What is tri-boite-mail?

An email-triage workflow that sorts messages in a connected Gmail account using labels and CRM context. It prepares contextual reply drafts, while sending remains a human action.

It helps search and inspect email threads, label them by type, match senders with CRM records, and draft replies using customer history and open quotations.

It reduces inbox clutter without deleting messages and makes messages needing a response easier to handle. It also helps distinguish clients, prospects, administration, and low-value email.

tri-boite-mail — Skill for Claude Code by PrendsTaPart

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add PrendsTaPart/Plugin-Claude-MCP-BraindCode-

Claude Code

/plugin install rapido-direction

Made for: Claude Code.

Or install rapido-direction, the plugin that ships this one along with the rest of its 5 skills, 1 agent.

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/prendstapart/plugin-claude-mcp-braindcode-/tri-boite-mail/github.svg)](https://agentmods.dev/skills/prendstapart/plugin-claude-mcp-braindcode-/tri-boite-mail)

Your own site

<a href="https://agentmods.dev/skills/prendstapart/plugin-claude-mcp-braindcode-/tri-boite-mail"><img src="https://agentmods.dev/badge/skills/prendstapart/plugin-claude-mcp-braindcode-/tri-boite-mail/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/prendstapart/plugin-claude-mcp-braindcode-/tri-boite-mail"><img src="https://agentmods.dev/badge/skills/prendstapart/plugin-claude-mcp-braindcode-/tri-boite-mail.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 627 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	$0.00059	$0.00627
Opus 5	$0.00030	$0.00313
Sonnet 5	$0.00012	$0.00125
Haiku 4.5	$0.00006	$0.00063

Measured 5d ago against content hash b4c7650dff88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tri-boite-mail 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 5d 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.

rapido-direction/skills/tri-boite-mail/SKILL.md · 47 lines

What it actually says

Tri de boîte mail

Étape 0 — Références (obligatoire)

Charger ${CLAUDE_PLUGIN_ROOT}/reference/regles-direction.md. Outils Gmail absents → expliquer + renvoyer vers README-installation.md.

Workflow

Collecter — search_threads (périmètre convenu : non lus, ou une requête ciblée type from:… / is:important) ; get_thread pour le contenu des fils à traiter.
Classer chaque fil — croiser avec le CRM (search_entreprises / list_contacts sur l'expéditeur) :
- CLIENT reconnu (existe au CRM) ;
- PROSPECT (inconnu mais métier — cf. cibles-personas.md) ;
- ADMIN (factures, banque, administratif) ;
- BRUIT (newsletters, spam mou).
Étiqueter — list_labels puis create_label si manquants : Clients, Prospects, Factures, À-traiter — appliquer via label_thread/label_message. Le BRUIT est étiqueté, jamais supprimé (règle : on classe, on ne supprime pas).
Brouillons pour l'actionnable — pour chaque fil qui attend une réponse : create_draft CONTEXTUALISÉ —
- client/prospect CRM reconnu : historique (get_historique_prospect), devis en cours (list_devis) intégrés à la réponse ;
- ton de rapido-kb/ton-et-accroches.md ;
- un prospect entrant chaud → proposer d'enchaîner sur le skill secretariat-commercial (RDV).
Récap — N fils classés (par étiquette), N brouillons prêts (liste destinataire + objet) — RAPPELER que les brouillons attendent dans Gmail et que l'ENVOI appartient à l'utilisateur.

Garde-fous

JAMAIS d'envoi (l'outil ne le permet pas — ne pas le contourner par un autre canal) ; corbeille/spam = confirmation (hook).
Un fil ambigu (litige, ton juridique, RH) = escalade : le signaler dans le récap SANS brouillon automatique (règle « sensible » de regles-direction.md).
Ne pas étiqueter à tort un email personnel : en cas de doute, demander.

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.

5d ago First seen · 47 lines · 59 tokens per session scan A b4c7650dff88

Subscribe to this mod's changes

tri-boite-mail is a skill published in the GitHub repository PrendsTaPart/Plugin-Claude-MCP-BraindCode- (8 stars, last pushed 15d ago), licensed Apache-2.0. It adds 59 tokens to every session and 627 once invoked, about $0.0003 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 2026-09-03.

Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

the-open-agent/openagent · 17 tokens

mochi-remind

Handle due reminders — notify the user with natural language and mark them done.

kirodotdev/KiroCrew · 20 tokens