dream-log

dream-log is a command for coding agents from proticom/gnosys. It costs 0 tokens per session (573 once invoked), scanned A, original, MIT.

A command for viewing recent Dream Mode runs from Gnosys's central audit log, which records what happened during each run.

In plain words
What is it for?
Use it to review recent runs, filter by date or failures, and get formatted results or JSON for scripts.
Why use it?
It helps you check whether runs succeeded, failed, or could not reach their provider without inspecting the database manually.

Command

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 commands/proticom/gnosys/dream-log
Clone the repo
git clone --depth 1 https://github.com/proticom/gnosys

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 dream-log

README.md
[![agentmods](https://agentmods.dev/badge/commands/proticom/gnosys/dream-log.svg)](https://agentmods.dev/commands/proticom/gnosys/dream-log)
Your own site
<a href="https://agentmods.dev/commands/proticom/gnosys/dream-log"><img src="https://agentmods.dev/badge/commands/proticom/gnosys/dream-log.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 573 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00573
Opus 5 $0.00000 $0.00287
Sonnet 5 $0.00000 $0.00115
Haiku 4.5 $0.00000 $0.00057

Measured 3d ago against content hash e2b69e5afd90, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dream-log 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 3d 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.

docs/commands/dream-log.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gnosys dream log

Show recent Dream Mode runs from the central audit log.

Usage

gnosys dream log
gnosys dream log --last 10
gnosys dream log --since 2026-05-01
gnosys dream log --failures-only
gnosys dream log --json

Options

Option Description
--last <N> Number of most recent runs to show (default: 20)
--since <YYYY-MM-DD> Only runs completed on or after this date
--failures-only Only runs with errors or unreachable provider
--json Output raw audit rows as JSON

Behavior

  1. Opens the central DB via GnosysDB.openCentral().
  2. Fetches recent dream runs with getRecentDreamRuns(limit, { failuresOnly, sinceIso }).
  3. Prints formatted output or JSON.

Parent --json hoisting

Commander v13 can hoist --json to the parent dream command when both define it. The CLI passes parentJson: !!this.parent?.opts().json so gnosys dream --json log also emits JSON.

Formatted output

Each run shows completion time, duration, status, counters, and provider/model when present.

Status classification:

  • provider unreachable — dream provider could not be reached
  • N error(s) — run completed with errors
  • did work — summaries, decays, or relationships were produced
  • no LLM work — run completed without LLM-side changes

Example:

3 dream run(s):

  2026-05-28T05:00:00Z (45.2s) did work
    decays=2 summaries=1 reviews=0 relations=3
    provider=ollama/llama3.2

JSON output

{
  "count": 1,
  "runs": [ ... ]
}

JSON is emitted even when there are zero runs.

Empty output

When no runs match (non-JSON mode):

No dream runs recorded.

Errors

Central DB unavailable:

Central DB not available.

Exits with code 1.

Validation

cd gnosys-public
npm run cli -- dream log --help
npx vitest run src/test/dream-log-command-handler.test.ts
  • gnosys dream / gnosys dream run — trigger a dream cycle.
  • gnosys audit — broader operation audit trail.

Read the full file on GitHub · 96 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.

  1. 3d ago First seen · 96 lines · 0 tokens per session scan A e2b69e5afd90

Subscribe to this mod's changes

dream-log is a command published in the GitHub repository proticom/gnosys (4 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 573 tokens. 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.