Paperasse is a collection of skills that help AI agents handle French business bureaucracy, including accounting, taxation, invoicing, auditing, notarial law, and condominium management. It is intended for users of agents such as Claude Code, Codex, Cursor, and similar tools, and includes connectors for Qonto transactions and Stripe payments.
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 romainsimon/paperasse --skill controleur-fiscalgit clone --depth 1 https://github.com/romainsimon/paperasseWrote 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/romainsimon/paperasse/controleur-fiscal)<a href="https://agentmods.dev/skills/romainsimon/paperasse/controleur-fiscal"><img src="https://agentmods.dev/badge/skills/romainsimon/paperasse/controleur-fiscal/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/romainsimon/paperasse/controleur-fiscal"><img src="https://agentmods.dev/badge/skills/romainsimon/paperasse/controleur-fiscal.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 | $0.00136 | $0.03847 |
| Opus 5.5 | $0.00054 | $0.01539 |
| Sonnet 5.5 | $0.00027 | $0.00769 |
| Haiku 4.5 | $0.00014 | $0.00385 |
Grade A, and why
controleur-fiscal 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.
How it starts
The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simulation de Contrôle Fiscal DGFIP
Ce skill simule un contrôle fiscal tel que mené par un vérificateur de la Direction Générale des Finances Publiques (DGFIP) sur une société soumise à l'IS.
Posture du vérificateur
Adopter la posture d'un inspecteur des finances publiques en vérification de comptabilité :
- Suspicion méthodique : chaque charge déduite doit être justifiée
- Littéralité : appliquer strictement les textes du CGI et du BOFiP
- Exhaustivité : examiner tous les postes, même de faible montant
- Proportionnalité : ajuster la profondeur au risque détecté
Étape préalable : Collecter le contexte (OBLIGATOIRE)
Ne jamais démarrer le contrôle sans les informations minimales. Si elles manquent, les demander à l'utilisateur avant toute autre action.
Si un fichier company.json existe, le lire pour obtenir le contexte automatiquement.
Informations requises :
- Identité de l'entreprise : raison sociale, SIREN, forme juridique, régime d'imposition (IS/IR), régime TVA, capital social, adresse
- Exercice contrôlé : date de début, date de fin, durée en jours
- Documents disponibles : FEC, bilan, compte de résultat, balance, liasse fiscale, grand livre, relevés bancaires, factures
Si une information critique manque (SIREN, forme juridique, régime fiscal), la demander explicitement. Ne pas faire de suppositions.
Programme de vérification
Exécuter les 8 axes de contrôle séquentiellement. Pour chaque anomalie, rédiger un chef de redressement au format standardisé.
Axe 1 : Examen du FEC (art. L. 47 A-I LPF)
Lire le fichier FEC.
Contrôles obligatoires :
- Conformité format (18 colonnes, séparateur
|) - Équilibre global : Total Débits = Total Crédits
- Équilibre par écriture : chaque EcritureNum est balancée
- Numérotation séquentielle continue (pas de trou)
- Dates dans la période de l'exercice
- Absence de montants négatifs
- PieceRef renseignée pour chaque écriture
- Cohérence CompteNum / racines PCG
What ships with it
9 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.
- 1mo ago First seen · 328 lines · 136 tokens per session scan A 840952a3fdad
controleur-fiscal is a skill published in the GitHub repository romainsimon/paperasse (2,559 stars, last pushed 2mo ago), licensed MIT. It adds 136 tokens to every session and 3,847 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
kyc-escalation
Write an internal KYC/AML escalation memo: a factual time-stamped trigger description, customer-profile vs activity mismatch analysis, red-flag taxonomy mapping, outstanding information, and a recommendation with rationale. Use when asked to escalate a KYC alert, document an AML concern, write up unusual-activity…
amlbot
AMLBot integration. Manage data, records, and automate workflows. Use when the user wants to interact with AMLBot data.
ma-playbook
M&A strategy for acquiring companies or being acquired. Due diligence, valuation, integration, and deal structure. Use when evaluating acquisitions, preparing for acquisition, M&A due diligence, integration planning, or deal negotiation.
itr-wala
File Indian income tax returns for FY 2025-26 (AY 2026-27), or plan FY 2026-27 (Tax Year 2026-27), including current-year advance-tax estimates. Use when the user wants to file their ITR, compute or verify Indian income tax, compare the old vs new tax regime, read a Form 16, AIS, TIS or Form 26AS, reconcile TDS…
ai-ethics-review
Conduct a structured ethical review of an AI or ML feature, model, or product. Use when preparing to deploy an AI system, assessing algorithmic risk, auditing a model for bias, or producing a responsible AI impact assessment. Produces a structured ethics review covering fairness, transparency, privacy, safety…
revenue-recognition
Determines when and how revenue is recognized — performance obligations, contract terms that change the answer, and the deal structures that create accounting problems. Use this to work out how a contract should be recognized, review a non-standard deal before it is signed, understand deferred revenue, or spot terms…