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/ai-swiss/base/explorer-une-questionnpx skills add ai-swiss/base --skill explorer-une-questiongit clone --depth 1 https://github.com/ai-swiss/baseWrote 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/ai-swiss/base/explorer-une-question)<a href="https://agentmods.dev/skills/ai-swiss/base/explorer-une-question"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/explorer-une-question.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 5.1 | $0.00040 | $0.01073 |
| Opus 5 | $0.00020 | $0.00536 |
| Sonnet 5 | $0.00008 | $0.00215 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
explorer-une-question 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 6d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explorer une question
Aider la personne à approfondir une question ouverte ou à mettre de l'ordre dans ses notes, en gardant toujours visible la différence entre ce qui est établi, ce qui relève de son opinion, et ce que tu supposes. Le but est qu'elle pense mieux, non que tu penses à sa place.
Lis skills/competences/validation-aux-bons-moments/SKILL.md. Si la personne a des notes, demande où elles se trouvent et lis-les avant de synthétiser.
Inputs
- La question ou le sujet à explorer (texte libre)
- Les notes existantes, si la personne en a (un dossier, un fichier)
Étapes
1. Cadrer la question
«Reformulons la question pour être sûr de partir du bon endroit: [reformulation]. C'est bien cela que vous voulez explorer?»
← Validation du cadre
2. Partir de ce qui existe
Si la personne a des notes, lis-les et restitue ce qu'elles contiennent, sans rien ajouter à ce stade:
«Voici ce que je lis dans vos notes, fidèlement: [synthèse]. Ai-je bien restitué ce que vous aviez écrit?»
Distingue clairement les trois registres, et garde-les distincts dans tout ce qui suit:
- ce que vos notes disent (cité, attribué);
- ce qui est votre opinion déjà formée;
- ce que je suppose ou propose (marqué
[HYPOTHESE: ...]).
← Validation de la restitution
3. Ouvrir des angles
Propose des angles que la personne n'a peut-être pas vus, en les présentant comme des questions plutôt que comme des vérités:
«Voici quelques angles pour ouvrir la réflexion:
- [angle 1, sous forme de question]
- [angle 2]
Tout ce qui n'est pas dans vos notes est une proposition de ma part, à prendre ou à laisser. Lesquels vous parlent?»
Ce que tu avances et qui n'est ni dans les notes ni vérifiable se marque [INCERTITUDE: ...]. Tu ne présentes jamais une supposition comme un fait.
← Réaction de la personne
4. Synthétiser, en gardant les registres séparés
Propose une synthèse structurée qui conserve la distinction établie / opinion / hypothèse:
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.
- 6d ago First seen · 99 lines · 40 tokens per session scan A 1c2c292d73b2
explorer-une-question is a skill published in the GitHub repository ai-swiss/base (43 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,073 once invoked, about $0.0002 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
deck-presenter-mode
【模板: Presenter Mode Deck】 【意图】怕忘词的演讲者专用 deck, 含逐字稿 notes 与 popup teleprompter。 【布局】.
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
Release Notes Generator
Generate professional software release notes from a commit log: classify changes, write user-facing summaries, draft a publishable announcement, and assess release readiness. Use for release, changelog, version, and deploy requests.
summarize
Summarize conversations, logs, docs, or investigation notes into action-oriented text with evidence tags. Use for recap, handoff, CI failure digest, or MEMORY. Triggers: 总结, 汇总, summarize, 交接, 复盘, 调试总结.
markdown-documents
Use when creating or editing Markdown documents, notes, reports, briefs, drafts, or other editable writing where Markdown should be the primary artifact format.
session-artifact-indexing
Use this skill when a session creates or references several documents, trackers, plans, templates, source links, or skills that the user may need later.