Borrowing it
Nothing to install: this file belongs to romil569/RepoGuardian-RHD-Enterprise. 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/romil569/RepoGuardian-RHD-Enterprise/main/AGENTS.mdgit clone --depth 1 https://github.com/romil569/RepoGuardian-RHD-EnterpriseWrote 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/romil569/repoguardian-rhd-enterprise/agents-md)<a href="https://agentmods.dev/instructions/romil569/repoguardian-rhd-enterprise/agents-md"><img src="https://agentmods.dev/badge/instructions/romil569/repoguardian-rhd-enterprise/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/romil569/repoguardian-rhd-enterprise/agents-md"><img src="https://agentmods.dev/badge/instructions/romil569/repoguardian-rhd-enterprise/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 | $0.01433 | $0.01433 |
| Opus 5.5 | $0.00573 | $0.00573 |
| Sonnet 5.5 | $0.00287 | $0.00287 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade A, and why
RepoGuardian-RHD-Enterprise 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 2mo 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RepoGuardian Agent Notes
RepoGuardian is an agentic open-source maintainer assistant powered by RHD — Repository Health Director. RepoGuardian is the platform; RHD is the repository intelligence agent. Prompt 2 implements the compulsory hackathon pipeline: GitHub sync, repository-scoped indexing, project-aware RAG, deterministic agent tools, multi-step issue investigation, selective escalation, and evidence validation. Prompt 3 extends that pipeline with advanced duplicate detection, context-aware completeness, priority scoring, security signals, release-regression analysis, related PR intelligence, repository health, weekly brief, human feedback, evaluation metrics, and telemetry. Prompt 4 adds a human-in-the-loop maintainer workflow with safe action recommendations, review queue, approval/rejection, policy validation, GitHub action execution guards, and audit logging. The RHD upgrade adds repository URL onboarding, full repository review, deterministic intent routing, an Ask RHD console, issue clusters, top actions, workload intelligence, and public read-only repository analysis.
Architecture
backend/: FastAPI, Pydantic settings, SQLAlchemy models, Alembic migrations, service placeholders.backend/app/github/client.py: GitHub service interface currently backed by authenticated GitHub CLI for local development.backend/app/services/github_sync.py: repository connect/sync/upsert pipeline.backend/app/services/indexing.py: converts issues, PRs, comments, and releases into indexed repository documents.backend/app/rag/retriever.py: repository-filtered local vector/keyword retrieval fallback.backend/app/agents/tools/analysis.py: structured deterministic tools for classification, completeness, priority, escalation, similar issues, PRs, and releases.backend/app/agents/workflows/investigation.py: multi-step orchestrator with safe operational trace.backend/app/services/advanced_intelligence.py: deterministic Prompt 3 intelligence engines and repository analytics.backend/app/api/routes/analytics.py: health, weekly brief, and evaluation endpoints.backend/app/api/routes/investigations.py: human feedback endpoints for completed investigations.backend/app/api/routes/settings.py: non-secret policy settings endpoint.backend/app/services/action_recommendations.py: Prompt 4 recommendation, policy, approval, execution, and idempotency logic.backend/app/services/audit.py: append-oriented safe audit events.backend/app/api/routes/action_recommendations.py: review queue and action workflow endpoints.backend/app/api/routes/audit_log.py: audit log API.backend/app/services/rhd.py: RHD repository review, deterministic intent routing, tool orchestration, top actions, clustering, workload, and source-grounded answers.backend/app/api/routes/rhd.py: RHD onboarding, full review, initial scan, and query endpoints.backend/app/services/evidence.py: strict evidence source validation.frontend/: Next.js, TypeScript, Tailwind CSS, repository sync/search UI, investigation UI, health dashboards, feedback controls, and non-secret settings panels.infrastructure/: database initialization and future deployment assets.docs/: setup reports and architecture notes.demo/: harmless local demo source material.
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.
- 2mo ago First seen · 77 lines · 1,433 tokens per session scan A 7386f6ca3497
RepoGuardian-RHD-Enterprise AGENTS.md is an instructions file published in the GitHub repository romil569/RepoGuardian-RHD-Enterprise (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,433 tokens to every session, about $0.0057 per session on Opus 5.5. 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.
RepoGuardian-RHD-Enterprise AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| RepoGuardian-RHD-Enterprise AGENTS.mdromil569/RepoGuardian-RHD-Enterprise | Instructions file | 0 | 1mo ago | MIT | A | 1,433 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |