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 jxoesneon/Ciel --skill ciel-knowledge-and-memorygit clone --depth 1 https://github.com/jxoesneon/CielWrote 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/jxoesneon/ciel/ciel-knowledge-and-memory)<a href="https://agentmods.dev/skills/jxoesneon/ciel/ciel-knowledge-and-memory"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/ciel-knowledge-and-memory/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/jxoesneon/ciel/ciel-knowledge-and-memory"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/ciel-knowledge-and-memory.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 | $0.00026 | $0.00527 |
| Opus 5 | $0.00013 | $0.00264 |
| Sonnet 5 | $0.00005 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
ciel-knowledge-and-memory 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 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.
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.
What it actually says
CIEL ADAPTATION: Knowledge & Memory (The Intel Layer)
This skill manages the flow of information from live codebase structure to durable cross-session memory.
Knowledge Ingestion (Layers)
- Active (L1): GitHub/Linear for live roadmap and implementation truth.
- Short-term (L2): Project memory files (
~/.claude/projects/*/memory/) for user preferences. - Semantic (L3): MCP Memory Server for structured knowledge graphs and observations.
- Durable (L4): Dedicated knowledge base repo for curated research and synthesized docs.
Memory Search (Index -> Timeline -> Fetch)
- Mandate: NEVER fetch full details without filtering first.
- Protocol:
- Search: Get a table of IDs and Titles to minimize tokens.
- Timeline: Interleave sessions and observations around an anchor ID to find context.
- Fetch: Batch-get only the 2-3 most relevant full observations.
Structural Exploration (Smart Explore)
- Map First: Use
smart_searchorsmart_outline(AST-based) before performing a fullread_file. - Unfold: Review signatures and unfold ONLY the implementation of specific functions/methods needed.
- Token Efficiency: Target 4-8x token savings vs raw file reads.
Anti-Patterns
- The Context Dump: Reading 10+ full files when a structural map would suffice.
- Amnesiac Session: Starting work without checking MCP memory for previous decisions.
- Durable-Code Drift: Storing live application code in a knowledge base instead of the Git repo.
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 · 53 lines · 26 tokens per session scan A 3bb27c2f6ddc
ciel-knowledge-and-memory is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 26 tokens to every session and 527 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 2026-09-03.
Other skills, from other repositories
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.
mem0-integration
Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.
embeddings-setup
Bring Open Second Brain semantic search online — embedding API key, sqlite-vec extension, first reindex, optional periodic refresh. INVOKE when the user mentions "embeddings", "semantic search", "vector index", or after o2b search check reports vecextension: unavailable, embeddingkey: missing, or any line in its…
rag-evaluate-quality
Periodically measure the retrieval quality of the knowledge base using evaluateretrieval (MRR@5, Recall@5, Precision@5) plus getindexstats for health metrics. Run weekly, after significant reindex activity, or when the user reports declining answer quality. Prevents silent index rot and grounds "should we tune X"…
vault-semantic-search
Search vault notes by meaning using semantic search (RAG). Activate this skill when users want to find notes by concept or topic rather than exact keywords, or when keyword search tools return poor results.