A nightly vault pass that rewrites one record at a time using that record’s activity, which is its audit history. It closes completed work and removes obvious duplicates without inventing information.

Use it to update records from daily activity, mark finished work closed, and clean up clear duplicates overnight.

It keeps records aligned with what actually happened while preserving their history and avoiding made-up facts.

How dgraziosi/foundation configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to dgraziosi/foundation. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dgraziosi/foundation/main/.agents/skills/dream/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/dgraziosi/foundation

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dgraziosi/foundation/dream/github.svg)](https://agentmods.dev/skills/dgraziosi/foundation/dream)

Your own site

<a href="https://agentmods.dev/skills/dgraziosi/foundation/dream"><img src="https://agentmods.dev/badge/skills/dgraziosi/foundation/dream/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dgraziosi/foundation/dream"><img src="https://agentmods.dev/badge/skills/dgraziosi/foundation/dream.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,244 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00043	$0.01244
Opus 5.5	$0.00017	$0.00498
Sonnet 5.5	$0.00009	$0.00249
Haiku 4.5	$0.00004	$0.00124

Measured 2mo ago against content hash 759258356373, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dream 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 2mo 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/skills/dream/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dream

You are running Dream. Dream is the nightly vault pass. The user can run this, or attach it to Vault Keeper.

Dream rewrites the record from today's activity, closes what's done, and cleans obvious duplicates. One record at a time. Invent nothing.

Cite .agents/skills/foundation-mcp/ for which vault call to use. Cite .agents/skills/handoff/ when a step finishes. Look up the live vault schema at call time (bootstrap, inspect_ontology, or the server tool list). Do not trust a dump in this file.

The user is the human who runs this vault on this machine. The vault MCP is on this machine (http://127.0.0.1:8787). Stay on localhost. Do not tell anyone to expose it.

A record is the node (the system of record). Activity is the audit log. History stays in activity. Do not call the graph “the Vault.”

Vault Keeper still does not invent life facts. A bot running Dream may rewrite a record from that record's own activity.

Schedule and voice

02:00, all 7 nights, user-local. Overnight on purpose. Run Dream before backup when both exist. If a morning brief also exists, that clock is 08:00 user-local. Put these clocks on the bot's Routines. Do not add a live instance cron in git.

Quiet when the pass finished and nothing needs the user. Ping the user when you stopped because the activity does not say what is true, or when a destructive call needs a key with destructive scope.

This pass rewrites records that moved. Vault health, nightly backup, the weekly graph report (.agents/skills/graph-hygiene/), and product updates have their own schedules. That weekly report stays a report. Do not turn this pass into that report.

What Dream is not

Not Letta sleep-time compute. Do not precompute the next query.
Not Mem0 chat extract. Do not ingest mail or chat.
Do not invent insight records.
Do not write dues into standing harness memory. Dues stay on the record.
Not a new vault call. Use get, list_activity, upsert, and search. Destructive calls (delete, unlink, undo, manage_type retire) need a key with destructive scope. delete, unlink, and node or edge undo also need if-match timestamps from get.
Not a Viewer pass.

Read the full file on GitHub · 59 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.

2mo ago Changed 759258356373
2mo ago First seen · 59 lines · 43 tokens per session scan A 01c8b220c17e

Subscribe to this mod's changes

dream is a skill published in the GitHub repository dgraziosi/foundation (1 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 1,244 once invoked, about $0.0002 per session on Opus 5.5. 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.

Memory and context

dream next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dreamdgraziosi/foundation	Skill	1	today	MIT	A	43	Claude Code, Codex
knowledge-ingestopenclaw/openclaw	Skill	394k	today	MIT	A	80	Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0	Skill	68k	2d ago	Apache-2.0	A	217	Claude Code, Codex
forgetasgeirtj/system_prompts_leaks	Skill	71k	2d ago	CC0-1.0	A	74	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	yesterday	MIT	A	184	Claude Code
ha-data-storesshiwenwen/hope-agent	Skill	1.9k	yesterday	MIT	A	115	Claude Code, Codex
memoryopensquilla/opensquilla	Skill	7.1k	6d ago	Apache-2.0	A	44	Claude Code, Codex

foundation: Skill for Claude Code