opendream AGENTS.md

opendream AGENTS.md is an instructions file for Codex, OpenCode from pylit-ai/opendream. It costs 446 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for OpenDream covering release safety, folder-specific guidance, and the steps for activating and recording its project context.

In plain words
What is it for?
Use them before substantial work to run the project's preparation hook, follow guidance in relevant subfolders, and record how selected context was used before finishing.
Why use it?
They help agents use the project's shared context while keeping private machine details, secrets, and generated local state out of committed files.

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/pylit-ai/opendream/agents-md
Clone the repo
git clone --depth 1 https://github.com/pylit-ai/opendream

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 opendream AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pylit-ai/opendream/agents-md.svg)](https://agentmods.dev/instructions/pylit-ai/opendream/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/pylit-ai/opendream/agents-md"><img src="https://agentmods.dev/badge/instructions/pylit-ai/opendream/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 446 This file is loaded in full into every session.
When invoked 446 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 $0.00446 $0.00446
Opus 5 $0.00223 $0.00223
Sonnet 5 $0.00089 $0.00089
Haiku 4.5 $0.00045 $0.00045

Measured 4d ago against content hash e9091d15271d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opendream 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 4d 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 · 41 lines

What it actually says

AGENTS.md

Contributor guidance for OpenDream.

Release Hygiene

  • Keep this file and path-scoped AGENTS files release-safe.
  • Do not add local machine paths, secrets, provider/account details, internal URLs, or generated local tool state here.
  • Tool-specific generated surfaces belong in ignored local directories.

Path-Scoped Guidance

  • opendream/AGENTS.md
  • .meta/spec-adapters/AGENTS.md
  • tests/AGENTS.md

OpenDream Activation

This checked-in block is the Codex adapter form of the generic OpenDream activation flow. Other agents use equivalent generated surfaces or direct CLI calls.

Before substantial work from the workspace root, set OPENDREAM_QUERY to the actual task text, then run if the hook exists: [ -f .opendream/hooks/codex-pre-task.sh ] && sh .opendream/hooks/codex-pre-task.sh "${OPENDREAM_QUERY:-}" || true

If selected_memory_ids is non-empty, record how context was used with opendream record-context-use or include a terse final line such as OpenDream context used: <ids> / OpenDream context ignored: <reason>.

Before the final response from the workspace root, run if the hook exists: [ -f .opendream/hooks/codex-post-task.sh ] && sh .opendream/hooks/codex-post-task.sh "${OPENDREAM_SUMMARY:-Task completed.}" || true

opendream doctor --workspace "$PWD" --surface agents checks managed files only. opendream verify activation-capture --workspace "$PWD" --targets codex proves diagnostic memory capture. If hooks are absent, continue and repair with opendream activate --workspace "$PWD" --repair, then run capture verification.

For scripted Codex entrypoints, prefer: sh .opendream/bin/codex-task-wrapper.sh --summary "${OPENDREAM_SUMMARY:-Task completed.}" -- <agent command>

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. 4d ago First seen · 41 lines · 446 tokens per session scan A e9091d15271d

Subscribe to this mod's changes

opendream AGENTS.md is an instructions file published in the GitHub repository pylit-ai/opendream (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 446 tokens to every session, about $0.0022 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.