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 allcolor/PawFlow-Agents --skill legal-workflowsgit clone --depth 1 https://github.com/allcolor/PawFlow-AgentsWrote 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/allcolor/pawflow-agents/legal-workflows)<a href="https://agentmods.dev/skills/allcolor/pawflow-agents/legal-workflows"><img src="https://agentmods.dev/badge/skills/allcolor/pawflow-agents/legal-workflows/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/allcolor/pawflow-agents/legal-workflows"><img src="https://agentmods.dev/badge/skills/allcolor/pawflow-agents/legal-workflows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00057 | $0.00816 |
| Opus 5 | $0.00028 | $0.00408 |
| Sonnet 5 | $0.00011 | $0.00163 |
| Haiku 4.5 | $0.00006 | $0.00082 |
Grade A, and why
legal-workflows 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflows sur demande
Ces cinq workflows ne sont pas des flows CRON (contrairement à
deadline-watch/weekly-digest) : ils demandent un jugement au moment de
l'exécution, donc ils sont déclenchés explicitement par l'avocate ou un
agent, pas planifiés. Le garde-fou commun aux cinq : jamais d'envoi ni de
décision automatique, toujours une citation de source quand le workflow
touche du contenu juridique (skill legal-citations), toujours une
validation humaine avant toute action irréversible.
Nouveau dossier (intake)
- Déclenché manuellement ou vocalement ("nouveau dossier pour M./Mme X").
- Structurer les entités de base dans la base SQLite locale — table
dossiers(client, type_affaire, statut='actif', date_ouverture) — et dans la Knowledge Graph pour les relations qualitatives. - Vérification de conflit d'intérêt avant ouverture définitive :
rechercher si une partie du nouveau dossier apparaît déjà côté adverse
dans un autre dossier du cabinet (recherche transversale table
dossiers/Knowledge Graph). Présenter le résultat comme une alerte à vérifier par l'avocate — jamais un blocage automatique : la décision de conflit d'intérêt reste un jugement professionnel. - Si des dates de procédure sont identifiées dès l'intake, proposer la
création des entités "délai" correspondantes dans la table
delais(déclenchera le prochain passage du flowdeadline-watch) — toujours présentées à valider par l'avocate avant insertion, jamais actées automatiquement.
Relecture de brouillon (rôle collègue)
- Déclenché manuellement ("relire ce brouillon").
- Charger le brouillon et les pièces du dossier (dates, montants, noms)
depuis la table
pieces/le filestore de la conversation. - Retour structuré : liste numérotée d'incohérences détectées + suggestions d'angle, jamais une édition directe du fichier source.
Préparation d'audience
À J-2/J-1 d'une audience identifiée par une entrée de la table delais de
type "audience" : assembler un brief consultable (pièces du dossier,
chronologie reconstruite, dernières conclusions, points en délibéré) —
toujours comme support de préparation pour l'avocate, jamais comme document
à déposer.
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 · 68 lines · 57 tokens per session scan A dca37e792fac
legal-workflows is a skill published in the GitHub repository allcolor/PawFlow-Agents (25 stars, last pushed 3d ago), licensed MIT. It adds 57 tokens to every session and 816 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
performing-soc2-type2-audit-preparation
Automates SOC 2 Type II audit preparation including gap assessment against AICPA Trust Services Criteria (CC1-CC9), evidence collection from cloud providers and identity systems, control testing validation, remediation tracking, and continuous compliance monitoring. Covers all five TSC categories (Security…
privacy-by-design
Use when building apps that collect user data. Ensures privacy protections are built in from the start—data minimization, consent, encryption.
oo-boldsign
BoldSign (boldsign.com). Use this skill for ANY BoldSign request — reading, creating, and updating data. Whenever a task involves BoldSign, use this skill instead of calling the API directly.
implementing-gdpr-data-protection-controls
The General Data Protection Regulation (EU) 2016/679 (GDPR) is the EU's comprehensive data protection law governing the collection, processing, storage, and transfer of personal data. This skill cover.
advogado-criminal
Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.
advogado-especialista
Advogado especialista em todas as areas do Direito brasileiro: familia, criminal, trabalhista, tributario, consumidor, imobiliario, empresarial, civil e constitucional.