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-spec-drivengit 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-spec-driven)<a href="https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/matematic-spec-driven"><img src="https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/matematic-spec-driven/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-spec-driven"><img src="https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/matematic-spec-driven.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 | $0.00320 | $0.05730 |
| Opus 5 | $0.00160 | $0.02865 |
| Sonnet 5 | $0.00064 | $0.01146 |
| Haiku 4.5 | $0.00032 | $0.00573 |
Grade A, and why
matematic-spec-driven 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 11d 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 — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MateMatic Spec-Driven - dev pipeline dla naszych projektow
Spec-Driven Development dla wewnetrznych projektow MateMatic. NIE produkt sprzedazowy dla kancelarii (tym jest [[matematic-konstytucja-ai]]). Tutaj: my, dla siebie, do PATRON / KGLF / POAS / skilli / mikroproduktow / aplikacji / serialu.
Source pattern: github/spec-kit (MIT) v0.8.12 - 4-fazowa methodology Constitution -> Specify -> Plan -> Tasks z marker [P] i Constitution Check GATE. Cherry-pick wybranych elementow + adaptacja pod MateMatic project types.
Status: v0.1.0 - faza C adopcji spec-kit (po fazie B = sandbox install 2026-05-20). Walidacja w boju przy 1-2 projektach (rekomendacja: nowy konektor SAOS w PATRON albo Biblioteka EPUB v3).
Kiedy uzywac
✅ TAK:
- Nowy projekt MateMatic od zera (nowy mikroprodukt, aplikacja, agent)
- Duza ficzer w istniejacym projekcie (PATRON / KGLF / www-matematic)
- Skill ktory ma 4+ podkomendy i zaleznosci (np. matematic-video-pipeline)
- Odcinek serialu "Nie tylko dla orlow" wymagajacy formalnego rozbicia (6-9 scen, fan-out subagentow)
- Audyt istniejacego projektu - czy ma konstytucje? czy ficzer zgadza sie z konstytucja?
❌ NIE:
- Sprzedaz kancelarii (uzyj [[matematic-konstytucja-ai]])
- Krotki post LI / aktualnosc BW (uzyj [[edit-article]] albo [[linkedin-voice-wieslaw-mazur]])
- Pojedynczy bugfix / refactor w juz dzialajacym module
- MEMO Ej Aj (uzyj [[memo-production-pipeline]])
4 fazy + walidacja
Faza 1 - /mspec-konstytucja (Constitution)
Output: .matematic/konstytucja.md (jeden plik per projekt, SEMVER versioning).
Konstytucja projektu = niezmienne zasady, na ktore wszystkie downstream artefakty musza sie powolac. NIE myl z konstytucja AI dla kancelarii (tamta dotyczy ORGANIZACJI klienta, ta - PROJEKTU MateMatic).
Struktura:
# [Nazwa projektu] - Konstytucja
## Mission (1 zdanie)
[Po co ten projekt istnieje, w kontekscie MateMatic]
## Core Principles (3-7 articles)
### Article I - [Nazwa]
[Imperatyw MUST / MUST NOT / SHOULD]
### Article II - [Nazwa]
...
**Dwa gotowe wzorce artykulow** (zapozyczone z `tutti-os/tutti`, egzekwowalne
mechanicznie, nie tylko deklaratywnie - wklej i dostosuj gdy pasuje do projektu):
- **Limit rozmiaru pliku** - "Pliki z logika biznesowa MUST pozostac <= 800 linii;
przekroczenie wymaga rozbicia modulu, nie wyjatku w konstytucji." Prosta,
mechaniczna bariera przeciw monolitom - latwa do sprawdzenia w CI/pre-commit.
- **Drift ADR dla vendorowanych/forkowanych specyfikacji** - "Kazdy fork/vendoring
zewnetrznego protokolu, schematu lub API (np. ELI, wzorzec ADR z dograh, logika
scrapowania ISAP) MUST miec wlasny ADR dokumentujacy punkt pinowania + cykliczny
recheck upstream drift." Formalizuje problem ktory juz mielismy nieformalnie -
patrz [[feedback_kod_wyprzedza_dokumentacje_drift]] i
[[feedback_errata_propagacja_z_rodzica_adr]].
## Boundaries (granice)
- Co projekt **robi**
- Czego projekt **nie robi** (anty-zakres)
- Z czym wspolpracuje (zaleznosci na inne projekty MateMatic)
## Governance (kto decyduje)
- Owner: Wieslaw Mazur
- Reviewers: [marko-pl dla content, security-review dla kodu, etc.]
- Amendment process: [jak zmieniac konstytucje]
## Compliance Map (mapowanie na zewnetrzne wymogi)
- AI Act art. ... (jesli dotyczy)
- RODO art. ... (jesli dotyczy)
- AGPL / MIT / CC BY-SA (licencja projektu)
**Version:** 0.1.0 | **Ratified:** YYYY-MM-DD | **Last Amended:** YYYY-MM-DD
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.
- 11d ago First seen · 409 lines · 320 tokens per session scan A 470cb07a41f1
matematic-spec-driven is a skill published in the GitHub repository matematicsolutions/awesome-matematic-skills-pl (6 stars, last pushed 17d ago), licensed MIT. It adds 320 tokens to every session and 5,730 once invoked, about $0.0016 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
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
bernstein-plan
Create and manage multi-step execution plans in Bernstein. Plans decompose complex goals into stages with dependencies. Use when the user wants to plan a complex feature, break down a large task, or review an execution plan before agents start working.
bernstein-run
Run a verified multi-agent goal with Bernstein. Use when a task is too large for a single agent session: Bernstein decomposes the goal into tasks, spawns CLI coding agents in parallel git worktrees, verifies their output, and merges results. Also use to check run status, costs, and to verify a finished run against its…
bernstein-approve
Review and approve/reject pending tasks or plans in Bernstein. Use when the user asks about approvals, wants to review agent work, or needs to approve/reject a plan before execution begins.
bernstein-quality
Show quality metrics for Bernstein runs - success rates per model, lint/test pass rates, completion time distributions. Use when the user asks about quality, reliability, which model performs best, or pass rates.
manager
Planning - decompose goals, create tasks via task server.