agentic-productivity AGENTS.md

A set of instructions for agents working with Agentic Productivity, a system that stores task lists, workplace knowledge, journals, and project notes in version-controlled Markdown files.

In plain words
What is it for?
Use it when an agent needs to work with AGENTS.md, TASKS.md, memory files, people records, project notes, or company context.
Why use it?
It tells an agent where the project’s working memory and other information live, helping it follow the repository’s organization.

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/jsattler/agentic-productivity/agents-md
Clone the repo
git clone --depth 1 https://github.com/jsattler/agentic-productivity

Made for: Codex, OpenCode.

Per session 781 This file is loaded in full into every session.
When invoked 781 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 $0.00781 $0.00781
Opus 5 $0.00391 $0.00391
Sonnet 5 $0.00156 $0.00156
Haiku 4.5 $0.00078 $0.00078

Measured 3d ago against content hash 9478ad6c8220, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentic-productivity 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 3d 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 · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

High-level instructions for AI agents working with the Agentic Productivity system.

Project Overview

Agentic Productivity is a productivity system designed for agentic workflows. It combines task management, workplace memory, and daily journaling in plain markdown files stored in git for versioning and syncing.

Key files:

  • AGENTS.md: Working memory (hot cache) - you are here
  • TASKS.md: Task tracking with status sections

Key directories:

  • memory/: Long-term knowledge base
    • glossary.md: Complete decoder ring (acronyms, terms, nicknames, codenames)
    • notes/{YYYY-MM}.md: Daily journal entries (YYYY-MM.md format)
    • people/{name}.md: Individual profiles
    • projects/{name}.md: Project details
    • context/company.md: Teams, tools, processes
  • skills/: Agent skills following agentskills.io format

Working Memory

This file (AGENTS.md) serves as the working memory - a hot cache of frequently-used information. Keep this section updated with your most active context.

Me

[Your name and role here]

People

Who Role
[Nickname] [Full Name], [role]

→ Full list: memory/glossary.md, profiles: memory/people/

Terms

Term Meaning
[acronym] [expansion]

→ Full glossary: memory/glossary.md

Projects

Name What
[Codename] [description]

→ Details: memory/projects/

Preferences

  • [preferences discovered]

Core Workflows

Daily Notes

  • One file per month: notes/YYYY-MM.md
  • Free-form journaling style
  • No frontmatter required
  • Link to people using standard markdown: [Name](../memory/people/filename.md)
  • Use checkboxes for action items: - [ ] Task

People References

  • Create files in memory/people/ directory
  • Use frontmatter for metadata (name, email, tags, relationship, etc.)
  • Link from daily notes using relative paths
  • File naming: firstname-lastname.md (lowercase, hyphenated)
  • Add to memory/glossary.md for nickname/alias decoding

Read the full file on GitHub · 126 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. 3d ago First seen · 126 lines · 781 tokens per session scan A 9478ad6c8220

Subscribe to this mod's changes

agentic-productivity AGENTS.md is an instructions file published in the GitHub repository jsattler/agentic-productivity (5 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 781 tokens to every session, about $0.0039 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.