pplx-proxy: Instructions file for Codex

AGENTS.md

pplx-proxy AGENTS.md is an instructions file for Codex, OpenCode from jamie950315/pplx-proxy. It costs 6,191 tokens per session, scanned B, original, MIT.

Repository instructions for pplx-proxy, a self-hosted service that forwards requests to Perplexity.ai and exposes them through an OpenAI-compatible API and MCP, a standard for connecting AI tools to applications.

In plain words
What is it for?
Use it when modifying the FastAPI server, request translation, streaming responses, model discovery, session keep-alive tasks, or account-tier filtering.
Why use it?
It gives a coding agent the system’s architecture, model access rules, and important request settings so changes are made with the proxy’s constraints in mind.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions Codex.

This is jamie950315/pplx-proxy's own configuration. It tells Codex and OpenCode how to work on pplx-proxy itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pplx-proxy configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jamie950315/pplx-proxy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jamie950315/pplx-proxy/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/jamie950315/pplx-proxy

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for pplx-proxy AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jamie950315/pplx-proxy/agents-md/github.svg)](https://agentmods.dev/instructions/jamie950315/pplx-proxy/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jamie950315/pplx-proxy/agents-md"><img src="https://agentmods.dev/badge/instructions/jamie950315/pplx-proxy/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.

agentmods 80×15 button for pplx-proxy AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jamie950315/pplx-proxy/agents-md"><img src="https://agentmods.dev/badge/instructions/jamie950315/pplx-proxy/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,191 This file is loaded in full into every session.
When invoked 6,191 The same file — it is already loaded in full.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.06191 $0.06191
Opus 5.5 $0.02476 $0.02476
Sonnet 5.5 $0.01238 $0.01238
Haiku 4.5 $0.00619 $0.00619

Measured 1mo ago against content hash e051d9efcd40, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

pplx-proxy AGENTS.md scanned grade B with 2 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 1mo 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -X POST /admin/update-models -d '{"models":{"new":["pro","pref"]},"merge":true}'

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST /admin/update-models -d '{"models":{"new":["pro","pref"]},"merge":true}'
AGENTS.md · 461 lines

How it starts

The opening of the file, as written. The whole thing — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

What This Is

pplx-proxy is a self-hosted reverse proxy for Perplexity.ai. Uses your Pro/Max subscription cookie to access all models through OpenAI-compatible REST API and MCP server.

Current Work and Deployment (2026-09-09)

  • Release: image input, local file storage, and the experimental Responses function bridge are included in main. Deployed application commit: 5c89981 on Pi5, pplx-proxy.service, port 8892.
  • The user authorized merging codex/attachments-function-tools into main and deploying this release. Use isolated runtime data and a separate localhost port for further testing; verify the running service before claiming a successful rollout.
  • Post-deployment public checks passed at https://pplx.0ruka.dev: ordinary Chat, streaming Chat, Responses, official SDK Chat/Responses PNG input, and Files create/retrieve/delete. Perplexity substituted gpt56_terra with gpt5_nano during the image checks; image recognition still passed. Existing credentials were preserved.
  • /v1/files local upload/read/delete passed; limits are 20 MiB per file and 200 MiB total. Local storage success is not proof of upstream document reading.
  • Documents remain incomplete: upstream upload must be followed by /rest/sse/attachment_processing/subscribe and confirmed completion. Cloudflare currently returns 403; document requests explicitly fail with 502. Do not report document support as complete.
  • Responses function bridge is experimental and unreliable. One official SDK auto-selection/client-execution/stream-continuation loop passed; a repeat returned non-JSON output and correctly failed with response.failed / tool_protocol_error, so SDK get_final_response() had no completed response. It is prompt-mediated, not native Perplexity function calling. Do not claim stable or completed support; do not add fallback or automatic retry to hide failures.
  • Invalid protocol JSON/schema/tool choices fail with 502 (tool_protocol_error) or response.failed; never fall back to successful text. Function streams wait for complete validation before emitting callable items. Never execute client functions in the proxy.
  • Chat Completions function tools still return 400. When a stored function continuation omits tool definitions, preserve the full context and effective definitions but use tool_choice: none. Explicitly resend definitions to enable further calls.

Read the full file on GitHub · 461 lines

Changes

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.

  1. 1mo ago Changed · +19 lines · +673 tokens per session e051d9efcd40
  2. 1mo ago Changed · -205 lines · -1,897 tokens per session e4b0ede974e8
  3. 2mo ago Changed · +8 lines · +212 tokens per session cc1ce8197fe1
  4. 2mo ago First seen · 639 lines · 7,203 tokens per session scan B 88f4b0fc4795

Subscribe to this mod's changes

pplx-proxy AGENTS.md is an instructions file published in the GitHub repository jamie950315/pplx-proxy (30 stars, last pushed 1mo ago), licensed MIT. It adds 6,191 tokens to every session, about $0.0248 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

pplx-proxy AGENTS.md compared with instructions from other repositories

pplx-proxy AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pplx-proxy AGENTS.mdjamie950315/pplx-proxyInstructions file301mo agoMITB6,191Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode