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.
npx agentmods add instructions/aigentive/ralphx/agents-mdgit clone --depth 1 https://github.com/aigentive/RalphXWhat 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 | $0.04046 | $0.04046 |
| Opus 5 | $0.02023 | $0.02023 |
| Sonnet 5 | $0.00809 | $0.00809 |
| Haiku 4.5 | $0.00405 | $0.00405 |
Grade A, and why
RalphX 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 2d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintainer note: Keep this file compact. Prefer one-line rules, links to source docs, and explicit non-negotiables over prose.
AGENTS.md
Project
RalphX — native Mac GUI for autonomous AI development with Rust/Tauri backend and React frontend.
Primary project docs:
CLAUDE.mdfrontend/CLAUDE.mdsrc-tauri/CLAUDE.md.claude/rules/*.md.claude/rules/openai-gpt-5-prompting.mdfor target-model prompt-guide routing across supported GPT-5 familiesdocs/ai-docs/openai/README.mdfor GPT-5.4, GPT-5.5, and GPT-5.6 family guides plus official-source links.claude/rules/ideation-verification-architecture.mdfor the ideation verification feature map: parent-vs-child ownership, runtime flow, UI surfaces, debugging, and tests.claude/rules/delegation-topology.mdfor canonical delegation allowlists, auto-injected delegation guidance, and MCP visibility/enforcement rules.claude/rules/runtime-root-vs-target-project.mdfor the contract between RalphX-owned runtime/plugin/log roots and the user’s active target project checkout.claude/rules/production-cli-resolution.mdfor Finder/Homebrew-safe CLI binary resolution in installed app runtime paths.claude/rules/codeql-path-safety.mdfor CodeQL-safe filesystem sink validation when paths are influenced by env vars, settings, HTTP/MCP payloads, DB state, agent metadata, or repo contents.claude/rules/multi-harness.mdfor provider-neutral runtime/config/event rules and documentation sync requirements.claude/rules/agent-thinking-capture.mdanddocs/architecture/agent-thinking-capture.mdfor cross-harness reasoning capture, capability probing, event/persistence ownership, failure edges, and focused proofs.claude/rules/agent-mcp-tools.mdfor multi-layer agent MCP/tool alignment across canonical agent metadata, harness runtime config, prompt contracts, and MCP registration.claude/rules/agent-workspace-review-modes.mdfor the non-interchangeable local Workspace Review gate and remote GitHub Review PR workflow.claude/rules/merge-recovery-consistency.mdfor the coupled merge-failure behavior across merge outcome handling, manual retry, reconciliation, startup recovery, and MergeIncomplete UI.claude/rules/stateful-workflow-review.mdfor false-success review of completion/cache/retry/recovery/state-machine changes.claude/rules/task-state-machine.mdfor the 28 internal task statuses, the transition table, and the validated transition API contract.claude/rules/big-pr-review-checklist.mdfor the recurring failure classes big PRs ship here and the 12 falsifiable pre-merge checks that catch them.claude/rules/rust-test-execution.mdfor selective Rust test commands, the standard Rust test stack, shared SQLite fixtures/builders, and the no-broad-fmtrule.claude/rules/wkwebview-css-vars.mdfor Tauri (WKWebView) CSS custom-property inheritance rules — theme tokens for bg/text/border MUST be literals, not chainedvar()references.claude/rules/release-script-validation.mdfor safe validation of release proposal/wrapper scripts without triggering real publish steps.claude/rules/icon-only-buttons.mdfor accessible tooltip requirements on icon-only controls.claude/rules/frontend-interaction-performance.mdfor non-negotiable lazy loading, first-paint-safe UI transitions, deferred hydration/teardown, and decoupled panel/drawer interactions.claude/rules/visual-testing.mdfor Playwright-first visual QA, scoped dev-server use, and the explicit-request-only Computer Use boundary.claude/rules/pr-descriptions.mdfor reviewer-focused PR bodies: context, impact, decisions, risks; validation logs stay secondary
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.
- 2d ago First seen · 128 lines · 4,046 tokens per session scan A e934aa6f306d
RalphX AGENTS.md is an instructions file published in the GitHub repository aigentive/RalphX (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 4,046 tokens to every session, about $0.0202 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 2026-08-31.
Other instructions, from other repositories
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.