agentmods.dev

PodlingsMCP: Instructions file for Codex

AGENTS.md

PodlingsMCP AGENTS.md is an instructions file for Codex, OpenCode from justinmclean/PodlingsMCP. It costs 467 tokens per session, scanned A, original, MIT.

A project guide for coding agents working on an Apache project that analyzes incubator podlings. Podlings are projects in Apache’s trial phase before graduation or retirement.

In plain words
What is it for?
Use it when working with podlings.xml data, sponsor filters, completion rates, timelines, durations, MCP tool handlers, or the server’s test suite.
Why use it?
It explains the code layout, data meanings, defaults, and checks needed when changing the XML parser, tools, protocol, or tests.

Instructions file for CodexOpenCode

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

This is justinmclean/PodlingsMCP's own configuration. It tells Codex and OpenCode how to work on PodlingsMCP 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 PodlingsMCP configures →

not rated 0repo 6mo ago A scan 467 tokens original MIT
View source ↗ justinmclean/PodlingsMCP
Reuse

Borrowing it

Nothing to install: this file belongs to justinmclean/PodlingsMCP. 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/justinmclean/PodlingsMCP/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/justinmclean/PodlingsMCP

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 PodlingsMCP AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/justinmclean/podlingsmcp/agents-md"><img src="https://agentmods.dev/badge/instructions/justinmclean/podlingsmcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 467 This file is loaded in full into every session.
When invoked 467 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 $0.00467 $0.00467
Opus 5.5 $0.00187 $0.00187
Sonnet 5.5 $0.00093 $0.00093
Haiku 4.5 $0.00047 $0.00047

Measured 2mo ago against content hash 779a1ff03152, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

PodlingsMCP 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 2mo 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 · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS

Purpose

This repository contains a small dependency-light MCP server for working with Apache Software Foundation Incubator podlings.xml data.

Project Layout

  • podlings/data.py
    • XML loading, parsing, normalization, sponsor classification, and date/duration helpers
  • podlings/tools.py
    • MCP tool handlers and shared argument/analytics helpers
  • podlings/schemas.py
    • Shared tool schema fragments and schema-builder helpers
  • podlings/protocol.py
    • JSON-RPC/MCP stdio protocol handling
  • server.py
    • Thin entrypoint
  • tests/
    • Unit and integration tests
  • tests/fixtures.py
    • Shared Python test fixtures and temp XML helpers
  • tests/fixtures/
    • File-based test fixtures such as sample-podlings.xml

Key Defaults And Concepts

  • sponsor_type defaults to incubator for filtering and analytics tools unless explicitly overridden.
  • completed means podlings that reached an end state: graduated or retired.
  • Count/rate timeline tools place results into years using enddate.
  • Duration timeline tools use both startdate and enddate.

Developer Workflow

Use these commands before finishing changes:

  • make check-format
  • make lint
  • make typecheck
  • make test

CI runs the same checks in GitHub Actions.

Contribution Guidelines

  • Keep new MCP tool schema definitions in podlings/schemas.py.
  • Keep MCP protocol wiring in podlings/protocol.py.
  • Prefer extending shared helpers in podlings/tools.py over copying analytics logic.
  • Add tests for any new tool, filter, or output shape.
  • Update README.md when adding or changing public MCP tools or defaults.
  • Keep test-only data under tests/fixtures.py or tests/fixtures/ rather than at the repo root.

Testing Notes

  • Direct tool behavior belongs in tests/test_tools.py.
  • Parsing/data behavior belongs in tests/test_data.py.
  • Protocol helper behavior belongs in tests/test_protocol.py.
  • End-to-end MCP stdio coverage belongs in tests/test_mcp_integration.py.

Read the full file on GitHub · 59 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. 2mo ago First seen · 59 lines · 467 tokens per session scan A 779a1ff03152

Subscribe to this mod's changes

PodlingsMCP AGENTS.md is an instructions file published in the GitHub repository justinmclean/PodlingsMCP (0 stars, last pushed 6mo ago), licensed MIT. It adds 467 tokens to every session, about $0.0019 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.

Related

PodlingsMCP AGENTS.md compared with instructions from other repositories

PodlingsMCP AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
PodlingsMCP AGENTS.mdjustinmclean/PodlingsMCPInstructions file06mo agoMITA467Codex, 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