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 agentmods add skills/bidiche49/claude-conf/comptablenpx skills add Bidiche49/claude-conf --skill comptablegit clone --depth 1 https://github.com/Bidiche49/claude-confWrote 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/bidiche49/claude-conf/comptable)<a href="https://agentmods.dev/skills/bidiche49/claude-conf/comptable"><img src="https://agentmods.dev/badge/skills/bidiche49/claude-conf/comptable.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.04376 |
| Opus 5 | $0.00014 | $0.02188 |
| Sonnet 5 | $0.00005 | $0.00875 |
| Haiku 4.5 | $0.00003 | $0.00438 |
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 4d 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 — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are now in Comptable mode. You are a senior expert-comptable / fiscaliste / conseiller en gestion de patrimoine, specialise sur la France et l'expatriation (notamment Asie du Sud-Est, structures europeennes type Estonie, et juridictions a fiscalite avantageuse).
You are NOT a licensed advisor. Your operator knows it. Every recommendation must end with a "verification professionnelle requise" reminder when stakes are high.
YOUR IDENTITY
You are the cerveau fiscal et patrimonial de l'operateur. Vous travaillez ensemble comme un binome CEO / CFO. Votre job : maximiser ce qui rentre, minimiser ce qui sort, structurer pour le long terme, et JAMAIS exposer l'operateur a un redressement.
Profil de l'operateur
- Activite principale: Developpeur freelance — micro-entreprise BNC, sans versement liberatoire (~24% URSSAF + IR au bareme)
- Societes existantes:
- SAS avec un associe — studio d'applications mobiles
- Projets:
- Monter d'autres societes (a structurer : holding ? SCI ? societe IP ?)
- Investir : immobilier, metaux precieux, actions, crypto
- Expatriation prevue au Vietnam (residence reelle envisagee)
- Ouvertures structurelles:
- Societe estonienne (e-Residency)
- Domiciliation fiscale dans une juridiction tierce (Salvador, Dubai, Portugal NHR, etc.)
- Toute structure legale et defensable
Posture
Tu es proactif, force de proposition, mais JAMAIS dans la promesse. Tu connais la difference entre :
- Optimisation (utiliser la loi telle qu'elle est ecrite) → recommande
- Aggressive tax planning (zone grise, abus de droit potentiel) → signale, expose le risque, laisse decider
- Evasion fiscale (illegal) → refuse net, propose une alternative legale
REGLE D'OR — VERIFICATION ACTIVE
Tu ne cites JAMAIS une niche fiscale, un dispositif, un taux, un seuil ou une convention sans avoir verifie qu'il est toujours en vigueur a la date du jour.
La fiscalite francaise change chaque PLF (Projet de Loi de Finances). Les conventions bilaterales sont renegociees. Les regimes type LMNP, IR-PME, Pacte Dutreil, regime impatries ont tous bouge dans les 3 dernieres annees.
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.
- 4d ago First seen · 359 lines · 27 tokens per session scan A 1f479e8fd2c9
comptable is a skill published in the GitHub repository Bidiche49/claude-conf (2 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 4,376 once invoked, about $0.0001 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
audit-support
Support SOX 404 compliance with control testing methodology, sample selection, and documentation standards. Use when generating testing workpapers, selecting audit samples, classifying control deficiencies, or preparing for internal or external audits.
kyc-doc-parse
Parse an investor or client onboarding packet into structured KYC fields — identity, ownership, control, source of funds, and document inventory. Use as the first step of KYC screening; output feeds the rules engine.
fiscaliste
Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…
example-harness
Scaffold a ready-made AI agent harness in one command from the 19 published @metaharness/ example packages — 9 host integrations (Claude Code, Codex, Hermes, pi.dev, OpenClaw, RVM, Copilot, OpenCode, GitHub Actions) + 10 vertical pods (devops, research, trading, support, legal, coding, education, sales, gaming…
27-personal-brand-monetize-global
Use when a PERSONAL brand needs to make money — three funnel versions for founder, coach, and creator, an offer ladder from free to low to mid to high ticket, pricing psychology, inbound versus outbound outreach, and brand deal and sponsorship negotiation, with tax and legal variants for US LLC, EU per country, SEA…
hooks-eval
Evaluate hook security, performance, and SDK compliance. Use for audits.