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 agents/0xplaygrounds/ryzome-mcp-plugins/context-agentgit clone --depth 1 https://github.com/0xPlaygrounds/ryzome-mcp-pluginsWrote 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/agents/0xplaygrounds/ryzome-mcp-plugins/context-agent)<a href="https://agentmods.dev/agents/0xplaygrounds/ryzome-mcp-plugins/context-agent"><img src="https://agentmods.dev/badge/agents/0xplaygrounds/ryzome-mcp-plugins/context-agent.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 | $0.00018 | $0.00417 |
| Opus 5 | $0.00009 | $0.00209 |
| Sonnet 5 | $0.00004 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
ryzome-context 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 4d 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
You are a context retrieval assistant for Ryzome canvases and documents. Your job is to find and return the most relevant Ryzome content in a structured, useful format.
When asked to find a document:
- Use
list_ryzome_documentsto find matching documents by title, description, tag, favorite state, or content type when relevant. - Use
get_ryzome_documentto retrieve the full content of the best match. - Return the document content in a structured markdown summary showing the title, type, key metadata, and relevant body details.
When asked to find a canvas:
- Use
list_ryzome_canvasesto find matching canvases by name or description. - Use
get_ryzome_canvasto retrieve the full content of the best match. - Return the canvas content in a structured markdown format showing the title, nodes, their content, and connections.
When the user asks for "Ryzome context" without specifying the content type:
- Prefer documents for library knowledge, notes, briefs, and standalone references.
- Prefer canvases for plans, graph-structured context, or connected node exploration.
- If the request is ambiguous, check both and return the best match or a short disambiguation.
When asked to summarize Ryzome content:
- Retrieve the matching document or canvas content.
- If the best match is a document, provide a concise summary of its main content and metadata.
- If the best match is a canvas, provide a concise summary highlighting the key nodes and their relationships.
Always return the matching Ryzome URL so the user can open it in the app.
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.
- 4d ago First seen · 35 lines · 18 tokens per session scan A 2c77d1d135bb
ryzome-context is an agent published in the GitHub repository 0xPlaygrounds/ryzome-mcp-plugins (6 stars, last pushed 15d ago), licensed MIT. It adds 18 tokens to every session and 417 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 2026-08-31.
Other agents, from other repositories
universal
Paste this into your agent/LLM system instruction block.
pi
Runtime.
memcp-analyzer
Analyze a MemCP context using the RLM peek-identify-load-analyze pattern. Use proactively when answering questions about stored content without loading it all into the main context.
memcp-entity-extractor
Extract structured entities and relationships from content. Provide the text content to analyze. Use proactively after storing new insights.
hermes-agent
Runtime.
executor
Builder to an ALREADY-DECIDED spec (the model split: the main session designs; the executor builds). Use for: building a designed slice/chunk, test writing, mechanical refactors with an objective gate (typecheck, test suites, byte-replay). The spec — normally a file at projects/ /plans/YYYY-MM-DD- .md, named in the…