dbrain-processor

A daily processor for voice and text entries sent through Telegram. It classifies them as tasks or thoughts, saves thoughts as linked Obsidian notes, and creates an HTML report; it can also use client, project, and CRM context.

In plain words
What is it for?
Process entries on command or on a daily schedule, create notes and checklist tasks, detect business references, and send a formatted HTML report through Telegram.
Why use it?
It turns an unstructured daily inbox into organized notes, tasks, and a report. This reduces manual sorting and keeps personal entries connected to relevant business information.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/smixs/agent-second-brain/dbrain-processor
Any agent
npx skills add smixs/agent-second-brain --skill dbrain-processor
Clone the repo
git clone --depth 1 https://github.com/smixs/agent-second-brain

Made for: Claude Code, Codex.

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,954 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00060 $0.03954
Opus 5 $0.00030 $0.01977
Sonnet 5 $0.00012 $0.00791
Haiku 4.5 $0.00006 $0.00395

Measured 2d ago against content hash fca129032676, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dbrain-processor 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 2d 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.

vault/.claude/skills/dbrain-processor/SKILL.md · 513 lines

How it starts

The opening of the file, as written. The whole thing — 513 lines — stays where its author put it; the contents beside it link to each section on GitHub.

d-brain Processor

Process daily entries → thoughts (Obsidian) + HTML report (Telegram).

Integrates with Your Business data for business context.

CRITICAL: Output Format

ALWAYS return RAW HTML. No exceptions. No markdown. Ever.

Your final output goes directly to Telegram with parse_mode=HTML.

Rules:

  1. ALWAYS return HTML report — even if entries already processed
  2. ALWAYS use the template below — no free-form text
  3. NEVER use markdown syntax (**, ##, ```, -)
  4. NEVER explain what you did in plain text — put it in HTML report

WRONG:

<b>Title</b>

CORRECT: Title

Processing Flow

  1. Load personal context — Read goals/1-yearly, goals/2-monthly, goals/3-weekly
  2. Load business context:
    • Read business/_index.md — Your Business (клиенты, проекты, CRM)
    • Read projects/_index.md — личные проекты (если релевантно)
  3. Read daily — daily/YYYY-MM-DD.md
  4. Process entries — Classify → task or thought, detect business mentions
  5. Create cards (autograph) — new entities/thoughts become vault cards per the autograph template (type, description-as-snippet, tags, status); tasks become checklist entries in the daily note / project notes
  6. Build links — Connect notes with [[wiki-links]], link to business entities
  7. Generate HTML report — business activity + day summary
  8. Log actions to daily — append action log entry (see below)
  9. Evolve MEMORY.md — update long-term memory if needed (see below)
  10. Capture observations — record friction signals to handoff.md (see below)

ОБЯЗАТЕЛЬНО: Логирование в daily/

После ЛЮБЫХ изменений в vault — СРАЗУ пиши в daily/YYYY-MM-DD.md:

Формат:

## HH:MM [text]
{Описание действий}

**Создано/Обновлено:**
- [[path/to/file|Name]] — описание

Что логировать:

  • Создание файлов в thoughts/
  • Обновление business/ или projects/
  • Добавление task-записей в daily/проекты
  • Синхронизация с внешними системами

Пример:

## 14:30 [text]
Обработка ежедневных записей

**Создано задач:** 2
- [ ] Follow-up Acme Corp (due: завтра, p2)
- [ ] Подготовить КП Unilever (due: пятница, p2)

**Сохранено мыслей:** 1
- [[thoughts/ideas/product-launch|Product Launch]] — идея запуска

Read the full file on GitHub · 513 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. 2d ago First seen · 513 lines · 60 tokens per session scan A fca129032676

Subscribe to this mod's changes

dbrain-processor is a skill published in the GitHub repository smixs/agent-second-brain (361 stars, last pushed 27d ago), licensed MIT. It adds 60 tokens to every session and 3,954 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 2026-08-30.

Related

Other skills, from other repositories

graph-mutation-plan

Cookbook for composing an applygraphmutations plan — stable entitykey patterns, the canonical label/edge vocabulary, evidence/invalidation/confidence discipline, and a worked example. Load this when building a non-trivial mutation plan.

potpie-ai/potpie · 51 tokens

scienceworld-growth-focuser

Use when you have planted a seed or need to track a plant's growth stage (sprouting, flowering, reproduction). Applies the 'focus on' action to a specific plant or biological entity to signal intent and monitor its development. Trigger after planting or when you need to observe life cycle progression in the…

zjunlp/SkillNet · 71 tokens

scienceworld-conditional-box-placer

Moves an object to one of two destination containers based on a numeric threshold check. Trigger after a measurement (e.g., temperature) is taken. Place object in 'green' box if value > threshold, or 'blue' box if value < threshold.

zjunlp/SkillNet · 59 tokens

ledger

OPS on-demand: This skill should be used when the user asks to "ops ledger", "what did we handle", or…

Lifecycle-Innovations-Limited/claude-ops · 28 tokens

pdf

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…

spytensor/openmozi · 92 tokens

po-pass

Run the solo product-owner gate before product, UX, graph, MCP, CLI, workflow, or macOS-shell work. Separate phenomenon from problem, score all six rubric rows, and escalate mechanically.

wlsdks/ontology-atlas · 43 tokens