social-monitor: Instructions file for Codex

AGENTS.md

social-monitor AGENTS.md is an instructions file for Codex, OpenCode from 777genius/social-monitor. It costs 1,563 tokens per session, scanned A, original, Apache-2.0.

A set of repository rules for Social Monitor, including required documents, code-structure guidance, quality checks, and frontend safeguards.

In plain words
What is it for?
It is for making backend and Flutter frontend changes while following the project's architecture, testing, design, and release rules.
Why use it?
It tells coding agents which instructions to read and which checks to follow before changing different parts of the project.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is 777genius/social-monitor's own configuration. It tells Codex and OpenCode how to work on social-monitor itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything social-monitor configures →

Reuse

Borrowing it

Nothing to install: this file belongs to 777genius/social-monitor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/777genius/social-monitor/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/777genius/social-monitor

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for social-monitor AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/777genius/social-monitor/agents-md/github.svg)](https://agentmods.dev/instructions/777genius/social-monitor/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/777genius/social-monitor/agents-md"><img src="https://agentmods.dev/badge/instructions/777genius/social-monitor/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.

agentmods 80×15 button for social-monitor AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/777genius/social-monitor/agents-md"><img src="https://agentmods.dev/badge/instructions/777genius/social-monitor/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,563 This file is loaded in full into every session.
When invoked 1,563 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01563 $0.01563
Opus 5 $0.00781 $0.00781
Sonnet 5 $0.00313 $0.00313
Haiku 4.5 $0.00156 $0.00156

Measured 12d ago against content hash efa03aee4deb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

social-monitor 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 12d 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.

AGENTS.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Social Monitor Agent Rules

This file is the root entrypoint for every agent working in this repository. Read it before changing code, then load the linked rule files for the area you touch. When two rules overlap, the stricter rule wins.

Mandatory Rule Index

Read these before any code change:

  • CLAUDE.md - repository-wide quality bar, prohibited flows and done gates.
  • .claude/rules/quality-architecture.md - backend/API Clean Architecture, DDD boundaries and release gates.
  • .claude/rules/ddd-clean-architecture-folders.md - canonical frontend feature scaffold, DDD folders and Clean Architecture dependency direction.
  • .claude/rules/flutter-frontend-quality.md - Flutter frontend architecture, responsive rules, design-system rules and executable frontend gates.
  • .claude/rules/flutter-clean-disk-deep-lessons.md - concrete failure modes from clean_disk that must not be repeated here.
  • apps/frontend/AGENTS.md - frontend package roles, app/design-system/shared-kernel boundaries and local done checks.
  • apps/frontend/docs/README.md - frontend UX, design-system, state, API, testing, observability and privacy playbooks.
  • docs/iterations/04-mobile-app/15-change-control.md - change-control bans for the mobile/frontend iteration.
  • docs/iterations/04-mobile-app/18-decision-log.md - recorded architecture decisions for the mobile/frontend iteration.

Hard Stops

  • Do not run agent launch, provisioning, terminal-runtime, task-assignment or smoke-flow checks on real user projects. Use sandbox/test projects only.
  • Do not weaken architecture tests, hooks or dependency-direction gates without replacing them with equal or stronger executable checks.
  • Do not let human-written source or test files exceed 1000 LOC. Generated/build/vendor outputs are excluded; existing legacy debt in scripts/check-source-line-cap.mjs may only shrink and cannot receive new behavior without splitting.
  • Do not add behavior to human-written Dart files over 500 lines. Split first.
  • Do not let any human-written Dart file exceed 600 lines.
  • Do not add raw headless, headless_adaptive, generated API clients or heavy renderer packages directly to feature widgets.
  • Do not add dio, retrofit, retrofit_generator or openapi_retrofit_generator to frontend app or feature packages. The frontend REST generator and HTTP transport implementation live only in apps/frontend/packages/generated_api unless an ADR and architecture-test exception approve a replacement.
  • Do not model frontend async state as loose isLoading/error fields. Use shared typed state and failures.
  • Do not let async stores apply stale results after workspace, query, filter, route or selection changes.
  • Do not add raw route path strings, route parsing or deep-link policy inside frontend features. App composition owns typed FeatureRouteContract registration.
  • Do not persist frontend cache, credentials or provider payloads from a feature without an ADR and architecture-test exception.
  • Do not read feature flags from environment variables inside features. Capabilities are app composition state and fail closed.
  • Do not handle realtime streams in a feature without cursor, schema version, sequence, dedupe and workspace-scope guarding.
  • Do not log raw frontend payloads. Use correlation/action/screen ids and redacted fields.
  • Do not put raw provider payloads, access tokens, API keys or realistic secrets in frontend tests, logs, screenshots or fixtures.
  • Do not reintroduce a local apps/frontend/packages/headless_adaptive package directory. The source of truth is https://github.com/777genius/flutter_headless.git.
  • Do not create frontend feature packages manually. Use npm run frontend:create-feature -- <bounded_context> "<Title>" "<Purpose>".
  • Do not add flutter_modular or get_it to frontend packages without an ADR and an equal-or-stronger architecture test.
  • Do not import modularity_flutter outside frontend app root or feature presentation/routes and presentation/composition.
  • Do not call ModuleProvider.of outside *_feature_module_host.dart.
  • Do not export feature pages directly; public feature barrels export route entrypoints only.
  • Do not create default frontend feature folders named ports/ or adapters/. Use canonical DDD folders and product-language names.
  • Read the local apps/frontend/features/<feature>/AGENTS.md before editing a frontend feature.
  • Read apps/frontend/AGENTS.md before editing frontend app, package or feature code.
  • Do not create broad frontend dumps such as models.dart, dtos.dart, mapper.dart, widgets.dart, helpers.dart, utils.dart or generic manager.dart.

Read the full file on GitHub · 92 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. 12d ago First seen · 92 lines · 1,563 tokens per session scan A efa03aee4deb

Subscribe to this mod's changes

social-monitor AGENTS.md is an instructions file published in the GitHub repository 777genius/social-monitor (46 stars, last pushed today), licensed Apache-2.0. It adds 1,563 tokens to every session, about $0.0078 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.

Related

Other instructions, from other repositories

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.

github/spec-kit · 7,126 tokens

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens