What is adopter-ce-dossier?

A document-review process for examining an unconfigured folder and preparing an evaluation form for its owner. BASE is the tooling's structured setup for documents, agents, and processes.

Use it to inspect an existing document collection, identify its current processes and materials, and propose what BASE could do with it.

It lets someone assess what the folder contains without writing files or creating configuration before the owner agrees.

How ai-swiss/base configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ai-swiss/base. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ai-swiss/base/main/.ai/agents/concierge-base/skills/processes/adopter-ce-dossier/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/ai-swiss/base

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ai-swiss/base/adopter-ce-dossier/github.svg)](https://agentmods.dev/skills/ai-swiss/base/adopter-ce-dossier)

Your own site

<a href="https://agentmods.dev/skills/ai-swiss/base/adopter-ce-dossier"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/adopter-ce-dossier/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ai-swiss/base/adopter-ce-dossier"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/adopter-ce-dossier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,405 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00095	$0.04405
Opus 5.5	$0.00038	$0.01762
Sonnet 5.5	$0.00019	$0.00881
Haiku 4.5	$0.00010	$0.00441

Measured 14d ago against content hash 2cbf1941d5f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

adopter-ce-dossier 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 14d 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.

.ai/agents/concierge-base/skills/processes/adopter-ce-dossier/SKILL.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Partir de ce que vous avez

Une personne montre ce qu'elle a et veut savoir ce qu'un assistant ferait pour elle. Ce process regarde, juge, puis propose: il construit une fiche de proposition que la personne lit, remplit et renvoie. Il ne crée ni agent, ni process, ni configuration. C'est l'export de la fiche qui déclenche la suite, et c'est un autre process qui l'exécute.

La personne ne connaît peut-être rien à l'IA. La fiche parle de son travail, avec ses mots.

Étapes

Avant l'étape 1, pose les sept étapes dans la liste de tâches de l'outil; sans elle, annonce-les une fois, avec les mots de la personne, puis coche-les au fil (compétence journal, Progression). Avant l'export, seule la fiche s'écrit, pas même le journal.

1. Reconnaître le point de départ

Avant de lire, dis d'où la personne part. Lance node <cadre BASE>/tools/base.mjs init --root <dossier> sans --yes (ou base init, si la commande courte est installée): la commande dit de quelle sorte de dossier il s'agit (workspace, BASE, collection, dossier de documents, dossier vide) et n'écrit rien. Puis regarde les noms de fichiers et les premiers titres. Quatre points de départ, qui se combinent souvent:

Point de départ	Ce qui le signale	Ce qui suivra la fiche
Des besoins décrits	un transcript, un compte rendu, des notes d'entretien, un e-mail: des personnes qui parlent de leur travail, des irritants, des chiffres	`creer-agent`, avec le plan tiré de l'export
Des documents de travail non pensés pour l'IA	procédures, modes d'emploi, modèles de courrier, barèmes, annuaires, un wiki exporté	`importer-l-existant`, avec la carte d'import tirée de l'export
Une structure déjà pensée pour l'IA	`CLAUDE.md`, `AGENTS.md`, `.cursor/rules/`, des prompts système, les instructions d'un GPT; ou un BASE (`base.config.json`, `.ai/agents/`)	`ameliorer-agent` si c'est un BASE; sinon `importer-l-existant`, la structure servant de source
Rien	un dossier vide, ou une phrase sans document	`diagnostic`, qui fait parler, puis revient ici avec ses notes

Read the full file on GitHub · 289 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.

14d ago Changed · +7 lines 2cbf1941d5f6
1mo ago Changed · +164 lines · +42 tokens per session e3037e13aabe
1mo ago First seen · 118 lines · 53 tokens per session scan A e1f34a73c4ed

Subscribe to this mod's changes

adopter-ce-dossier is a skill published in the GitHub repository ai-swiss/base (65 stars, last pushed 8d ago), licensed Apache-2.0. It adds 95 tokens to every session and 4,405 once invoked, about $0.0004 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 2026-09-19.

CLAUDE.md Documents Planning besoins compte-rendu discussion dossier entretien procedures proposer règles structure transcript

adopter-ce-dossier next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
adopter-ce-dossierai-swiss/base	Skill	65	8d ago	Apache-2.0	A	95	Claude Code
youtube-fetcherJimmySadek/youtube-fetcher-to-markdown	Skill	485	2mo ago	MIT	A	74	Codex
conversation-content-pipelineorganvm-iv-taxis/a-i--skills	Skill	17	2mo ago	Apache-2.0	A	53	Claude Code
layout-analyzerclaude-office-skills/skills	Skill	563	9mo ago	MIT	A	5	Claude Code, Codex
transcript-to-epubforsvn-labs/transcript-to-epub	Skill	2	2mo ago	MIT	A	56	Claude Code
report-generatorhuifer/drug-discovery-skills	Skill	22	10mo ago	none	A	61	Claude Code
orbit-notionnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	117	Claude Code, Codex

base: Skill for Claude Code