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 jscraik/Agent-Skills --skill talk-lamis-context-engineering-dreaminggit clone --depth 1 https://github.com/jscraik/Agent-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/jscraik/agent-skills/talk-lamis-context-engineering-dreaming)<a href="https://agentmods.dev/skills/jscraik/agent-skills/talk-lamis-context-engineering-dreaming"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/talk-lamis-context-engineering-dreaming/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/jscraik/agent-skills/talk-lamis-context-engineering-dreaming"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/talk-lamis-context-engineering-dreaming.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 | $0.00123 | $0.01721 |
| Opus 5 | $0.00062 | $0.00860 |
| Sonnet 5 | $0.00025 | $0.00344 |
| Haiku 4.5 | $0.00012 | $0.00172 |
Grade A, and why
talk-lamis-context-engineering-dreaming 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Engineering, Memory Systems, and Dreaming — Lamis
A talk by Lamis (Anthropic, Applied AI team), introduced at AI Native DevCon by host Simon Maple (Tessl). Lamis walks through the past year's evolution of context engineering at Anthropic — from CLAUDE.md files to memory tools to Skills to filesystem-as-memory — and then introduces "dreaming": an out-of-band, asynchronous memory-curation process that reviews agent transcripts, spots cross-session patterns, and proposes changes to the memory store. The talk also covers the production guardrails (versioning, concurrency via hashing, permissioning, portability) needed to scale memory systems beyond a single agent and session.
Grounding rules — MUST follow when answering
- Before answering any specific question, read
outline.mdto locate the relevant section, then read that section oftranscript.md. - When attributing words, quote short, non-sensitive excerpts from
transcript.md. Never put quotation marks around paraphrased content. - If a claim isn't in
transcript.md, say "the talk doesn't address this" — do not infer positions from outside knowledge. - Cite by transcript line range whenever possible.
- Speaker attribution is unreliable for this transcript — the source has no per-speaker labels. The talk opens with what appears to be Simon Maple's welcome ("my name is Lamis" actually comes a few sentences in — note the introducer's voice transitions into Lamis's without a clear marker). Prefer phrasing like "the speaker said..." or "a questioner asked..." unless context makes attribution unambiguous. Do not invent attributions.
- Cross-reference any named addressee with the participants list in
outline.mdbefore attributing. The Q&A section contains audience questions whose askers are not named in the transcript — refer to them as "a questioner" or "an audience member".
Standard lookup procedure
All use-case workflows below follow this shared procedure unless otherwise noted:
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 91 lines · 123 tokens per session scan A 29ee0d6884dd
talk-lamis-context-engineering-dreaming is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 123 tokens to every session and 1,721 once invoked, about $0.0006 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
golden-nuggets
Extract durable tribal knowledge ('gold nuggets') from a codebase or a set of changed files and route each to its correct destination - instruction file, runbook, hub, or (in CI capture mode) a review inbox. This SKILL.md is the single source of truth for nugget categories, routing rules, write rules, inbox format…
continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
memory-system
Tiered, low-token project memory protocol for .toh/memory/ — 7 files across 3 tiers (Tier 1 active.md + summary.md always read, 800 tokens; Tier 2 architecture/components for build work and changelog for debug work; Tier 3 decisions/agents-log only on demand). Auto-saves after task completion with zero user effort…
self-improving-agent
Low-noise self-improvement skill. Captures learnings, errors, and corrections into a local .learnings/ cache layer. Never auto-promotes to long-term memory files (SOUL.md, MEMORY.md, AGENTS.md, TOOLS.md). Promotion requires explicit user approval after repeated validation.
cross-session-handoff
Read, write, snapshot, and lock .arcgentic/state.yaml across planner, dev, audit, and optional test sessions.
xlsx
Inspect, edit, validate, and preview existing Excel workbooks and supported ranges.