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/rossoctl/examples/wiki-discovery-mcpnpx skills add rossoctl/examples --skill wiki-discovery-mcpgit clone --depth 1 https://github.com/rossoctl/examplesWrote 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/rossoctl/examples/wiki-discovery-mcp)<a href="https://agentmods.dev/skills/rossoctl/examples/wiki-discovery-mcp"><img src="https://agentmods.dev/badge/skills/rossoctl/examples/wiki-discovery-mcp.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 | $0.00000 | $0.00597 |
| Opus 5 | $0.00000 | $0.00298 |
| Sonnet 5 | $0.00000 | $0.00119 |
| Haiku 4.5 | $0.00000 | $0.00060 |
Grade A, and why
wiki-discovery-mcp 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kwiki Discovery Agent (MCP)
Write new knowledge to the wiki memory service after checking for novelty.
Prerequisites
The wiki-memory MCP server must be registered and running (stdio or streamable-http on port 8322).
Procedure
1. Get a Template (optional)
Call wiki_get_template to get a structured starting point:
- No args: list available templates
template_id: get specific template (paper-summary, concept-overview, how-to-guide, comparison)
2. Check Novelty First
Call wiki_check_novelty with:
topic_id: target topic (e.g. "ai")title: title of the new contentabstract: brief summary or first paragraph
If "novel": false, do NOT write.
3. Write the Page
Call wiki_write with:
topic_id: target topicpath: filename (e.g. "transformers.md")content: full markdown content (use frontmatter with tags)message: commit message (optional)draft: set totrueto submit for review instead of publishing
Returns suggested links to related pages.
4. Submit as Draft (optional)
Call wiki_write with draft=True to submit for review:
wiki_write(topic_id="ai", path="draft.md", content="...", draft=True)
→ "Draft: ai/draft.md"
5. Approve/Reject Drafts (admin)
wiki_list_drafts(topic_id)— list pending draftswiki_approve_draft(topic_id, path)— approve and publish
Example Flow
wiki_get_template(template_id="paper-summary") → template markdown
wiki_check_novelty(topic_id="ai", title="LoRA", abstract="Low-rank adaptation...")
→ {"novel": true}
wiki_write(topic_id="ai", path="lora.md", content="---\ntags: [paper, fine-tuning]\n---\n# LoRA\n\n...")
→ "Written: ai/lora.md\nSuggested links:\n- ai/fine-tuning.md (score=0.08)"
Content Guidelines
- Use YAML frontmatter with tags:
---\ntags: [paper, topic]\n--- - Include a top-level
# Titleheading - Use
## Sectionsfor organization - Link to related pages with
[[page-name]]or[text](page.md) - Keep pages focused on one concept
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 · 76 lines · 0 tokens per session scan A f56c1638e5e9
wiki-discovery-mcp is a skill published in the GitHub repository rossoctl/examples (11 stars, last pushed 6d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 597 tokens. 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 2026-08-30.
Other skills, from other repositories
context-okf-llm-ingest
Use when extracting a codebase's implementation decisions into Metatron with an LLM/agent instead of metatron ingest — authoring candidate decisions as Open Knowledge Format (OKF) markdown files locally for review.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory for MiniMax Code. Recall durable context, store important facts and decisions, and link related memories with the mnemon CLI.
agent-team-design
Use when designing a new multi-agent team, visible agents folder, role boundaries, handoff flow, PM Soul, Memory Curator, Policy Gate, or evaluation role. Use for agent-team repo creation even when the user only says they want a meta-agent or agent operating system.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…