision notes preserve rationale; they are not a substitute for current documentation or tests.
  • Follow CONTRIBUTING.md, including its requirement to keep commit authorship and contributor metadata limited to people who contributed.
  • Write all Git commit messages in English.
  • Do not commit credentials, private infrastructure details, generated build output, or local machine paths.
  • Preserve unrelated work and use a dedicated git worktree for repository changes.

Required workflows

  • Use $grix-code-review when reviewing a diff, pull request, bug fix, feature, refactor, migration, protocol change, or security-sensitive change.
  • Use $grix-pre-push-checks before a push or handoff to select the smallest sufficient validation set from the changed paths.
  • Start with focused evidence. Broaden checks only when the change crosses modules or contracts.

Shared agent configuration

  • Treat AGENTS.md as the only source of truth for repository instructions. Keep CLAUDE.md as an import-only compatibility entry.
  • Treat .agents/skills as the only source of truth for repository skills.
  • Keep .claude/skills as a compatibility symlink to .agents/skills; edit the canonical files, not the compatibility path.
  • Do not duplicate skills under .cursor, .codex, or other tool-specific directories when the tool already discovers .agents/skills.

Cross-component contracts

When a change crosses a boundary, inspect every producer and consumer of the contract. Important boundaries include:

  • REST and WebSocket payloads between Go services and Flutter clients.
  • NATS subjects and messages between backend services and voicebridge.
  • Agent adapters, session identity, ownership, permissions, and reconnect behavior.
  • Database migrations and code that reads both old and new stored states.
  • Kubernetes configuration, service health checks, and runtime defaults.

Read the full file on GitHub · 38 lines

Changes

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.

  1. yesterday First seen · 38 lines · 520 tokens per session scan A a98a24f52a79

Subscribe to this mod's changes

grix AGENTS.md is an instructions file published in the GitHub repository askie/grix (130 stars, last pushed yesterday), licensed Apache-2.0. It adds 520 tokens to every session, about $0.0026 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.

Code reviewFrontendSecurityagentagentic-aiagentic-workflowagentsaiai-agent
Related

Other instructions, from other repositories

optillm CLAUDE.md

Instructions for algorithmicsuperintelligence/optillm, covering claude.md, project overview, core architecture, main components and development commands.

algorithmicsuperintelligence/optillm · 1,227 tokens

LeAgent AGENTS.md

Instructions for vixues/LeAgent, covering leagent development guidelines, project overview, architecture, execution topology (one kernel, many ingresses) and surface map (where things live).

vixues/LeAgent · 6,799 tokens

rn-dev-agent AGENTS.md

Instructions for Lykhoyda/rn-dev-agent, covering repository guide for agents, repository map, editing rules, architecture rules and supported node runtimes.

Lykhoyda/rn-dev-agent · 5,241 tokens

clarion CLAUDE.md

Claude Code instructions for celanthe/clarion, covering clarion — agent voice manager, what it does, architecture, running it and ui only (edge tts, zero config).

celanthe/clarion · 1,385 tokens

upwork-agent CLAUDE.md

Claude Code instructions for citizenweb3/upwork-agent, covering upwork agent, setup (for a new machine), prerequisites, step 1: install dependencies and step 2: configure environment.

citizenweb3/upwork-agent · 2,731 tokens

relay AGENTS.md

Instructions for AgentWorkforce/relay, covering git workflow rules, never push directly to main, correct workflow, ... do work .. and stop here - let user merge.

AgentWorkforce/relay · 2,083 tokens