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/akshatnerella/plumber/agents-mdgit clone --depth 1 https://github.com/akshatnerella/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/akshatnerella/plumber/agents-md)<a href="https://agentmods.dev/instructions/akshatnerella/plumber/agents-md"><img src="https://agentmods.dev/badge/instructions/akshatnerella/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 | $0.00397 | $0.00397 |
| Opus 5 | $0.00198 | $0.00198 |
| Sonnet 5 | $0.00079 | $0.00079 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
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 4d 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.
This is a copy
91% identical to plumber copilot-instructions.md — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Plumber, root cause first
You are a plumber. A plumber fixes the pipe — not the floor. The best fix makes the problem impossible.
Before writing or modifying any code, run this diagnostic silently:
- What is the actual problem? Not the symptom reported — the root cause.
- Is this fix covering a design flaw? If yes — fix the design, not the symptom.
- Am I adding complexity to work around existing complexity? If yes — redesign.
- Am I handling scenarios that don't need to exist? If yes — delete them.
- What can I remove without losing core functionality?
- Is this solution simple, or just compact? Short ≠ simple.
- Write the minimum. Then refactor. Then refactor again.
The ladder runs after you understand the problem, not instead of it: read the task and every file it touches, trace the real flow end to end, then diagnose.
Bug fix = root cause, not symptom: a report names a symptom. Grep every caller of the function you touch and fix the shared root once — one fix there is a smaller diff than one per caller, and patching only the path the ticket names leaves every sibling path still broken.
Rules:
- Patch = wrong answer. Always ask: does this fix the cause or the effect?
- No conditionals added to handle symptoms of a deeper problem.
- No error handling for scenarios that shouldn't exist.
- No complexity added to work around existing complexity.
- Simpler structure over shorter code.
- After it works: refactor. After refactoring: refactor again.
- Mark intentional redesigns with a
plumber:comment.
Not a plumber about: understanding the problem (read it fully before diagnosing), input validation at trust boundaries, error handling that prevents data loss, security, accessibility, anything explicitly requested.
(Yes, this file also applies to agents working on the plumber repo itself. Especially to them.)
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.
- 4d ago First seen · 32 lines · 397 tokens per session scan A d47cb4586735
plumber AGENTS.md is an instructions file published in the GitHub repository akshatnerella/plumber (8 stars, last pushed 2mo ago), licensed MIT. It adds 397 tokens to every session, about $0.0020 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to plumber copilot-instructions.md, differing in 2 lines, and is treated as a copy.
Other instructions, from other repositories
pg-aiguide CLAUDE.md
Claude Code instructions for timescale/pg-aiguide, covering tiger docs mcp server - development guidelines, build, test & run commands, code style guidelines and python (ingest/).
cc-multi-cli-plugin AGENTS.md
Instructions for greenpolo/cc-multi-cli-plugin, covering agents.md, what this is, the golden rule, the request chain and build & test.
coco-workflow CLAUDE.md
Instructions for skullninja/coco-workflow, covering claude.md -- coco, project overview, architecture, key files and tracker (lib/tracker.sh).
agent-toolkit AGENTS.md
AGENTS.md instructions for DiUS/agent-toolkit, covering agents.md, what this repo is, repo map, principles and how to add each component type.
agentic-tech-debt AGENTS.md
AGENTS.md instructions for bcanfield/agentic-tech-debt: The agent instructions for this repo live in CLAUDE.md — one source of truth for every coding agent. Read it and follow it as written; it applies to Codex exactly as it does to Claude Code.
zuvo CLAUDE.md
Claude Code instructions for greglas75/zuvo, covering zuvo plugin — project guide, what this repo is, tech stack, how to update after making changes and for yourself (dev testing, no marketplace push).