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 agentmods add skills/sneg55/agent-starter/dreamnpx skills add sneg55/agent-starter --skill dreamgit clone --depth 1 https://github.com/sneg55/agent-starterWrote 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/sneg55/agent-starter/dream)<a href="https://agentmods.dev/skills/sneg55/agent-starter/dream"><img src="https://agentmods.dev/badge/skills/sneg55/agent-starter/dream.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.00779 |
| Opus 5 | $0.00014 | $0.00390 |
| Sonnet 5 | $0.00005 | $0.00156 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade B, and why
dream scanned grade B with 1 finding 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 5d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`grep -rn "<narrow term>" .claude/transcripts/ --include="*.jsonl" | tail -50` How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dream: Memory Consolidation
You are performing a dream - a reflective pass over your memory files. Synthesize what you've learned recently into durable, well-organized memories so that future sessions can orient quickly.
Phase 1 - Orient
lsthe memory directory to see what already exists- Read
MEMORY.mdto understand the current index - Skim existing topic files so you improve them rather than creating duplicates
- If
logs/orsessions/subdirectories exist, review recent entries there
Phase 2 - Gather recent signal
Look for new information worth persisting. Sources in rough priority order:
- Daily logs (
logs/YYYY/MM/YYYY-MM-DD.md) if present - these are the append-only stream - Existing memories that drifted - facts that contradict something you see in the codebase now
- Transcript search - if you need specific context, grep transcripts for narrow terms:
grep -rn "<narrow term>" .claude/transcripts/ --include="*.jsonl" | tail -50
Don't exhaustively read transcripts. Look only for things you already suspect matter.
Phase 3 - Consolidate
For each thing worth remembering, write or update a memory file. Use these type conventions:
| Type | What belongs | Examples |
|---|---|---|
| user | User's role, goals, preferences, knowledge | "senior Go dev, new to React" |
| feedback | Corrections AND confirmations from user | "don't mock DB in tests", "bundled PR was right call" |
| project | Ongoing work context, deadlines, initiatives | "merge freeze 2026-03-05 for mobile release" |
| reference | Pointers to external systems | "pipeline bugs in Linear project INGEST" |
Each memory file uses this format:
---
name: {{name}}
description: {{one-line description}}
type: {{user, feedback, project, reference}}
---
{{content - for feedback/project: rule, then **Why:** and **How to apply:**}}
Focus on:
- Merging new signal into existing topic files rather than creating near-duplicates
- Converting relative dates ("yesterday", "last week") to absolute dates
- Deleting contradicted facts - if today's investigation disproves an old memory, fix it at the source
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.
- 5d ago First seen · 85 lines · 27 tokens per session scan B 64ade648c74b
dream is a skill published in the GitHub repository sneg55/agent-starter (76 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 779 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
audit-context
Measures where a project's Claude context is going before applying any of clean-context's levers. Reports what Glob discovers with and without ignore files applied, the twenty largest files in the repo and which are generated, the cumulative size of every CLAUDE.md loaded for this working directory, and how many MCP…
project-memory
Use to create and maintain durable cross-session project memory and the progress ledger, so long autonomous builds resume cleanly after compaction, restarts, or new sessions. Read it when starting work and update it as decisions and tasks land.
whats-up
Fetch recent activity from Autographical — what the user and their AI agents have been working on. Use when starting a session, when the user mentions recent activity, when the user alludes to what they were doing or looking at, or picking up where they left off. Also use when the conversation feels like a topic…
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
assigns-audit
Inspect LiveView socket assigns for memory bloat — missing temporaryassigns, unused assigns, unbounded lists needing streams, memory estimates. Use when LiveView memory grows or you need to add temporaryassigns.
compound
Capture solved problems as searchable solution docs. Use after fixing bugs, when "that worked", or after successful /phx:review or /phx:investigate.