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 thepaperscompany/niw-skills --skill niw-package-reviewgit clone --depth 1 https://github.com/thepaperscompany/niw-skillsWrote 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/thepaperscompany/niw-skills/niw-package-review)<a href="https://agentmods.dev/skills/thepaperscompany/niw-skills/niw-package-review"><img src="https://agentmods.dev/badge/skills/thepaperscompany/niw-skills/niw-package-review/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/thepaperscompany/niw-skills/niw-package-review"><img src="https://agentmods.dev/badge/skills/thepaperscompany/niw-skills/niw-package-review.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 | $0.00161 | $0.03763 |
| Opus 5.5 | $0.00064 | $0.01505 |
| Sonnet 5.5 | $0.00032 | $0.00753 |
| Haiku 4.5 | $0.00016 | $0.00376 |
Grade A, and why
niw-package-review 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 1mo 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
12 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.
- references/archetype-calibration.md 10 KB
- references/current-adjudication-bar.md 15 KB
- references/evidence-tiers.md 5.9 KB
- references/filing-date-doctrine.md 4.7 KB
- references/legal-framework.md 5.9 KB
- references/package-review-scope.md 2.6 KB
- references/policy-alerts.md 5.2 KB
- references/policy-manual-substance.md 18 KB
- references/verdict-rubric.md 10.0 KB
- scripts/check_manifest.py 5.9 KB runs code
- scripts/filing_date_guard.py 6.4 KB runs code
- scripts/verify_quotes.py 6.3 KB runs code
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.
- 1mo ago First seen · 253 lines · 161 tokens per session scan A dc2667d702a0
niw-package-review is a skill published in the GitHub repository thepaperscompany/niw-skills (13 stars, last pushed 1mo ago), with no licence file. It adds 161 tokens to every session and 3,763 once invoked, about $0.0006 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 2026-09-04.
Other skills, from other repositories
matematic-konstytucja-ai
Generuje "Konstytucje AI" dla kancelarii prawnej - dokument governance definiujacy zasady uzycia AI w organizacji, na bazie cherry-pick patternu github/spec-kit (constitution -> spec -> plan -> tasks). 6 sekcji - mission, principles (max 9 articles), boundaries, governance roles, audit, evolution. Output - dokument…
adversarial-legal-review-pl
Czerwony zespół dla pisma prawnego - bierze gotowy deliverable wysokiej stawki (opinia, memo DD, M&A, pismo procesowe, rekomendacja do zarządu) i prowadzi kontradyktoryjną debatę: builder buduje najmocniejszą wersję tezy, attacker ją atakuje kontrargumentami i kontr-orzecznictwem, synthesizer godzi, verifier robi…
citation-grounding-pl
Mechaniczny weryfikator cytatu dla tekstów prawnych po polsku z GRADIENTEM weryfikacji (ISTNIENIE / TREŚĆ / FRAGMENT) - sprawdza string-matchem, czy każdy cytat z orzeczenia, ustawy, umowy lub pisma faktycznie istnieje w dokumencie źródłowym, czy sygnatura jest realna i czy parafraza oddaje stanowisko sądu, zamiast…
eu-sparql-search
Use when you need EU legislation, publications or CJEU case law found by CELEX number, date, subject or document type, or a SPARQL query written for the Publications Office endpoint (https://publications.europa.eu/webapi/rdf/sparql) and the Cellar knowledge graph (CDM ontology): finding regulations, directives and…
redline-docx-pl
Redlining polskich umow i pism w .docx z natywnymi Word Track Changes - bez niszczenia formatowania OOXML. Czyta .docx do Markdown (CriticMarkup) dla LLM, aplikuje zmiany jako sledzone (w:ins/w:del) + komentarze, i robi sanitize przed wyslaniem (strip metadanych autora, last-modified-by, rsid, timestampy - RODO przy…
terminy-procesowe-pl
Metodyka obliczania terminów procesowych i materialnych w prawie polskim - klasyfikuje termin (ustawowy / sądowy / instrukcyjny, procesowy / materialny), wylicza go krok po kroku wg reguł KC (art. 110-116) z podstawą prawną i tagiem pewności przy KAŻDYM kroku, sprawdza dni wolne, flaguje pułapki (ogłoszenie vs…