Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skillsnpx agentmods add skills/cosmicstack-labs/mercury-agent-skills/knowledge-baseWrote 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/cosmicstack-labs/mercury-agent-skills/knowledge-base)<a href="https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/knowledge-base"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/knowledge-base/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/cosmicstack-labs/mercury-agent-skills/knowledge-base"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/knowledge-base.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 85 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00019 | $0.05872 |
| Opus 5.5 | $0.00008 | $0.02349 |
| Sonnet 5.5 | $0.00004 | $0.01174 |
| Haiku 4.5 | $0.00002 | $0.00587 |
Grade A, and why
knowledge-base 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 2mo 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 — 806 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Base Creation
Build searchable, maintainable knowledge bases that your team actually uses — turning tribal knowledge into organizational assets.
Core Principles
1. Knowledge Bases Are Products, Not Projects
A knowledge base is never "done." It requires ongoing investment: content creation, curation, cleanup, and promotion. Treat it like a product with a roadmap, owners, and metrics.
2. Search Is the Primary Interface
If users can't find what they need in 2-3 searches, the knowledge base has failed. Invest in search quality, metadata, tagging, and cross-referencing before adding more content.
3. Lower the Barrier to Contribution
The easier it is to write and publish, the more content you'll get. Support markdown, provide templates, reduce review friction for minor edits, and celebrate contributors.
4. Structure for Discoverability, Write for Scannability
Organize content in categories users naturally think in. Use clear titles, descriptive summaries, consistent formatting, and plenty of internal links.
5. Measure What Matters
Track search success rates, popular content, stale pages, and user feedback. Use data to decide what to improve, archive, or create next.
Knowledge Base Maturity Model
| Level | Content | Search | Maintenance | Contribution | Governance |
|---|---|---|---|---|---|
| 1: Graveyard | Random docs, no structure | None (browse only) | Never updated | No process | No owners |
| 2: Collection | Some structure, inconsistent | Basic text search | Updated reactively | A few contributors | Unclear ownership |
| 3: Organized | Taxonomy defined, templates used | Tagged + full-text search | Regular reviews | Active contributors | Defined content owners |
| 4: Curated | Reviewed content, versioned | Faceted + filtered search | Scheduled audits | Contributor workflows | Editorial board |
| 5: Living | Feedback-driven, analytics-informed | Semantic + AI-assisted | Continuous improvement | Embedded in workflows | Metrics-driven governance |
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.
- 2mo ago First seen · 806 lines · 19 tokens per session scan A 29a2f29a6a8f
knowledge-base is a skill published in the GitHub repository cosmicstack-labs/mercury-agent-skills (487 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 5,872 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
officecli-academic-paper
Use this skill to build academic-style .docx output: journal / conference / thesis chapters carrying formal citation style (APA, Chicago, IEEE, MLA), numbered equations, figure & table cross-references, footnotes/endnotes, bibliography, or multi-column journal layout. Trigger on: 'research paper', 'journal paper'…
officecli
Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.
A set of instructions for working with PDF files, which are documents designed to preserve their layout across devices.
read
Fetches URLs and PDFs, then summarizes or returns clean Markdown; can also search the web through DeepSeek when built-in search is thin. Use when asked to read, fetch, quote, cite, convert, or save a URL or PDF. Not for local text files already in the repo.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
huashu-md-to-pdf
A document converter that turns Markdown files into professionally formatted PDF white papers with an Apple-style design.