What is pyaireader AGENTS.md?

A set of project instructions in an AGENTS.md file for the PigeonAI-Yang/pyaireader project.

Use it when working on pyaireader, especially for platform searches, logged-in browser reading, article or tweet collection, and release or changelog work.

It gives coding agents the project’s rules for using skills, reading web content, collecting articles or posts, testing tools, and handling browser profiles.

How PigeonAI-Yang/pyaireader configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to PigeonAI-Yang/pyaireader. 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/PigeonAI-Yang/pyaireader/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/PigeonAI-Yang/pyaireader

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/pigeonai-yang/pyaireader/agents-md/github.svg)](https://agentmods.dev/instructions/pigeonai-yang/pyaireader/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/pigeonai-yang/pyaireader/agents-md"><img src="https://agentmods.dev/badge/instructions/pigeonai-yang/pyaireader/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/pigeonai-yang/pyaireader/agents-md"><img src="https://agentmods.dev/badge/instructions/pigeonai-yang/pyaireader/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 579 This file is loaded in full into every session.

When invoked 579 The same file — it is already loaded in full.

Security scan A 0 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.

Model	Per session	Once invoked
Fable 5.1	$0.00579	$0.00579
Opus 5.5	$0.00232	$0.00232
Sonnet 5.5	$0.00116	$0.00116
Haiku 4.5	$0.00058	$0.00058

Measured 1mo ago against content hash 93cea751c4c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pyaireader 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 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.

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.

AGENTS.md · 22 lines

How it starts

The opening of the file, as written. The whole thing — 22 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Rules

Agent Skills

For pyaireader usage, web reading, X/Twitter search, article/tweet collection, or MCP/CLI smoke tests, use the $pyaireader skill from skills/pyaireader/SKILL.md.
Keep skills/pyaireader/SKILL.md as the general reader entry point and platform index. Put special-platform procedures under skills/pyaireader/references/platforms/.
For logged-in or dynamic browser reads, use the dedicated edge_cdp_profile channel by default. It launches real Edge with pyaireader's own profile under ~/.pyaireader/edge-cdp-profiles/ and must not open tabs in the user's daily Edge windows.
For X/Twitter collection, edge_cdp_profile is the standard path. First-time login must be treated as part of the workflow: open browser-login or edge-cdp-profile-launch, give the user enough time to log in, then run a real search-platform x smoke test.
persistent_profile is a fallback/diagnostic path, not the X/Twitter standard path. Do not silently fall back to Playwright Chromium for X/Twitter work; if Edge is unavailable, report the browser configuration blocker.
X platform collection must not silently downgrade to anonymous web search. If search-platform x or MCP search_platform(platform="x") cannot run with a user browser session, report the task as incomplete and state the exact browser-session blocker.
Never bypass pyaireader's X request guard with an ad-hoc Playwright/CDP loop, repeated page.goto, parallel tabs, or concurrent profile/status reads. For any visible X interaction, use one tab, randomized pauses, cubic Bezier mouse movement, and real pointer clicks as defined in skills/pyaireader/references/platforms/x.md. If the current pyaireader command cannot perform the required interaction safely, stop and repair that path before collecting.

Release And Changelog

Shipped changes must not stay only under ## Unreleased. Before commit or push, move them into a dated section: ## X.Y.Z - YYYY-MM-DD.
When a release section is added, keep release metadata aligned in pyproject.toml, uv.lock, src/pyaireader/mcp/server.py, and docs/registry-server-json-candidate.json.
Do not edit old planning examples just because they mention an older version.
Before reporting release work as complete, run:
- uv lock if pyproject.toml version changed
- uv run python -c "from importlib.metadata import version; print(version('pyaireader'))"
- git diff --check

Read the full file on GitHub · 22 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.

1mo ago Changed · +1 lines · +98 tokens per session 93cea751c4c1
2mo ago First seen · 21 lines · 481 tokens per session scan A f177253369cc

Subscribe to this mod's changes

pyaireader AGENTS.md is an instructions file published in the GitHub repository PigeonAI-Yang/pyaireader (0 stars, last pushed 1mo ago), licensed MIT. It adds 579 tokens to every session, about $0.0023 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.

pyaireader AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pyaireader AGENTS.mdPigeonAI-Yang/pyaireader	Instructions file	0	1mo ago	MIT	A	579	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	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	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

pyaireader: Instructions file for Codex