intake

intake is a skill for Claude Code, Codex from tonydzi/second-brain-starter-kit. It costs 99 tokens per session (2,288 once invoked), scanned A, original, MIT.

A rule-routing workflow that records a new instruction in every relevant place, such as shared rules, memory, or a skill. It also leaves a shared record so other running processes can see it.

In plain words
What is it for?
Use it when adding or changing a preference, policy, or agent instruction that must apply across multiple files or automated processes.
Why use it?
It prevents a rule from being saved in only one place and then forgotten elsewhere. This reduces conflicting instructions and repeated manual updates.

Skill for Claude CodeCodex

Part of the second-brain-skills plugin — 57 skills shipped together

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/tonydzi/second-brain-starter-kit/intake
Any agent
npx skills add tonydzi/second-brain-starter-kit --skill intake
Clone the repo
git clone --depth 1 https://github.com/tonydzi/second-brain-starter-kit

Made for: Claude Code, Codex.

Or install second-brain-skills, the plugin that ships this one along with the rest of its 57 skills.

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 intake

README.md
[![agentmods](https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/intake.svg)](https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/intake)
Your own site
<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/intake"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/intake.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,288 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 $0.00099 $0.02288
Opus 5 $0.00049 $0.01144
Sonnet 5 $0.00020 $0.00458
Haiku 4.5 $0.00010 $0.00229

Measured 4d ago against content hash fbfd4780f0b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

intake 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.

skills/intake/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/intake — the rule intake (route it to its homes, don't just write it down)

🧒 When reporting to a non-technical owner: end with a child-simple "In plain words" recap (memory eli5-always). Reports TO him only — never inside vault notes.

Why (canon: memory rules-intake-channel). This chat is the dedicated channel where the owner drops ALL rules/policies/Bible entries/skills/CLAUDE.md edits/preferences, so that working chats stay clean. My job is not just to write it down, but to DELIVER the rule to all of its homes, cross-link it, and leave a trace in the always-loaded layer, so that automatic/parallel processes see it on their next start. This skill = the same manual flow I repeated ~10× in one session, folded into a single command.

Architecture (skill-design-three-layer): a thin SKILL.md orchestrator + deterministic steps (backup/commit/grep) + an external store (CLAUDE.md, memory, the vault). The routing decision is still shown to the owner in the report — the skill does not hide the logic, it executes it without asking at every step.


Step 0 — RECALL (dedup; cheap, ~0 tokens). NEVER spawn a duplicate

Before writing — check whether such a rule already exists (update it, don't spawn a copy; resolve conflicts by "newer beats older"):

  • MEMORY.md is already in context — scan its index by topic.
  • grep over memory: $USERPROFILE/.claude/projects/<project>/memory/.
  • grep over the Bible/vault: reglament-* / protocol-* under 03-Insights\Operations\ and 05-Resources\Protocols\; if needed, RAG via brain_ask.py "<topic>".
  • Found an existing one → update it (don't create a second), mark supersedes / refresh date_established. A conflict between the owner's own rules (origin: anton) is resolved only by him or by an explicit supersedes.

Step 1 — Classify the rule by its FORM → pick the homes

Route per operating-agreement → "Where durable rules go" (do NOT duplicate the rule across files — each level REFERENCES the one below):

  • How I work / a machine process (imports, dashboards, token economy, routines, my reply style) → CLAUDE.md (an always-on block) + memory (+ a line in MEMORY.md).
  • A durable fact / preference → memory (memory\*.md + a pointer line in MEMORY.md).
  • An action ON THE OWNER'S BEHALF towards the outside world (outreach, his chats, calendar, purchases, hiring, household) → the Bible (reglament-* in the vault) + if needed a lift into always-on in CLAUDE.md.
  • "Every time automatically when X" → a hook (skill update-config), not "keep it in mind".
  • Time-based "every Monday / every morning" → a scheduled task / routine (skill schedule).

Read the full file on GitHub · 79 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 · 79 lines · 99 tokens per session scan A fbfd4780f0b8

Subscribe to this mod's changes

intake is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (5 stars, last pushed 4d ago), licensed MIT. It adds 99 tokens to every session and 2,288 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

wiki-retrieve

Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…

AgriciDaniel/claude-obsidian · 81 tokens

wiki

Initialize, adopt, and route work for a separate Obsidian knowledge vault through the portable claude-obsidian core. Use for vault setup, scaffolding, workspace selection, cross-project configuration, or choosing the correct wiki sub-skill. Triggers: /wiki, set up wiki, scaffold vault, create knowledge base, adopt…

AgriciDaniel/claude-obsidian · 84 tokens

obsidian-bases

Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.

AgriciDaniel/claude-obsidian · 69 tokens

save

Save a user-selected answer, decision, insight, or session summary into an Obsidian vault as one reviewed transaction. Use only when the user explicitly asks to preserve specific conversation content, not when they supply a file or URL to ingest. Triggers: /save, save this, save that answer, file this conversation…

AgriciDaniel/claude-obsidian · 80 tokens

wiki-fold

Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit…

AgriciDaniel/claude-obsidian · 76 tokens

wiki-mode

Read or configure the vault filing methodology and suggest destinations for planned knowledge creation under Generic, LYT, PARA, or Zettelkasten. Use for wiki mode, methodology mode, what is my vault mode, set vault mode, switch to PARA, use LYT, Zettelkasten setup, change mode, configure mode, or methodology routing.…

AgriciDaniel/claude-obsidian · 83 tokens