Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/wrg32786/aigent-osnpx agentmods add skills/wrg32786/aigent-os/dreamWrote 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/wrg32786/aigent-os/dream)<a href="https://agentmods.dev/skills/wrg32786/aigent-os/dream"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/dream.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.01190 |
| Opus 5 | $0.00013 | $0.00595 |
| Sonnet 5 | $0.00005 | $0.00238 |
| Haiku 4.5 | $0.00003 | $0.00119 |
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 6d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dream - evidence-gated synthesis
/dream is the canonical writer for lessons and Dream synthesis. It never
applies an improvement, promotes its own proposal, edits system instructions,
or treats an agent-authored claim as verification.
Canonical ownership
- Lessons:
vault/memory/runtime/LESSONS.jsonl. - Dream synthesis:
vault/memory/DREAM_LOG.md. - The documented
memory/fallback is valid only for minimal installations. - Any older
runtime/DREAM_LOG.mdcopy is not an input or output. /closeand/nightlyinvoke this protocol instead of carrying a competing inline writer.- Candidate status transitions also go through this writer.
Invocation
/dream
/dream --window nightly
/dream --set-status <candidate-id> <approved|merged|rejected|blocked> \
--operator-evidence "<direct operator reference>"
proposed -> approved always requires the operator's exact decision. Never
infer approval from silence, an automated status, another agent, or prior prose.
Sources
Read, in order:
- The newest five valid capsules by frontmatter
created_at. - The newest five dated live Session Log blocks.
- Open Trust Decay captures.
- The newest three dated Honesty Ledger sessions.
- Recent Failed Experiments and Failure Modes entries.
- Existing Lessons JSONL for dedupe and prior evidence chains.
- Staged
NIGHTLY_CAPTURE_CANDIDATES.jsonlrows from the prior fire as discovery and pressure signals only. - Explicitly supplied local Git or command evidence.
Record exact source references. A capsule or Session Log entry can establish that a claim occurred; it cannot prove the claim true.
Lesson admission predicate
Append a lesson only when one is true:
- the same pattern appears in at least two independent source events;
- one explicit operator directive is paired with a separately observed outcome; or
- one mechanical red-before/green-after predicate supplies an artifact and literal exit codes.
Two retellings of one event are not independent. Discard one-off observations, unverified causal stories, and self-confirmation.
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.
- 6d ago First seen · 154 lines · 25 tokens per session scan A 14d1592dcd8b
dream is a skill published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 1,190 once invoked, about $0.0001 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 2026-09-01.
Other skills, from other repositories
hive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
memory-flush
Promote important recent log entries into MEMORY.md and prune stale ones.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
continuum-memory
Configure and use Continuum's two-tier memory system — mem0+Qdrant/Milvus for long-term facts, Redis for short-term sessions, with multi-tenant scopes (USER / AGENT / SHARED / RUN / CONVERSATION). Invoke when the user asks about "remember", "user preferences", "long-term memory", "vector search over memories"…
carryover
Use when recalling, saving or curating carryover memory, wikis, playbooks or the Obsidian vault.