What is plumb AGENTS.md?

Repository instructions for Plumb, a codebase whose tools manage file access, tasks, diagnostics, and session tracking.

They are for editing the correct source file, starting sessions, protecting against concurrent edits, using configured task runners, and checking project versions and changes.

They define how contributors should work safely with Plumb's tools and prevent changes from bypassing its safeguards.

How plumbkit/plumb configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to plumbkit/plumb. 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/plumbkit/plumb/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/plumbkit/plumb

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/plumbkit/plumb/agents-md/github.svg)](https://agentmods.dev/instructions/plumbkit/plumb/agents-md)

Your own site

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

Per session 1,858 This file is loaded in full into every session.

When invoked 1,858 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	$0.01858	$0.01858
Opus 5.5	$0.00743	$0.00743
Sonnet 5.5	$0.00372	$0.00372
Haiku 4.5	$0.00186	$0.00186

Measured 22d ago against content hash a53af3604952, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

plumb 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 22d 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 · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plumb — Agent Instructions

Source of truth: edit AGENTS.md only. CLAUDE.md and GEMINI.md are relative symlinks to it; never edit, replace, or unlink those paths.

This is the always-loaded engineering contract for the public Plumb codebase. Keep rules here and reference detail in docs/; make check-brief enforces the budget.

Working contract

Use Plumb's lane. When Plumb exposes a capability, use its MCP tool instead of native file, search, shell, or Git tools. Native tools bypass Plumb's concurrency guards, diagnostics, and session tracking. Exceptions are capabilities Plumb does not cover and read-only commodity tools hidden by a lean profile.
Bootstrap and guard writes. Call session_start first, passing a stable per-agent session_id (on Claude Code the identity hook supplies it and stamps every later call; a session_id alone identifies only that call). After read_file, use Plumb edits and pass its mtime or sha256 as expected_mtime or expected_sha when a concurrent writer may intervene. Prefer configured run_task slots over raw build/test/lint commands.
Trust live descriptions. Tool behaviour and schemas come from tools/list; session_start supplies client-specific guidance. This brief is orientation, not a second tool reference.
Avoid version drift. Read VERSION and CHANGELOG.md for the current version.

Purpose and invariants

Plumb gives coding agents an IDE intelligence layer over MCP: LSP semantics, a tree-sitter topology index, project memory, and a complete safe-filesystem toolkit. plumb serve is a resilient stdio proxy in front of a shared daemon.

LSP-correct semantics. Writes notify language servers through workspace/didChangeWatchedFiles; capabilities are negotiated, including server-initiated registration.
Concurrency-safe durability. Write tools use per-path locks, optimistic checks, atomic rename, and the shared durable-write path.
Per-session isolation. Read tracking, rate limits, and caches belong to a connection or declared agent, never accidental process globals.
Configurable safety. Compiled defaults, global config, project config, and environment overrides resolve with explicit provenance.

Read the full file on GitHub · 89 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.

22d ago Changed a53af3604952
24d ago Changed · +30 tokens per session d4a729c85c37
25d ago Changed 3f8a893aa51c
29d ago Changed e3f671ccba1c
1mo ago Changed · +16 tokens per session a4e13f8b0672
1mo ago Changed · +9 tokens per session 49385f9928bc
1mo ago Changed · +19 tokens per session 7c99662df140
2mo ago First seen · 89 lines · 1,784 tokens per session scan A f2a4ee88657b

Subscribe to this mod's changes

plumb AGENTS.md is an instructions file published in the GitHub repository plumbkit/plumb (4 stars, last pushed 5d ago), licensed MIT. It adds 1,858 tokens to every session, about $0.0074 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.

Go claude coding-agent language-server lsp mcp

plumb AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
plumb AGENTS.mdplumbkit/plumb	Instructions file	4	5d ago	MIT	A	1,858	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

plumb: Instructions file for Codex