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/marcoporcellato/matryca-plumber/agents-mdgit clone --depth 1 https://github.com/MarcoPorcellato/matryca-plumberWrote 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/marcoporcellato/matryca-plumber/agents-md)<a href="https://agentmods.dev/instructions/marcoporcellato/matryca-plumber/agents-md"><img src="https://agentmods.dev/badge/instructions/marcoporcellato/matryca-plumber/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 | $0.02428 | $0.02428 |
| Opus 5 | $0.01214 | $0.01214 |
| Sonnet 5 | $0.00486 | $0.00486 |
| Haiku 4.5 | $0.00243 | $0.00243 |
Grade A, and why
matryca-plumber 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Matryca Plumber instruction router
This file routes coding assistants to the correct instruction layer. Do not load every doc at once.
Audience map
| You are… | Read first | Do not load |
|---|---|---|
| Repository coding agent | This file; then activate only the matching .agents/skills/ adapter below |
Full SYSTEM_PROMPT.md and broad architecture docs unless the task requires them |
| Cursor agent patching this repo | This file + Cursor's matching .cursor/rules/ selected by glob/trigger |
Full SYSTEM_PROMPT.md (runtime vault law) |
| External agent on a user Logseq vault | llms.txt → SYSTEM_PROMPT.md |
.cursor/rules/ |
| Maintainer changing MCP/CLI/prompt contracts | docs/PROMPT_ARCHITECTURE.md, docs/openspec/agent-onboarding.md, docs/openspec/agent/, docs/openspec/llm-performance.md, rule 11-prompt-maintainer |
— |
| Maintainer planning v2.0 Shadow DB | docs/roadmaps/ROADMAP_V2_PREPARATION.md, v2_preparation_blueprints.md, Epic #20 |
Full v1.9.x audit triage docs |
Instruction loading strategy
.cursor/rules/is the canonical detailed policy set. Do not copy those rules into this file..agents/skills/contains thin, open Agent Skills adapters. Their metadata is cheap to discover; each adapter loads its canonical.mdconly when its task trigger applies.- Keep this root file limited to always-on constraints and routing. Do not preload all rules or linked SSOT documents.
- Do not rely on nested
AGENTS.mdfor file-glob behavior: instruction discovery follows the launch directory, not every file later edited. Prefer a task-triggered skill for cross-directory work.
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.
- 5d ago First seen · 114 lines · 2,428 tokens per session scan A f124e4c13491
matryca-plumber AGENTS.md is an instructions file published in the GitHub repository MarcoPorcellato/matryca-plumber (96 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,428 tokens to every session, about $0.0121 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
aionforge-memory AGENTS.md
Instructions for jscott3201/aionforge-memory, covering agent guide for aionforge memory, start here, workspace layout, core invariants and running locally.
llm-wiki-agent GEMINI.md
Gemini CLI instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
remnic AGENTS.md
AGENTS.md instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.
braindb CLAUDE.md
Claude Code instructions for dimknaf/braindb, covering braindb — claude instructions, ⚠ tool priority — read this first, it overrides habit, at the start of every session, 1. get always-on rules (behavioral guidelines) and project structure.
pydantic-ai-todo CLAUDE.md
Instructions for vstorm-co/pydantic-ai-todo, covering claude.md, what this project is, commands, structure and core pattern.
tpu_performance_autoresearch_wiki AGENTS.md
Instructions for vlasenkoalexey/tpu_performance_autoresearch_wiki, covering codex instructions, compatibility, operating rules and codex translation notes.