What is mecha-scribe?

A workflow for creating long project documents—such as specifications, plans, reports, and technical notes—in an Obsidian vault, a folder of linked Markdown notes. It routes each document to the appropriate project's documentation folder.

Use it when an agent needs to write a project specification, plan, report, or other long document in the vault.

It keeps long documentation out of code repositories and separate from short-term agent memory. It also provides a standard place and creation process for project documents.

mecha-scribe — Skill for Claude Code and Codex by bbarrosdavi

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 bbarrosdavi/mechabrain --skill mecha-scribe

Clone the repo

git clone --depth 1 https://github.com/bbarrosdavi/mechabrain

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bbarrosdavi/mechabrain/mecha-scribe/github.svg)](https://agentmods.dev/skills/bbarrosdavi/mechabrain/mecha-scribe)

Your own site

<a href="https://agentmods.dev/skills/bbarrosdavi/mechabrain/mecha-scribe"><img src="https://agentmods.dev/badge/skills/bbarrosdavi/mechabrain/mecha-scribe/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/bbarrosdavi/mechabrain/mecha-scribe"><img src="https://agentmods.dev/badge/skills/bbarrosdavi/mechabrain/mecha-scribe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,501 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	$0.00000	$0.01501
Opus 5.5	$0.00000	$0.00600
Sonnet 5.5	$0.00000	$0.00300
Haiku 4.5	$0.00000	$0.00150

Measured 9d ago against content hash 202390884598, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mecha-scribe 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 9d 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.

src/mechabrain/templates/mecha-scribe-skill.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mecha-Scribe — documentar projetos NA vault

Subsistema Classe B de documentação (spec §11). Você (agente) produz documentação longa na vault — nos diretórios de projeto, que já têm infra de docs — e não nos repositórios de código, e não como memória no mecha-brain. O doc já é indexado e aparece num memory_search — não feche a escrita com um episódico (isso duplica o rastro e polui o brain). O brain guarda só o conhecimento destilado (INS), quando houver.

Princípio: documento longo é conteúdo, não memória. Não escreva spec/plano/ relatório dentro de mecha-brain/.

Fluxo (siga na ordem)

ROTEAR — o projeto do trabalho corrente define a zona:
- <Área>/<Projeto>/02_Docs/ para docs técnicos, specs, planos, relatórios;
- a raiz do projeto só para DOC_* de alto nível;
- subprojeto (padrão fractal) → .../<Projeto>/<Subprojeto>/02_Docs/.
CRIAR a partir do template — de duas formas, nesta ordem de preferência:
- Obsidian CLI + Templater (preferido): com a CLI do Obsidian habilitada (Settings → General → Advanced), crie a nota pelo Templater a partir do template geral da vault (.../Templates/1_Template_Nota_Geral, ramo não-task). O Templater preenche frontmatter, seções e navegação. Como o template é interativo (prompts/suggester), responda os prompts com os valores da rota (título, tipo DOC/REL/TEC, projeto).
- Replicar o resultado (fallback headless): sem a CLI (outra máquina, sessão sem GUI), replique a saída do template — mesmo frontmatter, mesmas seções, mesma navegação. Frontmatter mínimo:
```
---
title: "<título descritivo>"
tags: [<projeto/*>, tipo/documentacao, <area/*>, status/ativo, agent/<seu id>]
created: YYYY-MM-DD
modified: YYYY-MM-DD
agent: <seu id do registry>      # quem escreveu (R6.2) — obrigatório, ver abaixo
project: "[[DASHBOARD_<Projeto>|<Projeto>]]"
code: "DOC"       # ou REL / TEC
status: ativo
dg-publish: <conforme a política da área>
---
```
  Pelo caminho do Templater o frontmatter sai sem autoria (o template é feito para um humano, o autor implícito) — acrescente agent: e a tag agent/<id> você mesmo depois de criar a nota.

Read the full file on GitHub · 95 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.

9d ago First seen · 95 lines · 0 tokens per session scan A 202390884598

Subscribe to this mod's changes

mecha-scribe is a skill published in the GitHub repository bbarrosdavi/mechabrain (0 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,501 tokens. 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 2026-10-06.

Documents Writing and docs

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

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

baoyu-youtube-transcript

A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.

JimLiu/baoyu-skills · 107 tokens

legal-hold

Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.

anthropics/claude-for-legal · 68 tokens

feishu

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

Hmbown/CodeWhale · 33 tokens

read

Fetches URLs and PDFs, then summarizes or returns clean Markdown. Use when asked to read, fetch, quote, cite, convert, or save a URL or PDF. Not for local text files already in the repo.

tw93/Waza · 46 tokens