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/tonydzi/second-brain-starter-kit/agents-mdgit clone --depth 1 https://github.com/tonydzi/second-brain-starter-kitWrote 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.
[](https://agentmods.dev/instructions/tonydzi/second-brain-starter-kit/agents-md)<a href="https://agentmods.dev/instructions/tonydzi/second-brain-starter-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/tonydzi/second-brain-starter-kit/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01104 | $0.01104 |
| Opus 5 | $0.00552 | $0.00552 |
| Sonnet 5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
second-brain-starter-kit AGENTS.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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — working in this repo
Written for AI coding agents, and equally readable by a human contributor. Short on purpose. Русская сводка — в конце.
What this repo is
A working "Claude Code as a second brain + working assistant" setup, stripped of personal data and cut down to a portable core: the method, not the data. 101 skills, a CRM engine with sample data, vault templates, engine passports, and the seed message that starts the first session.
The primary reader is someone else's agent, bootstrapping a system for its own operator. That shapes everything below: instructions must survive being executed by a model that has never seen this repo, on a machine you know nothing about.
Layout
SEED.md— the first message a user pastes into Claude Code. Everything starts here.BOOTSTRAP-CLAUDE.md— instructions to the installing agent.CLAUDE-EXTERNAL.md— the working principles that become the user's ownCLAUDE.md.skills/— 101 skill commands, mapped inskills/INDEX.md.crm-template/— markdown "card = file" CRM plus the scoring engine and demo data.engines/— the published engines;engines/PASSPORTS.mdis their catalogue.templates/,docs/— note templates, onboarding, and what is/isn't shared.HANDOVER.md— entry point if the reader already runs a fleet of agents.
How to verify a change
The one command that exercises real logic end to end, offline:
cd crm-template/reference
python demo.py # scores the shipped sample, prints bands, queue, and an agreement check
Read what it prints before you "fix" it: the priority column is expected not to reproduce exactly, because the export deliberately does not carry three signals that live in the message store. That gap is documented, not a bug — a PR that makes the numbers agree by changing the model is going the wrong way.
If you changed a skill or a doc, verification is different: paste the before/after of the concrete
file, per docs/HOW-TO-CONTRIBUTE.md. Abstract "this could be improved" is nearly impossible to
judge and will come back as a question.
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.
- 3d ago First seen · 83 lines · 1,104 tokens per session scan A 9c9dc74e90b3
second-brain-starter-kit AGENTS.md is an instructions file published in the GitHub repository tonydzi/second-brain-starter-kit (5 stars, last pushed 4d ago), licensed MIT. It adds 1,104 tokens to every session, about $0.0055 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
claude-obsidian GEMINI.md
Gemini CLI instructions for AgriciDaniel/claude-obsidian: Read AGENTS.md as the canonical host-neutral contract. Skills live in skills/ /SKILL.md and the portable core lives in claudeobsidian/.
claude-obsidian AGENTS.md
AGENTS.md instructions for AgriciDaniel/claude-obsidian, covering claude-obsidian: agent instructions, product and vault boundaries, bootstrap, canonical skills and mutation protocol.
claude-obsidian copilot-instructions.md
Copilot instructions for AgriciDaniel/claude-obsidian: Read AGENTS.md before proposing changes. The repository is an Agent Skills package, Claude Code adapter, standard-library Python core, and deterministic vault template—not the default live user vault.
llm-brain CLAUDE.md
Instructions for kimsanguine/llm-brain, covering llm-brain — claude code 운영 지침, 가드레일 (절대 위반 금지), 프라이버시 경계 (agent memory os), 명령어 and ingest.
superbrain CLAUDE.md
Instructions for m3talux/superbrain, covering superbrain — repository rules, non-negotiables, public-facing content, versioning and workflow.
cmds-llm-wiki AGENTS.md
Schema and harness document for the CMDS LLM Wiki vault. Defines the 3-layer architecture (Raw Sources / Wiki / Schema), ingest-query-lint operations, file conventions, and frontmatter standards. This is the single source of truth for LLM behavior in this vault.