Borrowing it
Nothing to install: this file belongs to phense/agentic-rag. 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/phense/agentic-rag/main/CLAUDE.mdgit clone --depth 1 https://github.com/phense/agentic-ragWrote 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/phense/agentic-rag/claude-md)<a href="https://agentmods.dev/instructions/phense/agentic-rag/claude-md"><img src="https://agentmods.dev/badge/instructions/phense/agentic-rag/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/phense/agentic-rag/claude-md"><img src="https://agentmods.dev/badge/instructions/phense/agentic-rag/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 | $0.00900 | $0.00900 |
| Opus 5.5 | $0.00360 | $0.00360 |
| Sonnet 5.5 | $0.00180 | $0.00180 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
agentic-rag CLAUDE.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 15d 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.
This is a copy
100% identical to agentic-rag AGENTS.md — 19 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shared knowledge engine
This repository is the canonical memory and knowledge engine shared by Claude Code and Codex.
Read README.md and the relevant document under docs/ before changing behavior.
Invariants
- Preserve one PostgreSQL + pgvector store for all clients. Never fork data by agent provider.
- All writes pass through the audited gateway (
rag saveormemory_save); never hand-write rows, embeddings, deduplication state, or audit records. - Keep both MCP privilege levels:
agentic-ragfor an authorized main session andagentic-rag-rofor read-only/subagent use. - Claude and Codex adapters must remain additive and idempotent. Do not remove or overwrite another client's settings, hooks, or MCP configuration.
- Never expose database credentials or other secret values in logs, tests, documentation, or commits.
Production compatibility and upgrades
agentic-rag is an actively used production system with multiple users and knowledge domains. Every change must remain compatible with the running installation or provide a real, tested upgrade path from that installation. A fresh-install test alone is insufficient.
- Before changing behavior, identify the supported source version and affected schema, stored data, configuration, CLI/MCP contracts, hooks, jobs, and client integrations. Preserve existing users, domains, access boundaries, pins, knowledge, checkpoints, and audit history.
- Prefer additive, backward-compatible changes. Account for active sessions, concurrent clients, queued work, and old/new client versions during an upgrade; document any required restart or maintenance window. Never silently reset, reinitialize, or discard production state.
- If compatibility cannot be preserved, deliver the upgrade path with the change: supported source/target versions, preflight checks, verified backup, exact migration and deployment order, safe retry/resume after interruption, post-upgrade checks, and rollback or tested recovery with explicit limits on downgrade and data loss. Preserve the audited write boundary.
- Verify affected existing-installation workflows. Rehearse migrations and recovery on an isolated representative multi-user, multi-domain installation before production rollout. Record commands, results, and remaining risks in the PR; a written plan without verification is insufficient.
- Do not merge a change that lacks compatibility evidence or its required verified upgrade path. Merge approval does not itself authorize production deployment, migration, or service interruption.
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.
- 15d ago First seen · 66 lines · 900 tokens per session scan A 31f3cb0e4586
agentic-rag CLAUDE.md is an instructions file published in the GitHub repository phense/agentic-rag (0 stars, last pushed 14d ago), licensed MIT. It adds 900 tokens to every session, about $0.0036 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to agentic-rag AGENTS.md, differing in 19 lines, and is treated as a copy.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.