garbage-man AGENTS.md

An instruction file for the garbage-man repository’s email-cleaner feature. It directs agents to the feature’s skill and defines how mailbox information and cleanup decisions must be handled.

In plain words
What is it for?
Use it when installing, running, or using the repository’s email cleaner, including reviewing mailbox metadata and preparing cleanup decisions.
Why use it?
It helps prevent accidental email changes and keeps mailbox data outside the public repository while preserving a consistent cleanup process.

Instructions file for CodexOpenCode

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/everyinc/garbage-man/agents-md
Clone the repo
git clone --depth 1 https://github.com/EveryInc/garbage-man

Made for: Codex, OpenCode.

Per session 138 This file is loaded in full into every session.
When invoked 138 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 $0.00138 $0.00138
Opus 5 $0.00069 $0.00069
Sonnet 5 $0.00028 $0.00028
Haiku 4.5 $0.00014 $0.00014

Measured 2d ago against content hash d61af41d9f70, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

garbage-man 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 2d 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 · 8 lines

What it actually says

Email Cleaner agent instructions

When a user asks to install, run, or use this repository, read and follow plugins/email-cleaner/skills/email-cleanup/SKILL.md.

Treat mailbox access as read-only through inventory and review. Prefer an email connector already available to the agent. Otherwise use the read-only IMAP adapter or accept canonical message metadata JSONL. Never ask the user to paste an email password or app password into chat; have them set credentials locally as environment variables.

Keep all mailbox metadata and decisions in the user's workspace under .mailroom/, never in this repository. Do not apply generated rules or alter existing email unless the user separately gives explicit write authorization.

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. 2d ago First seen · 8 lines · 138 tokens per session scan A d61af41d9f70

Subscribe to this mod's changes

garbage-man AGENTS.md is an instructions file published in the GitHub repository EveryInc/garbage-man (5 stars, last pushed 23d ago), licensed MIT. It adds 138 tokens to every session, about $0.0007 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.