gridgeist AGENTS.md

A set of instructions for Gridgeist, a project intended to turn product ideas into a structured visual system.

In plain words
What is it for?
Following the project's required development lifecycle, maintaining its state file, and keeping work focused on the smallest relevant workflow.
Why use it?
It tells agents which workflow to use, when to resume saved project state, and which files and delegation practices are forbidden.

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/ohmiler/gridgeist/agents-md
Clone the repo
git clone --depth 1 https://github.com/ohmiler/gridgeist

Made for: Codex, OpenCode.

Per session 141 This file is loaded in full into every session.
When invoked 141 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 $0.00141 $0.00141
Opus 5 $0.00071 $0.00071
Sonnet 5 $0.00028 $0.00028
Haiku 4.5 $0.00014 $0.00014

Measured 2d ago against content hash 6eae41c4a48c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gridgeist 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 · 9 lines

What it actually says

Project instructions

  • Do not use any superpowers:* skills in this repository.
  • Do not create or restore files under docs/superpowers/.
  • Use the solodeveling skill at the start of every task in this repository. Resume .solodeveling/state.md when present and let the skill route the work to the smallest relevant lifecycle workflow.
  • Keep one primary agent. Do not use subagents unless the user explicitly requests delegation.
  • If solodeveling is unavailable, state that briefly and continue with the same evidence-driven lifecycle rather than blocking routine work.
  • Work directly from the user's request and use only the minimum additional relevant skills.
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 · 9 lines · 141 tokens per session scan A 6eae41c4a48c

Subscribe to this mod's changes

gridgeist AGENTS.md is an instructions file published in the GitHub repository ohmiler/gridgeist (114 stars, last pushed 1mo ago), licensed MIT. It adds 141 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 2026-08-30.