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.
npx agentmods add instructions/pylit-ai/opendream/agents-mdgit clone --depth 1 https://github.com/pylit-ai/opendreamWrote 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.
[](https://agentmods.dev/instructions/pylit-ai/opendream/agents-md)<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00446 | $0.00446 |
| Opus 5 | $0.00223 | $0.00223 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
opendream AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
AGENTS.md
Contributor guidance for OpenDream.
Release Hygiene
- Keep this file and path-scoped AGENTS files release-safe.
- Do not add local machine paths, secrets, provider/account details, internal URLs, or generated local tool state here.
- Tool-specific generated surfaces belong in ignored local directories.
Path-Scoped Guidance
opendream/AGENTS.md.meta/spec-adapters/AGENTS.mdtests/AGENTS.md
OpenDream Activation
This checked-in block is the Codex adapter form of the generic OpenDream activation flow. Other agents use equivalent generated surfaces or direct CLI calls.
Before substantial work from the workspace root, set OPENDREAM_QUERY to the actual task text, then run if the hook exists:
[ -f .opendream/hooks/codex-pre-task.sh ] && sh .opendream/hooks/codex-pre-task.sh "${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>
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.
- 4d ago First seen · 41 lines · 446 tokens per session scan A e9091d15271d
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.
Other instructions, from other repositories
personal-model AGENTS.md
Instructions for Intuition-Lab/personal-model, covering agents.md, runtime boundary, commands, pipeline and documentation map.
plur CLAUDE.md
Claude Code instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
personal-model CLAUDE.md
Instructions for Intuition-Lab/personal-model: Read and follow AGENTS.md. It is the single agent orientation for this repository: Runtime boundary, commands, architecture, invariants, current documentation, privacy rules, and DCO workflow.
engraphis AGENTS.md
AGENTS.md instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, internal subagent delegation, 0. read this first — two architectures live in one package, 1. commands and ── unified dashboard + memory inspector ──.
paxm AGENTS.md
Instructions for pax-beehive/paxm, covering paxm 开发要求, git 与协作, 架构边界, 代码与验证 and 文档与发布.
brigade AGENTS.md
Instructions for escoffier-labs/brigade, covering agents.md, definition of done, rules, orientation and memory handoff.