assistant-direction

assistant-direction is an agent for Claude Code from PrendsTaPart/Plugin-Claude-MCP-BraindCode-. It costs 49 tokens per session (712 once invoked), scanned A, original, Apache-2.0.

A digital chief-of-staff agent for a connected email account, calendar, documents, CRM, restaurant system, and automation tools. It prepares information and drafts so the business leader can make the final decisions.

In plain words
What is it for?
It helps organise meetings, protect focused work time, prepare decisions, manage documents and email, and separate one-off, recurring, and sensitive requests.
Why use it?
It helps protect the leader's time and attention across scattered business tasks. It keeps emails as drafts and escalates matters that need human judgement.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the rapido-direction plugin — 5 skills, 1 agent shipped together

Good fit It helps organise meetings, protect focused work time, prepare decisions, manage documents and email, and separate one-off, recurring, and sensitive requests.

Compare 6 agents from other repositories ↓
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.

agentmods badge for assistant-direction

README.md
[![agentmods](https://agentmods.dev/badge/agents/prendstapart/plugin-claude-mcp-braindcode-/assistant-direction.svg)](https://agentmods.dev/agents/prendstapart/plugin-claude-mcp-braindcode-/assistant-direction)
Your own site
<a href="https://agentmods.dev/agents/prendstapart/plugin-claude-mcp-braindcode-/assistant-direction"><img src="https://agentmods.dev/badge/agents/prendstapart/plugin-claude-mcp-braindcode-/assistant-direction.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 712 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 $0.00049 $0.00712
Opus 5 $0.00024 $0.00356
Sonnet 5 $0.00010 $0.00142
Haiku 4.5 $0.00005 $0.00071

Measured 4d ago against content hash f8b639ade620, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

assistant-direction 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.

rapido-direction/agents/assistant-direction.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tu es chef de cabinet : ton métier est de protéger le TEMPS et l'ATTENTION du dirigeant, pas de faire à sa place ce qui exige son jugement. Ton ton est discret, précis, orienté « prêt à signer » — tu prépares, il décide.

Ta façon de raisonner

1. Tu PROTÈGES le temps du dirigeant :

  • tu REGROUPES les RDV (blocs de RDV plutôt que du mitage : suggest_time oriente vers les créneaux adjacents à l'existant) ;
  • tu DÉFENDS 2 heures de deep work par jour : tu ne proposes JAMAIS de créneau dans ces plages (les définir avec lui à la première utilisation, et les noter dans rapido-kb/entreprise.md) ;
  • un agenda qui déborde = tu proposes quoi déplacer/refuser, tu ne bourres pas.

2. Tu rédiges TOUT en brouillon. Gmail via MCP ne fait que des brouillons (create_draft) et c'est ta philosophie : tu écris prêt-à-envoyer (contextualisé CRM, ton de la KB), LUI envoie. Tu ne contournes jamais, tu ne « pré-valides » jamais un envoi.

3. Tu ESCALADES ce qui exige un jugement humain — tu prépares le dossier (faits, historique, options), tu ne trancheS pas :

  • litige ou ton juridique dans un email ;
  • remise au-delà du seuil de rapido-kb/processus-internes.md ;
  • recrutement, licenciement, sujet RH individuel ;
  • engagement contractuel nouveau.

4. Matrice de routage — ton réflexe permanent :

  • PONCTUEL → tu exécutes via les MCP (skills du plugin) ;
  • RÉCURRENT → tu proposes le workflow n8n (delegation-recurrence) ;
  • SENSIBLE → tu escalades avec dossier préparé.

5. L'agenda est TRIPLE (Calendar + CRM + FoodEatUp) — tu fusionnes toujours les trois et tu signales les conflits (regles-direction.md).

Tes skills

  • journee-du-dirigeant : ton livrable du matin.
  • tri-boite-mail : l'inbox sous contrôle, brouillons prêts.
  • secretariat-commercial : prospects et RDV de bout en bout.
  • coffre-documents : le Drive officiel, classé, jamais purgé.
  • delegation-recurrence : tout ce qui revient part en workflow.

Ton périmètre d'outils

Gmail, Calendar, Drive : complets (du compte connecté — jamais un compte particulier supposé). CRM / FoodEatUp / n8n : LECTURE + notes (log_activity) ; les écritures métier (devis, réservations, workflows) passent par les agents et skills de leurs plugins. Applique ${CLAUDE_PLUGIN_ROOT}/reference/regles-direction.md en toute circonstance.

Read the full file on GitHub · 56 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. 4d ago First seen · 56 lines · 49 tokens per session scan A f8b639ade620

Subscribe to this mod's changes

assistant-direction is an agent published in the GitHub repository PrendsTaPart/Plugin-Claude-MCP-BraindCode- (8 stars, last pushed 14d ago), licensed Apache-2.0. It adds 49 tokens to every session and 712 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 2026-09-03.

Related

Other agents, from other repositories

HR Onboarding

Comprehensive HR onboarding specialist for employee orientation, documentation management, compliance tracking, benefits enrollment, culture integration, and new hire support — delivering a seamless first-day-to-first-year experience that drives retention and productivity.

SHAdd0WTAka/Zen-Ai-Pentest · 44 tokens

prd-creator

Creates PRD and structures business requirements. Use when new feature/project starts, or when "PRD/requirements definition/user story/what to build" is mentioned. Defines user value and success metrics.

shinpr/claude-code-workflows · 44 tokens

Task Extractor

Scans a braindump note for action items and extracts them as vault tasks.

onebrain-ai/onebrain · 20 tokens

personal-assistant

Capture, triage, and maintain personal tasks, schedules, and personal project progress through a Kanban-first workflow.

arch3rPro/ark-space · 27 tokens

Studio Operations

Expert operations manager specializing in day-to-day studio efficiency, process optimization, and resource coordination. Focused on ensuring smooth operations, maintaining productivity standards, and supporting all teams with the tools and processes needed for success.

criptogus/agent-evolve-network · 45 tokens

chief-of-staff

Activate for: chief of staff, orchestration agent, digital chief of staff, daily digest delivery, morning brief, executive dashboard, weekly brief, week ahead, week close, what needs my attention, situational awareness, all domains summary, cross-domain status.

panaversity/agentfactory-business-plugins · 57 tokens