work-assistant AGENTS.md

work-assistant AGENTS.md is an instructions file for Codex, OpenCode from Wulfgardr/work-assistant. It costs 218 tokens per session, scanned A, original, MIT.

A set of contributor instructions for Work Assistant, a local email-management project designed to work independently of any email provider.

In plain words
What is it for?
Use it when contributing code, tests, screenshots, or documentation to Work Assistant, especially before committing changes.
Why use it?
It sets rules for privacy, separating email inspection from writing, and keeping provider-specific behavior out of the core.

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/wulfgardr/work-assistant/agents-md
Clone the repo
git clone --depth 1 https://github.com/Wulfgardr/work-assistant

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.

agentmods badge for work-assistant AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wulfgardr/work-assistant/agents-md.svg)](https://agentmods.dev/instructions/wulfgardr/work-assistant/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/wulfgardr/work-assistant/agents-md"><img src="https://agentmods.dev/badge/instructions/wulfgardr/work-assistant/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 218 This file is loaded in full into every session.
When invoked 218 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 $0.00218 $0.00218
Opus 5 $0.00109 $0.00109
Sonnet 5 $0.00044 $0.00044
Haiku 4.5 $0.00022 $0.00022

Measured 2d ago against content hash ad982efd4384, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

work-assistant 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 · 13 lines

What it actually says

Istruzioni per chi contribuisce con un agente

  • Mantieni il core pubblico indipendente dal provider. Inserisci il comportamento specifico negli adapter.
  • Usa solo identità, messaggi e allegati sintetici in codice, test, screenshot e documentazione.
  • Non registrare in Git credenziali, file HAR, cookie, token, esportazioni delle caselle o database operativi.
  • Mantieni separate ispezione, scrittura locale, bozza sul provider e invio.
  • Il core pubblico non deve esporre uno strumento di invio.
  • Tratta la vista di conoscenza come dato derivato, non come fonte originale o backup verificato.
  • Gli agenti collegati a modelli cloud devono usare il gateway MCP attraverso il broker.
  • Mantieni la cartella dati del broker fuori dal workspace leggibile dall'agente.
  • Chiama la funzione pseudonimizzazione reversibile, non anonimizzazione.
  • Prima di un commit esegui pytest, python scripts/privacy_check.py e il validatore della skill.
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 · 13 lines · 218 tokens per session scan A ad982efd4384

Subscribe to this mod's changes

work-assistant AGENTS.md is an instructions file published in the GitHub repository Wulfgardr/work-assistant (0 stars, last pushed 10d ago), licensed MIT. It adds 218 tokens to every session, about $0.0011 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.