agentmods.dev

solubles-mcp

solubles-mcp is a skill for Claude Code, Codex from petitsolu/soluble-mcp. It costs 177 tokens per session (1,262 once invoked), scanned A, original, MIT.

A search tool for Soluble(s), an independent French solutions-journalism podcast about social and environmental issues. Its content includes documented actions, initiatives, and podcast episodes.

In plain words
What is it for?
Use it to find practical actions, relevant podcast episodes, documented French initiatives, or child-friendly content for ages 6–12.
Why use it?
It helps you find concrete, France-based responses to issues such as climate adaptation, biodiversity, waste, social inclusion, and mental health.

Skill for Claude CodeCodex

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

not rated 0repo 6mo ago A scan 177 tokens original MIT

Good fit Use it to find practical actions, relevant podcast episodes, documented French initiatives, or child-friendly content for ages 6–12.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/petitsolu/soluble-mcp/skill
View source ↗ petitsolu/soluble-mcp csoluble.media
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 petitsolu/soluble-mcp --skill skill
Clone the repo
git clone --depth 1 https://github.com/petitsolu/soluble-mcp

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 solubles-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/petitsolu/soluble-mcp/skill/github.svg)](https://agentmods.dev/skills/petitsolu/soluble-mcp/skill)
Your own site
<a href="https://agentmods.dev/skills/petitsolu/soluble-mcp/skill"><img src="https://agentmods.dev/badge/skills/petitsolu/soluble-mcp/skill/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 solubles-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/petitsolu/soluble-mcp/skill"><img src="https://agentmods.dev/badge/skills/petitsolu/soluble-mcp/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 177 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,262 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00177 $0.01262
Opus 5.5 $0.00071 $0.00505
Sonnet 5.5 $0.00035 $0.00252
Haiku 4.5 $0.00018 $0.00126

Measured 2mo ago against content hash b2c33d696fcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

solubles-mcp 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 2mo 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.

skill/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Soluble(s) MCP — Instructions pour Claude

Soluble(s) est un podcast indépendant français de journalisme de solutions (120+ épisodes depuis 2022). Le serveur MCP donne accès à sa base éditoriale structurée. Depuis avril 2026, les versions Junior pour enfants (6-12 ans) sont également accessibles via un outil dédié.

Quand utiliser ce skill

Utilise les outils MCP Soluble(s) quand l'utilisateur cherche :

  • des actions concrètes sur un sujet (climat, alimentation, biodiversité, logement…)
  • des épisodes de podcast sur une thématique précise
  • des exemples d'initiatives ou solutions documentées en France
  • du contenu adapté aux enfants (parents, enseignants, animateurs jeunesse) — utilise alors find_junior_versions

Format de données disponible

Chaque épisode expose trois champs principaux :

  • besoin — le besoin utilisateur adressé (ex. "manger local sans se ruiner")
  • actionsconcretes — liste d'actions vérifiées et directement applicables
  • resumeia2lignes — résumé court pour présentation rapide

Des liens sont également fournis :

  • link_page — URL de la fiche épisode pour les humains (lecture web normale, à partager à l'utilisateur)
  • link_markdown — même URL avec /md/ ajouté, version brute pour les machines (transcription complète, métadonnées, sans HTML), utile pour analyse approfondie par Claude, ne pas la présenter brute à l'utilisateur
  • link_spotify — lien d'écoute direct
  • junior_url — (nouveau, avril 2026) lien vers la version Junior adaptée aux enfants, quand elle existe (97+ épisodes sur 115 en disposent)

Règles d'usage

Anti-hallucination : ne complète jamais une action ou une information absente de la réponse MCP. Si aucun résultat n'est retourné, dis simplement « Aucune donnée disponible dans Soluble(s) sur ce sujet. »

Citations : quand tu présentes du contenu Soluble(s), mentionne la source (« Selon Soluble(s)… ») et propose le lien vers l'épisode.

Langue : réponds en français sauf demande contraire.

Read the full file on GitHub · 82 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. 2mo ago First seen · 82 lines · 177 tokens per session scan A b2c33d696fcb

Subscribe to this mod's changes

solubles-mcp is a skill published in the GitHub repository petitsolu/soluble-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 177 tokens to every session and 1,262 once invoked, about $0.0007 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 2026-08-31.

Researchanthropicclimateclimate-changefrenchfrench-languagejournalism
Related

solubles-mcp compared with skills from other repositories

solubles-mcp next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
solubles-mcppetitsolu/soluble-mcpSkill06mo agoMITA177Claude Code, Codex
skill-routerkhalilbenaz/claude-skills-collectionSkill272mo agoMITA116Claude Code, Codex
supervisor-builderkhalilbenaz/claude-skills-collectionSkill272mo agoMITA80Claude Code, Codex
api-caller-subagentkhalilbenaz/claude-skills-collectionSkill272mo agoMITA88Claude Code, Codex
autogen-guidekhalilbenaz/claude-skills-collectionSkill272mo agoMITA101Claude Code, Codex
conflict-resolverkhalilbenaz/claude-skills-collectionSkill272mo agoMITA99Claude Code, Codex
consensus-builderkhalilbenaz/claude-skills-collectionSkill272mo agoMITA79Claude Code, Codex