comptable

comptable is a skill for Claude Code, Codex from romainsimon/paperasse. It costs 143 tokens per session (4,659 once invoked), scanned A, original, MIT.

An AI assistant for French business accounting, tax, and invoicing. It covers bookkeeping, VAT, corporate or personal income tax, annual closing, tax forms, accounting files, and electronic invoicing.

In plain words
What is it for?
Use it for accounting entries, VAT and tax returns, annual accounts, French tax forms, audit files, invoices, credit notes, and electronic-invoicing requirements.
Why use it?
It brings recurring accounting and invoicing checks into a single workflow. It requires validated company information before giving advice or checking invoice compliance.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for accounting entries, VAT and tax returns, annual accounts, French tax forms, audit files, invoices, credit notes, and electronic-invoicing requirements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/romainsimon/paperasse/comptable
About the project

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.

romainsimon/paperasse · 2,546 stars · on GitHub · agentskill.sh

Install

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.

Any agent
npx skills add romainsimon/paperasse --skill comptable
Clone the repo
git clone --depth 1 https://github.com/romainsimon/paperasse

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for comptable

README.md
[![agentmods](https://agentmods.dev/badge/skills/romainsimon/paperasse/comptable/github.svg)](https://agentmods.dev/skills/romainsimon/paperasse/comptable)
Your own site
<a href="https://agentmods.dev/skills/romainsimon/paperasse/comptable"><img src="https://agentmods.dev/badge/skills/romainsimon/paperasse/comptable/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.

agentmods 80×15 button for comptable

Your own site · 80×15
<a href="https://agentmods.dev/skills/romainsimon/paperasse/comptable"><img src="https://agentmods.dev/badge/skills/romainsimon/paperasse/comptable.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 143 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,659 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00143 $0.04659
Opus 5.5 $0.00057 $0.01864
Sonnet 5.5 $0.00029 $0.00932
Haiku 4.5 $0.00014 $0.00466

Measured 1mo ago against content hash b2b6dcd71c03, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

comptable 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.

comptable/SKILL.md · 317 lines

How it starts

The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Expert-Comptable IA

Co-pilote comptable, fiscal et facturation pour entreprises françaises. Compliance-first.

Prérequis : company.json

À chaque début de conversation, vérifier si company.json existe à la racine du projet :

  • company.json existe → le lire, passer au workflow
  • Seul company.example.json existe ou rien → lancer le setup guidé décrit dans references/setup.md AVANT toute autre action

Ne jamais donner de conseil sans contexte validé.

Vérification des champs facturation

Pour toute demande liée à une facture ou à la conformité e-facturation, vérifier que company.json contient :

invoicing.prefix              → Format de numérotation (ex: "F")
invoicing.next_numbers        → Map { "2025": 42, "2026": 1 } — séquence par année (reset 1er janvier)
invoicing.avoir_prefix        → Préfixe des avoirs (ex: "AV")
einvoicing.pa                 → Plateforme agréée choisie
einvoicing.pa_name            → Nom de la PA
einvoicing.peppol_id          → Identifiant PEPPOL (format iso6523:siret, ex "0225:12345678900014")
einvoicing.reception_ready    → Prête à recevoir (sept. 2026)
einvoicing.emission_ready     → Prête à émettre
einvoicing.ereporting_ready   → Prête à e-reporter
payment.default_terms         → Délai de paiement par défaut
payment.methods               → Modes de paiement acceptés
payment.bank_details.iban     → IBAN pour virements
payment.bank_details.bic      → BIC
payment.late_penalty_rate     → Taux pénalités de retard ("3x_legal" ou taux fixe en %)
payment.late_penalty_label    → Libellé textuel affiché sur la facture
payment.escompte              → Taux d'escompte ("none" ou taux en %)
payment.escompte_label        → Libellé textuel
payment.recovery_fee          → Indemnité forfaitaire (40 EUR par défaut, fixé par la loi)

Si un de ces champs est absent, proposer le setup partiel : references/facturation/setup-facturation.md.

Ne jamais générer de facture sans contexte entreprise validé.

Read the full file on GitHub · 317 lines

Changes

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.

  1. 1mo ago First seen · 317 lines · 143 tokens per session scan A b2b6dcd71c03

Subscribe to this mod's changes

comptable is a skill published in the GitHub repository romainsimon/paperasse (2,546 stars, last pushed 2mo ago), licensed MIT. It adds 143 tokens to every session and 4,659 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 2026-08-30.

Related

Other skills, from other repositories

capital-allocation

Allocate a finite budget or headcount across competing initiatives by return and strategic fit. Use when asked to allocate budget, decide where to invest, build a funding/portfolio plan, or make trade-offs across initiatives under a cap. Produces a capital-allocation plan — initiatives scored by expected return ×…

mohitagw15856/pm-claude-skills · 86 tokens

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…

mohitagw15856/pm-claude-skills · 93 tokens

agent-era-pricing

Redesign seat-based pricing for the agent era — when one human runs ten agents, per-seat models collapse. Use when agents are eroding seat counts, when asked to migrate to usage- or outcome-based pricing, to price an agent/API tier, or to defend revenue as customers automate their own usage. Produces a pricing…

mohitagw15856/pm-claude-skills · 108 tokens

ai-roi-audit

Audit whether the organisation's AI spend actually paid — measured against baselines, not vendor math or vibes. Use when a CFO asks what the AI tools returned, when renewing AI contracts, when consolidating overlapping AI subscriptions, or to build the measurement plan before the next spend. Produces an ROI audit with…

mohitagw15856/pm-claude-skills · 118 tokens

credit-memo

Write a credit memo for a lending decision: borrower story, facility structure, repayment sources, financial-ratio spread with covenant headroom, risk factors with mitigants, risk-rating rationale, and a recommendation. Use when asked to write a credit memo, credit application, credit paper, loan write-up, or prepare…

mohitagw15856/pm-claude-skills · 83 tokens

lending-risk-brief

Write a portfolio-level lending risk brief: concentration analysis by sector, geography and single name, vintage performance, migration matrix narrative, macro-sensitivity scenarios, top watch names, and actions. Use when asked to write a portfolio risk report, credit risk committee brief, loan book review, or…

mohitagw15856/pm-claude-skills · 91 tokens