agentmods.dev

wlanpi-mcp: Instructions file for Codex

AGENTS.md

wlanpi-mcp AGENTS.md is an instructions file for Codex, OpenCode from WLAN-Pi/wlanpi-mcp. It costs 1,041 tokens per session, scanned A, original, BSD-3-Clause.

Repository instructions for coding agents working on the WLAN-Pi MCP project. They explain branch and pull-request rules, version requirements, and the checks run by continuous integration, which automatically tests changes.

In plain words
What is it for?
Use them when changing the project to choose the right branch, update versions correctly, and run linting, type checks, formatting checks, and tests.
Why use it?
They help prevent invalid branches, mixed changes, version mismatches, and failed automated checks before a pull request is submitted.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is WLAN-Pi/wlanpi-mcp's own configuration. It tells Codex and OpenCode how to work on wlanpi-mcp 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 wlanpi-mcp configures →

not rated 6repo changed 2d ago A scan 1,041 tokens original BSD-3-Clause
View source ↗ WLAN-Pi/wlanpi-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to WLAN-Pi/wlanpi-mcp. 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/WLAN-Pi/wlanpi-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/WLAN-Pi/wlanpi-mcp

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 wlanpi-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wlan-pi/wlanpi-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/wlan-pi/wlanpi-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/wlan-pi/wlanpi-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/wlan-pi/wlanpi-mcp/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 wlanpi-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/wlan-pi/wlanpi-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/wlan-pi/wlanpi-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,041 This file is loaded in full into every session.
When invoked 1,041 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01041 $0.01041
Opus 5.5 $0.00416 $0.00416
Sonnet 5.5 $0.00208 $0.00208
Haiku 4.5 $0.00104 $0.00104

Measured 2d ago against content hash 48eeef25a38f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wlanpi-mcp 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.

AGENTS.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guidance for coding agents

Read this first.

Branch and PR rules

  • PRs target main (the default branch).
  • Always branch from main, never from another PR branch. Rebase or recreate your branch if it has drifted; do not stack PR branches.
  • One concern per PR. Size is a soft target: above 500 changed lines, add a Review order section to the description; above 1,000 is fine when the change is cohesive. Split only at real seams, never to hit a number. Put moves and formatting in separate commits from behavioral changes. Full policy: developer guide.
  • Only a release pull request edits debian/changelog or wlanpi_mcp/__version__.py. A fix or a feature pull request leaves both unchanged. Do not add a Debian revision -N. The release sets both files to the same major.minor.patch. Follow Land a Fix and Cut a Release.
  • The dev-build stamp is planned. It is not live yet. When it is, CI writes X.Y.Z~dev<YYYYMMDD>.<run_id>.<run_attempt>+g<sha> in the build workspace, uploads that .deb to Packagecloud wlanpi/dev, and does not tag it. Under that same CI, the release pull request uploads to wlanpi/main and tags v<version>.

Tooling and gates

All checks run through tox and are wired into CI workflows: python-lint-police.yml (lint), python-format-police.yml (formatcheck), test-python-package.yml (tests).

Before committing, run the gates that your change touches:

  • tox -e lint : ruff check wlanpi_mcp tests then mypy wlanpi_mcp
  • tox -e formatcheck : ruff format --check wlanpi_mcp tests
  • tox : the py313 test suite plus coverage

tox -e format rewrites the tree with ruff format when the check fails.

Rules that bite

  1. mypy runs against the installed package. The lint env deliberately omits skip_install so tox installs the package and its runtime deps; that is what lets mypy resolve mcp, uvicorn, httpx, and so on. Do not add skip_install = true to [testenv:lint], or every import becomes import-not-found.
  2. No bare generic annotations. mypy.ini sets disallow_any_generics, so dict, set, list, and tuple need explicit type arguments. Follow the existing convention: JSON payloads are dict[str, Any]. Add Any to the existing typing import rather than a new import line.
  3. MCP docstrings are user-facing. The MCP SDK serves each tool's, resource's, and prompt's __doc__ verbatim as its description to every client. A missing or vague docstring shows up directly in the client's tools/list. ruff enforces Google-convention docstrings (D100-D106, D205, D401, D415) on the package; tests/** is exempt from the presence rules because test names self-describe.
  4. Line length is owned by the formatter. E501 is disabled; let ruff format wrap long lines. Do not hand-wrap to satisfy a linter that is off.
  5. Coverage artifacts are never committed. .coverage, coverage.xml, and coverage.svg regenerate on every tox run and are gitignored. Do not git add them.
  6. Whitespace is handled by ruff (W291/W293). There are no whitespace scripts; do not reintroduce them.

Read the full file on GitHub · 80 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. 2d ago Changed · +5 lines · +114 tokens per session 48eeef25a38f
  2. 1mo ago Changed · +4 lines · +91 tokens per session bb5c29c75356
  3. 1mo ago First seen · 71 lines · 836 tokens per session scan A 168662a26acd

Subscribe to this mod's changes

wlanpi-mcp AGENTS.md is an instructions file published in the GitHub repository WLAN-Pi/wlanpi-mcp (6 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 1,041 tokens to every session, about $0.0042 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 2026-09-18.

CommitsGit and workflowTesting
Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens