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/fulminate-io/knowledge-mcp/ingest-patternsnpx skills add fulminate-io/knowledge-mcp --skill ingest-patternsgit clone --depth 1 https://github.com/fulminate-io/knowledge-mcpWrote 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/fulminate-io/knowledge-mcp/ingest-patterns)<a href="https://agentmods.dev/skills/fulminate-io/knowledge-mcp/ingest-patterns"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/ingest-patterns.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 5.1 | $0.00115 | $0.03574 |
| Opus 5 | $0.00057 | $0.01787 |
| Sonnet 5 | $0.00023 | $0.00715 |
| Haiku 4.5 | $0.00012 | $0.00357 |
Grade A, and why
ingest-patterns 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.
How it starts
The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ingest patterns: $ARGUMENTS
For universal orchestration discipline reference /orchestrate. This skill is pattern-ingestion-specific.
Four stages, in order:
- Collect — pull the source into a raw graph once. The raw graph is a cached structured document: every later stage replays it at zero network cost, so iterating costs nothing but your own time.
- Extract — ZERO LLM SPEND, and that is the whole point of this stage. Run inline recipe bodies against the raw graph and read the rows back; use the ranked text read to find which sections even mention what you are after. Nothing is written and nothing is summarized by a model.
- Freeze — when an extraction is worth re-running (a new edition, a second source of the same shape), SAVE the same body as a recipe. Freezing is a save, not a rewrite: an inline extract and a saved recipe are one mechanism with two ways to invoke it.
- Hydrate — the only stage that spends tokens. The
pattern-ingesteragent turns a CHOSEN SLICE of the extraction into full pattern nodes: original prose, applies-when and avoid-when use cases, working examples, primary references. Roughly 50k output tokens per pattern.
The shape of the cost is why the order matters. Collect and extract are cheap and repeatable, so do your deciding there; hydrate is expensive and therefore runs on what you decided, not on everything the source contains.
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 · 319 lines · 115 tokens per session scan A e446c5cdb335
ingest-patterns is a skill published in the GitHub repository fulminate-io/knowledge-mcp (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 115 tokens to every session and 3,574 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).
ark-documentation
Guidance for structuring Ark documentation using the Diataxis framework. Use this skill when creating new docs, deciding where content belongs, reviewing documentation PRs, or restructuring existing documentation.