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.
npx agentmods add instructions/cocaxcode/logbook-mcp/claude-mdgit clone --depth 1 https://github.com/cocaxcode/logbook-mcpWhat 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 | $0.01894 | $0.01894 |
| Opus 5 | $0.00947 | $0.00947 |
| Sonnet 5 | $0.00379 | $0.00379 |
| Haiku 4.5 | $0.00189 | $0.00189 |
Grade A, and why
logbook-mcp CLAUDE.md 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
logbook-mcp (v2)
Cuaderno de bitácora del developer via MCP. Notas, TODOs y code TODOs sin salir de tu AI. Obsidian-only desde v2.0 (SQLite eliminado).
Stack
- TypeScript 5 (ESM)
- MCP SDK (@modelcontextprotocol/sdk)
- Archivos Markdown con frontmatter YAML — backend Obsidian
- @orama/orama — search full-text BM25+fuzzy (puro JS)
- @clack/prompts — wizard interactivo
setup init - chokidar — watcher de cambios externos en el vault
- Vitest para tests
- tsup para build
Arquitectura
src/
├── index.ts # Entry: --mcp → server, else CLI dispatcher
├── server.ts # createServer() — registra 5 tools + 5 shims
├── cli.ts # Shim que llama a cli/dispatcher
├── config.ts # Config legacy (~/.logbook/config.json)
├── types.ts # Re-exports de storage/types
├── config/ # Sistema de config en capas (v2)
│ ├── types.ts # ConfigLayer, ResolvedConfig, ConfigTrace
│ ├── defaults.ts # Hardcoded defaults
│ ├── resolve.ts # resolveConfig() merge + trace
│ ├── detect-vaults.ts # Cascade obsidian.json → common-folder scan
│ ├── detect-plugins.ts # community-plugins.json
│ └── reminders-state.ts # .logbook/reminders-state.json (atomic R/W)
├── core/
│ └── auto-wikilinks.ts # autoWrapIds + expandRefShortcut middleware
├── cli/
│ ├── dispatcher.ts # --mcp vs CLI mode routing
│ ├── snippet.ts # MCP snippets per client (7 clientes)
│ └── commands/
│ ├── setup.ts # init wizard (@clack/prompts) + status + reorganize
│ ├── note.ts # logbook-mcp note <content>
│ ├── todo.ts # logbook-mcp todo add <content>
│ └── search.ts # logbook-mcp search <query>
├── storage/
│ ├── types.ts # StorageBackend + tipos compartidos
│ ├── index.ts # Factory getStorage() — sólo Obsidian
│ └── obsidian/
│ ├── index.ts # ObsidianStorage (monolito de v1, conserva)
│ ├── orama-adapter.ts # Búsqueda full-text (Orama, lazy + cache)
│ ├── frontmatter.ts # Parser/serializer YAML
│ ├── slug.ts # Slugify con acentos
│ ├── workspace.ts # Autodetección workspace/project
│ ├── wikilinks.ts # [[wikilinks]] (rendering existente)
│ ├── files.ts # Helpers .md
│ └── formatting.ts # Callouts, checkboxes
├── git/
│ ├── detect-repo.ts # detectRepoPath via git rev-parse
│ └── code-todos.ts # Scan TODO/FIXME/HACK/BUG via git grep
├── tools/ # 5 main tools + 5 shims deprecated
│ ├── note.ts # logbook_note
│ ├── todo.ts # logbook_todo (add/list/done/edit/rm)
│ ├── entry.ts # logbook_entry (list/edit/delete/standup/decision/debug)
│ ├── query.ts # logbook_query (search/log/timeline/tags/reminders/review/get)
│ ├── setup.ts # logbook_setup (init/status/inbox/topics)
│ └── shims/ # Deprecated, eliminados en v2.2
│ ├── tags.ts
│ ├── reminders.ts
│ ├── review.ts
│ ├── inbox.ts
│ └── topics.ts
└── resources/
└── reminders.ts # MCP resource: logbook://reminders
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.
- yesterday First seen · 170 lines · 1,894 tokens per session scan A 66e47982626d
logbook-mcp CLAUDE.md is an instructions file published in the GitHub repository cocaxcode/logbook-mcp (1 stars, last pushed 3mo ago), licensed MIT. It adds 1,894 tokens to every session, about $0.0095 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 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.