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.
curl -O https://raw.githubusercontent.com/777genius/social-monitor/main/CLAUDE.mdgit clone --depth 1 https://github.com/777genius/social-monitorWrote 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/777genius/social-monitor/claude-md)<a href="https://agentmods.dev/instructions/777genius/social-monitor/claude-md"><img src="https://agentmods.dev/badge/instructions/777genius/social-monitor/claude-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/777genius/social-monitor/claude-md"><img src="https://agentmods.dev/badge/instructions/777genius/social-monitor/claude-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 | $0.01110 | $0.01110 |
| Opus 5 | $0.00555 | $0.00555 |
| Sonnet 5 | $0.00222 | $0.00222 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade C, and why
social-monitor CLAUDE.md scanned grade C with 1 finding 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- Project Claude permissions and hooks block `.env`, `.envrc`, `.npmrc`, `.netrc`, cloud/kube/GitHub config, secret directories, private keys, credential CLIs, network CLIs and destructive reset commands. Do not bypass t How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social Monitor Claude Rules
Social Monitor is a backend/API-first NestJS and TypeScript monitoring platform. Treat this repository as a Clean Architecture codebase with DDD bounded contexts, lightweight-to-expanded DDD feature folders, explicit inner contracts, generated contracts and executable release gates.
Load the project quality rules before changing code:
@.claude/rules/quality-architecture.md @.claude/rules/ddd-clean-architecture-folders.md @.claude/rules/flutter-frontend-quality.md @.claude/rules/flutter-clean-disk-deep-lessons.md
Working Rules
- Read the current code and the nearest architecture docs before changing a module.
- Read the local feature
AGENTS.mdbefore changing any frontend feature. - Keep changes scoped to the requested bounded context and use case.
- Do not add feature code by bypassing domain/application contracts, infrastructure boundaries, runtime selectors, tenant scope or contract gates.
- Prefer small vertical slices with focused tests over broad speculative rewrites.
- Do not manually edit generated clients, Prisma generated output or OpenAPI snapshots except through the documented generator/check command.
- Do not run agent launch/provisioning/terminal-runtime/task-assignment smoke flows on real user projects. Use sandbox/test projects or deterministic fixture checks.
Required Quality Bar
- Domain code imports only domain-safe dependencies and shared kernel.
- New feature work should model bounded contexts, ubiquitous language, aggregates, entities, value objects, domain events, policies/specifications, repositories, domain services and application use cases explicitly when the behavior needs them.
- Feature use cases depend on domain objects and domain/application contracts, not NestJS, Prisma, RabbitMQ, SDK clients, DTOs or in-memory implementations.
- Inner contracts are Clean Architecture ports by role. They must not read
process.envor import infrastructure implementations, interfaces, frameworks or public contracts. - Interfaces/controllers map transport input to commands and must enforce tenant/workspace/auth boundaries before invoking use cases.
- Infrastructure implementations own external details and must not leak ORM/SDK DTOs into domain, features or public contracts.
- Runtime adapter choices must go through resolver functions and keep
npm run check:runtime-profile-guardsgreen. - Apps and composition roots import
libsthrough@social-monitor/...aliases, never deep-relative../../../libs/...paths. - Runtime configuration belongs in config/provider-token/composition code, not hidden inside infrastructure implementations, domain or feature use cases.
- Interface controllers, gateways, support services and authorizers receive env-derived config through provider tokens, not direct
process.envreads. - Trusted workspace-role header parsing goes through
WorkspaceRoleHeaderParser, never repeated controller env checks. - Public contract knowledge belongs behind domain/application contracts when use cases need it.
- Do not introduce runtime circular dependencies. Split boundaries through inner contracts or shared domain primitives instead.
- Source/provider changes must keep fixture readiness and live beta readiness explicit.
- API changes must keep OpenAPI, generated clients and error contracts fresh.
- Dependency changes must check the current stable version and keep
npm audit --audit-level=moderateandnpm run check:dependenciesgreen. - Human-written source and test files have a hard 1000 LOC cap. Generated/build/vendor outputs are excluded; existing legacy debt in
scripts/check-source-line-cap.mjsmay only shrink and cannot receive new behavior without splitting. - Project Claude hooks are active in
.claude/settings.json. They block prohibited real-project agent/runtime commands, includeTaskCreated/Agentcoverage, respectstop_hook_activeand keep architecture/code-quality rules from becoming prose-only. - Project Claude permissions and hooks block
.env,.envrc,.npmrc,.netrc, cloud/kube/GitHub config, secret directories, private keys, credential CLIs, network CLIs and destructive reset commands. Do not bypass that through Bash subprocesses. - User-controlled outbound URLs use the shared-kernel outbound URL policy for SSRF protection, and HTTP infrastructure implementations use
AbortSignal.timeoutfor live provider calls.
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.
- 12d ago First seen · 59 lines · 1,110 tokens per session scan C c03404ed4b4a
social-monitor CLAUDE.md is an instructions file published in the GitHub repository 777genius/social-monitor (46 stars, last pushed today), licensed Apache-2.0. It adds 1,110 tokens to every session, about $0.0056 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.
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).
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.
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).