agentmods.dev

workspace-md AGENTS.md

workspace-md AGENTS.md is an instructions file for Codex, OpenCode from slowdoctor-dev/workspace-md. It costs 639 tokens per session, scanned B, original, Apache-2.0.

Repository instructions for the workspace.md specification, including which files agents should read and how different runtimes enter and report status.

In plain words
What is it for?
Use it as the repository’s AGENTS.md guidance when working on or adopting the workspace.md specification.
Why use it?
It gives agents a fixed starting point and reading order so they can understand the workspace before making changes.

Instructions file for CodexOpenCode

not rated 1 3mo ago B scan 639 tokens original Apache-2.0
View the source file slowdoctor-dev/workspace-md
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/slowdoctor-dev/workspace-md/agents-md
Clone the repo
git clone --depth 1 https://github.com/slowdoctor-dev/workspace-md

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 workspace-md AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/slowdoctor-dev/workspace-md/agents-md.svg)](https://agentmods.dev/instructions/slowdoctor-dev/workspace-md/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/slowdoctor-dev/workspace-md/agents-md"><img src="https://agentmods.dev/badge/instructions/slowdoctor-dev/workspace-md/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 639 This file is loaded in full into every session.
When invoked 639 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.00639 $0.00639
Opus 5 $0.00319 $0.00319
Sonnet 5 $0.00128 $0.00128
Haiku 4.5 $0.00064 $0.00064

Measured 3d ago against content hash e1fb2e963df5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

workspace-md AGENTS.md scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`~/.gemini/settings.json`.
AGENTS.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This repo defines the workspace.md specification — a sibling to agents.md describing workspace topology for human-agent collaboration.

Adopter note: the line above describes this spec repo. When you adopt workspace.md, re-home this intro to describe your workspace (keep the §Reading order + §Per-runtime entry sections). If you already have an AGENTS.md, see 2-mind/forge/act/skill/init/SKILL.md §Existing AGENTS.md handoff and 3-control/foundation/adoption.md.

Reading order (load at session-start, in sequence)

Convenience summary of the canonical 7-item list in 3-control/foundation/use-driven-memory.md §Read order at session-start — same 7 items, in order (keep in sync). Skills cite the canonical, so this works even if an adopter's AGENTS.md omits this section.

  1. AGENTS.md (this file) — workspace entry + per-runtime mapping
  2. WORKSPACE.md — topology spec
  3. 3-control/foundation/PRINCIPLE.md — operating principles
  4. 3-control/foundation/SOUL.md — canonical identity (Owner-ratified)
  5. 2-mind/garden/essential/USER.md — semantic person-model
  6. 2-mind/garden/essential/NEXT.md — working buffer (consume + clear)
  7. 2-mind/garden/essential/journal/<most-recent>.md — recent-session continuity

2-mind/garden/essential/SOUL.md (working identity observations) is NOT loaded at session-start. Read only by the dream skill when proposing graduations to canonical 3-control/foundation/SOUL.md.

Per-runtime entry

This workspace adopts the AAIF universal entry pattern. Each runtime reads its own auto-discovered instruction file at the workspace root, all pointing at this AGENTS.md:

  • Codex CLI — reads AGENTS.md directly (native AAIF support).
  • Claude Code — reads CLAUDE.md → symlinked to AGENTS.md.
  • Gemini CLI — reads GEMINI.md → symlinked to AGENTS.md, or configure context.fileName: ["AGENTS.md", "GEMINI.md"] in ~/.gemini/settings.json.
  • Antigravity CLI (agy, Gemini CLI's successor) — auto-loads AGENTS.md + GEMINI.md unchanged; native skills under .agents/skills → 2-mind/forge/act/skill/. Full adapter + transition details: 3-control/runtime/antigravity-cli.md.

Read the full file on GitHub · 52 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 · 52 lines · 639 tokens per session scan B e1fb2e963df5

Subscribe to this mod's changes

workspace-md AGENTS.md is an instructions file published in the GitHub repository slowdoctor-dev/workspace-md (1 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 639 tokens to every session, about $0.0032 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

agent-memoryagentic-aiagents-mdai-agentsclaude-codecodex-cli
Related

Other instructions, from other repositories

m_flow AGENTS.md

AGENTS.md instructions for FlowElement-xinliuyuansu/m_flow, covering m-flow — developer & agent reference, 1. repository map, extension points, 2. local development and python backend (requires python 3.10 – 3.13).

FlowElement-xinliuyuansu/m_flow · 1,075 tokens

mda CLAUDE.md

Instructions for sno-ai/mda, covering claude.md — sno-ai/mda, release process for @markdown-ai/cli, to cut a release (any 1.1.x, 1.2.0, 2.0.0 — same flow), release notes — non-negotiable and what's new.

sno-ai/mda · 1,248 tokens

Meterless AGENTS.md

Instructions for Meterless/Meterless, covering agent instructions for meterless, routing table, isolation rule, repo-wide rules and non-coding agents.

Meterless/Meterless · 456 tokens

switchback-running CLAUDE.md

Instructions for rlacombe/switchback-running, covering ultrarunning training companion, constitution, athlete data, training philosophy and core principles.

rlacombe/switchback-running · 5,020 tokens

open-bridge AGENTS.md

Instructions for bks-lab/open-bridge, covering the bridge — agent instructions, required reading, session start detection (automatic), theme and agents.

bks-lab/open-bridge · 8,154 tokens

Agent-Context CLAUDE.md

Instructions for lx-wnk/Agent-Context, covering claude.md, project overview, commands, format all files and check formatting (ci-style).

lx-wnk/Agent-Context · 1,206 tokens