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 deliverable-fidelity-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/deliverable-fidelity-pl)<a href="https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/deliverable-fidelity-pl"><img src="https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/deliverable-fidelity-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/deliverable-fidelity-pl"><img src="https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/deliverable-fidelity-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 | $0.00242 | $0.02620 |
| Opus 5 | $0.00121 | $0.01310 |
| Sonnet 5 | $0.00048 | $0.00524 |
| Haiku 4.5 | $0.00024 | $0.00262 |
Grade A, and why
deliverable-fidelity-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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deliverable Fidelity PL - weryfikator wiernosci dokumentu
Filozofia
Najgrozniejszy blad to nie zly cytat, tylko prawdziwe ustalenie, ktore wypadlo z podsumowania. Analiza znalazla klauzule RED, opinia ma 12 stron, ale w podsumowaniu dla zarzadu tej klauzuli nie ma - bo model "streszczajac" ja pominal. Cytaty sie zgadzaja, teza wytrzymuje atak, a mimo to deliverable klamie przez przemilczenie. Ten skill sprawdza wiernosc: czy to, co wyszlo, oddaje to, co znaleziono.
To trzecia, odrebna os weryfikacji:
citation-grounding-pl- czy cytaty istnieja w zrodle (prawdziwosc).adversarial-legal-review-pl- czy teza wytrzymuje atak (odpornosc).deliverable-fidelity-pl- czy deliverable oddaje analize (wiernosc).
Kiedy odpalac
Gdy finalny dokument streszcza dluzsza analize - opinia z podsumowaniem dla zarzadu, memo DD z tabela ryzyk, raport z sekcja wnioskow. Tam, gdzie skracanie moze zgubic ustalenie. Nie trzeba dla krotkiego pisma bez warstwy "analiza -> streszczenie".
Wejscie
- Ustalenia analizy (findings) - lista z severity i opcjonalnym rozstrzygnieciem:
{ "findings": [ { "id": "F1", "severity": "RED", "tekst": "klauzula limitacji odpowiedzialnosci sprzeczna z art. 473 par. 2 KC", "rozstrzygniecie": "rekomendacja usuniecia" }, { "id": "F2", "severity": "YELLOW", "tekst": "termin platnosci 60 dni - ryzyko zatorow", "rozstrzygniecie": "" } ], "deliverable": "<pelny tekst finalnego dokumentu>" } - Deliverable - finalny tekst do sprawdzenia.
Workflow
- Check mechaniczny (skrypt, za darmo) - uruchom:
Skrypt wyciaga kluczowe terminy z kazdego ustalenia, normalizuje (lowercase, biale znaki, cudzyslowy, myslniki) i stosuje konserwatywny stem (utniecie 2 koncowych znakow przy slowach >=7, by zlapac fleksjenode scripts/fidelity-check.mjs <plik-zadania.json>- "klauzuli" pasuje do "klauzula"), po czym sprawdza, czy wystarczajaco terminow pojawia sie w deliverable.
Per ustalenie:
reprezentowanelubpominiete. Pominiete RED -> blokada (exit 1). Rozstrzygniecia tez sprawdzane.
- "klauzuli" pasuje do "klauzula"), po czym sprawdza, czy wystarczajaco terminow pojawia sie w deliverable.
Per ustalenie:
- Kontrola wyrywkowa LLM (osad) - dla ustalen RED (skrypt podaje liste
najciezsze_do_spotcheck_llm, maks. 3) sprawdz nie tylko obecnosc slow, ale czy sens jest oddany (RED moze byc wspomniany, ale zbagatelizowany - "drobna uwaga" zamiast "klauzula niewazna"). To robi model, nie skrypt - mechaniczny match nie wykryje przeklamania tonu. Gdy brak ustalen RED, ta kontrola odpada (skrypt nie eskaluje YELLOW). - Werdykt - liczony deterministycznie wg funkcji ponizej, nie "na oko".
What ships with it
2 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 · 160 lines · 242 tokens per session scan A 2991c76aa08c
deliverable-fidelity-pl is a skill published in the GitHub repository matematicsolutions/awesome-matematic-skills-pl (6 stars, last pushed 19d ago), licensed MIT. It adds 242 tokens to every session and 2,620 once invoked, about $0.0012 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
e-signature
Use when wiring an e-signature flow with DocuSign or Dropbox Sign — picking the SES/AES/QES legal tier, sending a PDF or template for signature, embedded signing, verifying signing webhooks, retrieving the signed PDF plus audit trail. NOT drafting contract text (that is contracts), NOT extracting fields from PDFs…
runtime-admissibility-review
Determines whether a specific AI-agent action, output, recommendation, or proposed commitment remains admissible for execution or institutional reliance under current authority, delegated scope, evidence, facts, policy, risk, escalation, and revocation conditions. Use this Skill before an enterprise or regulated AI…
agent-authority-charter-builder-arkadiy-miteiko
Creates an Agent Authority Charter for enterprise or regulated AI agents before deployment. Use this Skill when a user needs to define what an AI agent is allowed to do, who delegated authority to it, what actions are permitted or prohibited, when human approval is required, what evidence must be preserved, and how…
metago-compliance
A pre-task checklist for checking legal, ethical, and security concerns before acting. It covers privacy, copyright, permissions, sensitive data, system safety, and regional compliance requirements.
metago-thought-19-negentropy-engine
A framework for assessing whether a system has a positive or negative effect on social order, information clarity, trust, fairness, and innovation. It uses changes in these areas to discuss social responsibility and ethical risk.
metago-security-engineer
Security Engineer - specializes in security audit, penetration testing, vulnerability management, compliance checking, security design review, supply chain security, and incident response.