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 skills add slowdoctor-dev/workspace-md --skill dreamgit clone --depth 1 https://github.com/slowdoctor-dev/workspace-mdWrote 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/skills/slowdoctor-dev/workspace-md/dream)<a href="https://agentmods.dev/skills/slowdoctor-dev/workspace-md/dream"><img src="https://agentmods.dev/badge/skills/slowdoctor-dev/workspace-md/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.
<a href="https://agentmods.dev/skills/slowdoctor-dev/workspace-md/dream"><img src="https://agentmods.dev/badge/skills/slowdoctor-dev/workspace-md/dream.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00108 | $0.02248 |
| Opus 5.5 | $0.00043 | $0.00899 |
| Sonnet 5.5 | $0.00022 | $0.00450 |
| Haiku 4.5 | $0.00011 | $0.00225 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dream
When to use
Three modes:
- Chained: after
session-endof a substantive session (default). - Mid-session: on Hermes-style triggers — ≥5 tool calls in a non-trivial workflow, error recovery, Owner correction, novel workflow.
- Explicit: Owner invokes
/dreamdirectly.
Operational instance of R1 (consolidation under capacity) + R4 (dual-store graduation). Named for the sleep-consolidation metaphor that R1/R2 are grounded in (McGaugh hippocampus→cortex replay; Anthropic Auto Dream); session-end → dream → session-start completes a sleep cycle (lay down memory → consolidate during quiescence → wake to refined context).
Requires
Requires 3-control/foundation/SOUL.md,
3-control/foundation/PRINCIPLE.md, and 2-mind/garden/essential/
to exist. If any are missing, run init instead of continuing.
Quick reference
| Signal type | Target | Tier |
|---|---|---|
| Owner preference / decision pattern | garden/essential/USER.md |
T1 autonomous |
| Owner-stance / identity-shift signal | garden/essential/SOUL.md (Observations / Owner-signals sections) |
T1 autonomous |
| → graduation of identity to canonical | 3-control/foundation/SOUL.md |
T2 Owner-ratify |
| Synthesized domain observation | garden/<topic>.md (lazy create) |
T1 autonomous |
| Procedure ≥5 tool calls, reusable | new 2-mind/forge/act/skill/<name>/SKILL.md |
T1 autonomous (procedural memory) |
| Mechanical task ≥2 occurrences | new 2-mind/forge/act/script/<name> |
T1 autonomous |
| Cross-session pattern → spec-level principle | 3-control/foundation/PRINCIPLE.md |
T2 Owner-ratify |
| Hard constraint to enforce | 3-control/rule/<topic>.md |
T2 Owner-ratify |
T1 applies immediately (within R1 capacity bounds). T2 requires per-item Owner ratification — the 3-control/ governance boundary.
Procedure
1. Surgical signal gather
Read:
- Today's journal entry (written by
session-end) - Last 1–2 prior journal entries (cross-session pattern detection)
garden/essential/SOUL.mdObservations / Owner-signals
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 First seen · 192 lines · 108 tokens per session scan A c0dc8ab0b5da
dream is a skill published in the GitHub repository slowdoctor-dev/workspace-md (1 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 108 tokens to every session and 2,248 once invoked, about $0.0004 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.
Other skills, from other repositories
memclaw
The agent's persistent long-term memory — the only knowledge that survives across sessions, shared across the fleet under access control. Consult it at the start of a task to recall prior decisions, findings, and rules before acting, and write outcomes, decisions, and lessons as work completes. Use whenever a caura…
marm-init
Guided MARM MCP setup. Invoke after running marm-memory init on the CLI to configure MARM memory across your agent. Drives transport choice, runtime choice, MCP config writing, multi-agent linking, and server start. Works on Claude, Codex, Gemini, Qwen, Cursor, VS Code, and other MCP-capable agents.
company-brain
How an agent should operate as one mind inside a shared Company Brain built on Caura — recall before acting, obey fleet keystones, reuse and publish skills, and report outcomes so every task compounds across the whole organization. Use this whenever you work as part of a Caura-connected team or fleet and your work…
compass-integrity
Use when the user is about to rely on prior session memory for a non-trivial decision, or when something feels off about a recall hit — runs the Merkle chain check, drift summary, and daemon liveness in one pass and surfaces any tampering, drift bursts, or daemon-down state before the user acts on stale or corrupted…
lifecycle_report
Scan project memory for v1.7.1 lifecycle frontmatter · report tier distribution + promotion candidates (reinforcecount >= promoteafter) · NO LLM.
session_audit
Scan project memory · age distribution + ungrouped count (L1 build readiness) + per-namespace entity stats · NO LLM.