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 irfad7/claude-power-skills --skill autodreamgit clone --depth 1 https://github.com/irfad7/claude-power-skillsWrote 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/irfad7/claude-power-skills/autodream)<a href="https://agentmods.dev/skills/irfad7/claude-power-skills/autodream"><img src="https://agentmods.dev/badge/skills/irfad7/claude-power-skills/autodream/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/irfad7/claude-power-skills/autodream"><img src="https://agentmods.dev/badge/skills/irfad7/claude-power-skills/autodream.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 | $0.00089 | $0.01112 |
| Opus 5 | $0.00044 | $0.00556 |
| Sonnet 5 | $0.00018 | $0.00222 |
| Haiku 4.5 | $0.00009 | $0.00111 |
Grade A, and why
autodream 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 11d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
autoDream — Cross-Session Memory Synthesis
You are a memory consolidation agent. Your job is to review, merge, prune, and crystallize knowledge stored across session memory files — the same way the brain consolidates memories during sleep.
When To Run
- End of every meaningful work session
- When the user explicitly requests memory cleanup
- When memory files feel bloated, contradictory, or stale
- When starting a session and noticing memory drift
The Dream Cycle
Execute these four phases in order:
Phase 1: Scan — Read All Memory Sources
Read every memory/context file in the project. Common locations:
kai/MEMORY.md— session summaries and accumulated knowledgekai/GRAVITY.md— current prioritieskai/PULSE.md— live state of systems/orgskai/SCARS.md— things that broke and lessons learnedkai/DEBTS.md— obligations and technical debtkai/RELATIONSHIPS.md— people and contextkai/INSTINCT.md— learned patterns and reflexeskai/LINEAGE.md— decision history.claude/projects/*/memory/or equivalent auto-memory directories- Any
MEMORY.md,CHANGELOG.md, or context files in the project
For each file, note:
- Last modified date
- Entry count / size
- Staleness (how old is the most recent entry?)
Phase 2: Detect — Find Issues
Scan for these specific problems:
Contradictions Two entries that say opposite things. Example:
- Entry A: "API uses REST endpoints"
- Entry B: "Migrated API to GraphQL last week" → Keep the newer one. Delete the older one.
Duplicates Same information recorded multiple times in different words. → Merge into one clear entry. Delete the others.
Stale Entries Information that's no longer true or relevant. → Delete or move to an archive section.
Vague Entries Notes that are too imprecise to be useful. Example:
- "Had issues with the deployment" → Either crystallize into a specific fact ("Railway deployment fails when NODE_ENV isn't set") or delete.
Resolved Items Scars that have been fixed, debts that have been paid, tasks that are done. → Remove from active lists. Optionally archive.
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.
- 11d ago First seen · 135 lines · 89 tokens per session scan A f632023cffa1
autodream is a skill published in the GitHub repository irfad7/claude-power-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 1,112 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
report
Writes the session final report to a file, then prints only the path and a one-line summary. Fires when the prompt contains "Report per memstack:report", and also when the prompt begins with a standing trigger configured through MEMSTACKREPORTONTASKPROMPTS or MEMSTACKREPORTTRIGGERS. Dormant otherwise.
token-optimization
Use when the user says 'token optimization', 'save tokens', 'context window', 'reduce tokens', 'token stack', or 'TokenStack', or asks about extending context window capacity. Covers TokenStack, the built-in compression proxy that shrinks Claude Code tool output before it reaches the Anthropic API. Do NOT use for…
compress
Use when the user says 'tokenstack', 'compression', 'token savings', 'proxy status', or asks about context window usage.
state
Use when the user says 'update state', 'project state', 'where was I', or at session start to load current context.
grimoire
Use when the user says 'update context', 'update claude', 'save library', or after significant project changes.
catchup
Restore context after /clear by summarizing recent work and project state.