A testing skill for measuring whether a Memex “dream” consolidation pass improves retrieval from stored knowledge. It compares consolidation with no consolidation and can test repeated passes.

Use it to run a single evaluation, a no-consolidation control, repeated evaluations, or an evaluation that first collects the required test data.

It helps determine whether consolidation actually improves results or gradually damages the stored knowledge instead of assuming it helps.

dream-eval — Skill for Claude Code by robinslange/learning-loop

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.

Any agent

npx skills add robinslange/learning-loop --skill dream-eval

Clone the repo

git clone --depth 1 https://github.com/robinslange/learning-loop

Made for: Claude Code.

Or install learning-loop, the plugin that ships this one along with the rest of its 24 skills, 20 agents, 7 hooks.

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/robinslange/learning-loop/dream-eval/github.svg)](https://agentmods.dev/skills/robinslange/learning-loop/dream-eval)

Your own site

<a href="https://agentmods.dev/skills/robinslange/learning-loop/dream-eval"><img src="https://agentmods.dev/badge/skills/robinslange/learning-loop/dream-eval/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/robinslange/learning-loop/dream-eval"><img src="https://agentmods.dev/badge/skills/robinslange/learning-loop/dream-eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 606 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	$0.00081	$0.00606
Opus 5.5	$0.00032	$0.00242
Sonnet 5.5	$0.00016	$0.00121
Haiku 4.5	$0.00008	$0.00061

Measured 1mo ago against content hash 9a336d8cb241, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dream-eval 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 1mo 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.

plugin/skills/dream-eval/SKILL.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dream Eval: Measure a Consolidation Pass

Overview

wraps /dream without changing it, and answers three questions with a number: did this pass help, is /dream better than no consolidation at all, and does it degrade the corpus over repeated passes. report-only. control mode is the one that matters most: on a low-redundancy corpus the published prior says consolidation only ties raw retrieval, so proving it locally is the point.

Argument Parsing

Input	Mode	Passes	Mine first
`/learning-loop:dream-eval`	single	n/a	no
`/learning-loop:dream-eval --mode=control`	control	n/a	no
`/learning-loop:dream-eval --mode=repeated --passes=5`	repeated	5	no
`/learning-loop:dream-eval --mine`	(mode)		yes

Steps

acquire the dream lock first, before any mining or mode run, using Bash: ll-run marker.mjs lock-acquire dream. exit 0 means proceed. exit 1 means another /dream or dream-eval run is active (or a crashed one less than an hour old), so stop and tell the user. exit 2 means a usage or install error, report the stderr message and abort.
if probes.jsonl is absent and --mine was not passed, stop and say: "no probe corpus found. run with --mine first." (release the lock before stopping, see step 6).
if --mine, run the probe miner (forward + reverse) and persist to probes.jsonl.
run the chosen mode. the retrieval function is an in-session Task dispatch: given the question and the MEMORY.md index, pick up to 3 files to read. single mode snapshots the live dir first; control and repeated operate on clones only.
write the json + markdown report under dream-eval/reports/ and show the markdown summary inline.
release the dream lock when done, after the report is written, always, using Bash: ll-run marker.mjs lock-release dream.

Safety

shares the dream lock (acquired in step 1, released in step 6) so the harness and /dream never run at once.
single mode mutates the live memory dir (snapshot taken first); control and repeated never touch it.
archive over delete.

Read the full file on GitHub · 35 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.

1mo ago Changed 9a336d8cb241
2mo ago First seen · 35 lines · 81 tokens per session scan A e26ed852db88

Subscribe to this mod's changes

dream-eval is a skill published in the GitHub repository robinslange/learning-loop (13 stars, last pushed 4d ago), licensed Apache-2.0. It adds 81 tokens to every session and 606 once invoked, about $0.0003 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 2026-08-30.

Memory and context Testing

dream-eval next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dream-evalrobinslange/learning-loop	Skill	13	4d ago	Apache-2.0	A	81	Claude Code
knowledge-ingestopenclaw/openclaw	Skill	394k	yesterday	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
memoryopensquilla/opensquilla	Skill	7.1k	6d ago	Apache-2.0	A	44	Claude Code, Codex
ha-data-storesshiwenwen/hope-agent	Skill	1.9k	yesterday	MIT	A	115	Claude Code, Codex