agentmods.dev

plumb AGENTS.md

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

In plain words
What is it for?
They are for editing the correct source file, starting sessions, protecting against concurrent edits, using configured task runners, and checking project versions and changes.
Why use it?
They define how contributors should work safely with Plumb's tools and prevent changes from bypassing its safeguards.

Instructions file for CodexOpenCode

4 yesterday A scan 1,784 tokens original MIT
View the source file plumbkit/plumb
Install

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.

agentmods
npx agentmods add instructions/plumbkit/plumb/agents-md
Clone the repo
git clone --depth 1 https://github.com/plumbkit/plumb

Made for: Codex, OpenCode.

Per session 1,784 This file is loaded in full into every session.
When invoked 1,784 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01784 $0.01784
Opus 5 $0.00892 $0.00892
Sonnet 5 $0.00357 $0.00357
Haiku 4.5 $0.00178 $0.00178

Measured yesterday against content hash f2a4ee88657b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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. 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.

  1. LSP-correct semantics. Writes notify language servers through workspace/didChangeWatchedFiles; capabilities are negotiated, including server-initiated registration.
  2. Concurrency-safe durability. Write tools use per-path locks, optimistic checks, atomic rename, and the shared durable-write path.
  3. Per-session isolation. Read tracking, rate limits, and caches belong to a connection or declared agent, never accidental process globals.
  4. 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.

  1. yesterday 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 yesterday), licensed MIT. It adds 1,784 tokens to every session, about $0.0089 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 2026-08-31.

Data and AIDebuggingPlanningclaudecoding-agentgolanglanguage-serverlspmcp
Related

Other instructions, from other repositories

yayamlls AGENTS.md

AGENTS.md instructions for home-operations/yayamlls, covering agents.md: yayamlls, working in this repo: ai usage, commits, and safety, baseline, project layout and errors.

home-operations/yayamlls · 2,991 tokens

yayamlls CLAUDE.md

Claude Code instructions for home-operations/yayamlls, a project described as: YAML language server in Go. Schema-driven diagnostics, completion, hover; pluggable rendering for Flux HelmRelease and Kustomization via flate.

home-operations/yayamlls · 5 tokens

pi-go CLAUDE.md

Instructions for dimetron/pi-go, covering claude.md — pi-go, work in a git worktree, not the primary checkout, where worktrees live, what pi-go's agent already does, and why it matters and commits: all commits must be signed.

dimetron/pi-go · 4,720 tokens

glowbom-oss AGENTS.md

Instructions for glowbom/glowbom-oss, covering workspace instructions, public repository boundary and commit messages.

glowbom/glowbom-oss · 151 tokens

GoSQLX CLAUDE.md

Instructions for ajitpratap0/GoSQLX, covering claude.md, project overview, architecture, core components and token processing pipeline.

ajitpratap0/GoSQLX · 2,469 tokens

witness AGENTS.md

AGENTS.md instructions for IngTian/witness, covering agents.md, what this is, build, test, run, architecture (where things live) and runtime model (important invariants).

IngTian/witness · 2,008 tokens