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 matematicsolutions/awesome-matematic-skills-pl --skill matematic-mcp-fastmcp-instructions-plgit clone --depth 1 https://github.com/matematicsolutions/awesome-matematic-skills-plWrote 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/matematicsolutions/awesome-matematic-skills-pl/matematic-mcp-fastmcp-instructions-pl)<a href="https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/matematic-mcp-fastmcp-instructions-pl"><img src="https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/matematic-mcp-fastmcp-instructions-pl/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/matematicsolutions/awesome-matematic-skills-pl/matematic-mcp-fastmcp-instructions-pl"><img src="https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/matematic-mcp-fastmcp-instructions-pl.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 | $0.00335 | $0.07580 |
| Opus 5 | $0.00168 | $0.03790 |
| Sonnet 5 | $0.00067 | $0.01516 |
| Haiku 4.5 | $0.00034 | $0.00758 |
Grade A, and why
matematic-mcp-fastmcp-instructions-pl 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 12d 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 — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.
matematic-mcp-fastmcp-instructions-pl
Wzorzec kanoniczny dla MCP serverow MateMatic. Walidowany empirycznie na dograh-hq/dograh v1.31.0 (production system, 3-4 dni release cycle, 2.6k gwiazdek, drift testy w CI, BSD-2).
Kiedy uzywac
- Nowy MCP server MateMatic od pierwszego commita
- Retrofit istniejacych (saos-orzecznictwo, mcp-eu-compliance, matematic-anonimizacja-pl, mcp-pomoc-prawna-pl, sejm-eli-mcp, mcp-uodo, mcp-kio) - do konca Q3 2026
- Audit istniejacego MCP server (czy ma 8 elementow)
- Debug: LLM nie wywoluje tooli w odpowiedniej kolejnosci, klient MCP nie autoryzuje, error_codes ginace dla LLM
9 elementow kanonu
1. FastMCP(instructions=...) z procedural orchestration
Instrukcje wstrzykiwane do system promptu kazdego klienta MCP. LLM widzi je PRZED pierwszym tool call.
Tresc:
- Call order (ktora kolejnosc wywolywac tools)
- Error handling (jak iteorwac po failed tool call)
- Hard constraints (czego NIE robic)
- Field conventions (kanoniczne nazwy, format ID)
- Style (preferencje przy wyborze toolow gdy wiele rozwiazan)
Anti-content:
- NIE re-enumerowac tool signatures (drift - signatury sa w
tools/list) - NIE re-enumerowac error_codes (drift - error_codes w tool docstring)
- NIE per-field guidance (to lezy w
PropertySpec.llm_hint)
Wzor (Python):
from fastmcp import FastMCP
from .instructions import MY_MCP_INSTRUCTIONS
from .tools.foo import foo_tool
from .tools.bar import bar_tool
mcp = FastMCP("matematic-saos", instructions=MY_MCP_INSTRUCTIONS)
for _tool in (foo_tool, bar_tool):
mcp.tool(_tool)
2. Drift test (tests/test_mcp_instructions_drift.py)
Fail jesli:
- Instructions wymienia tool nie registered
- Tool ma error_code ktorego nie ma w docstring
Wzor w examples/test_instructions_drift.py.
3. Auth dwukanalowy X-API-Key LUB Bearer
FastMCP domyslnie stripuje Authorization header. MUSISZ explicit get_http_headers(include={"authorization"}).
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 499 lines · 335 tokens per session scan A b20eb443c42e
matematic-mcp-fastmcp-instructions-pl is a skill published in the GitHub repository matematicsolutions/awesome-matematic-skills-pl (6 stars, last pushed 19d ago), licensed MIT. It adds 335 tokens to every session and 7,580 once invoked, about $0.0017 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
backend
Python server code, APIs, async, strict typing.
architecture-paradigm-cqrs-es
Applies CQRS and Event Sourcing for read/write separation and audit trails. Use when designing systems with complex domain logic or full state-change history.
metago-architecture-design
A system-architecture design workflow that turns business requirements into a plan for components, interfaces, data flows, technology choices, and trade-offs.
metago-system-architect
System Architect - specializes in architecture design, database schema, API design, module decomposition, tech stack, and security architecture.
africa-mobile-money
Integrate M-Pesa, Orange Money, Wave, and MTN MoMo payment APIs with proper error handling, reconciliation, and multi-operator patterns.
africa-ussd-development
Build USSD applications for African markets — menu design, session management, multi-operator integration, and user experience patterns for feature phones.