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/rcconsult/ppxai/agents-mdgit clone --depth 1 https://github.com/rcconsult/ppxaiWrote 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/rcconsult/ppxai/agents-md)<a href="https://agentmods.dev/instructions/rcconsult/ppxai/agents-md"><img src="https://agentmods.dev/badge/instructions/rcconsult/ppxai/agents-md.svg" alt="Measured on agentmods" 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 | $0.11974 | $0.11974 |
| Opus 5 | $0.05987 | $0.05987 |
| Sonnet 5 | $0.02395 | $0.02395 |
| Haiku 4.5 | $0.01197 | $0.01197 |
Grade C, and why
ppxai AGENTS.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 3d 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.
# - claim_without_action: safety guardrails refuse /etc/shadow How it starts
The opening of the file, as written. The whole thing — 583 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Global Preferences
Code Style
- Python 3.10+ with type hints
- Use dataclasses for data structures
- Async/await for I/O operations
- pytest for testing
Tool Usage
- Prefer
apply_patch/replace_blockoverwrite_filefor existing files - Use
read_fileinstead ofcat/typeshell commands - Execute tools directly - don't explain what you're about to do
- Report results briefly after tool execution
Project: ppxai
ppxai is a terminal-based UI application for interacting with multiple AI providers (Perplexity AI, OpenAI, Gemini, local models via Ollama/vLLM).
Architecture
ppxai/engine/- Core business logic (no UI dependencies)ppxai/engine/providers/- Provider implementations:openai_native.py- Native OpenAI (GPT-5.x, o-series, Codex via Responses API)gemini.py- Native Gemini (google-genai SDK; native function_call/function_response tool threading)openai_compat.py- OpenAI-compatible (Perplexity, local/vLLM, custom)
ppxai/engine/model_profiles.py- Per-model behavioral profiles (tool calling, API routing)ppxai/engine/tools/- Tool system with builtins + brace-counting JSON parsernetwork_policy.py- AC-2 egress allowlist (fail-closed, https-only, SSRF guard)filesystem_policy.py- filesystem seal (per-run read/write jail;tools.agent.sandbox)agent_scoped_tools.py- AC-1 per-run tool allowlist (ScopedToolManagerchokepoint)
ppxai/engine/agent_runs.py- agent-platform run registry (AgentRunRegistry: lifecycle, events.jsonl, budgets, consent/ack/resume)ppxai/engine/agent_spec.py/agent_skill.py---spec/--skillloaders for the/tasktierppxai/server/- HTTP/SSE server for IDE integrationroutes/agent_v1.py-/v1/agent/{run,task,runs,...}(agent platform);routes/oneshot.py-/v1/oneshotgateway
ppxai/commands/- Slash command handlersppxai/config/- Configuration systemvscode-extension/- TypeScript VSCode extension (bundled via esbuild;taskController.tsfor the/taskfamily)
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.
- 3d ago First seen · 583 lines · 11,974 tokens per session scan C fb49cc05e5c0
ppxai AGENTS.md is an instructions file published in the GitHub repository rcconsult/ppxai (5 stars, last pushed 3d ago), licensed MIT. It adds 11,974 tokens to every session, about $0.0599 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 2026-08-31.
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).
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.
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.
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).
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.