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 skills/tonydzi/second-brain-starter-kit/five-hardnpx skills add tonydzi/second-brain-starter-kit --skill five-hardgit 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/skills/tonydzi/second-brain-starter-kit/five-hard)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/five-hard"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/five-hard.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 | $0.00077 | $0.00905 |
| Opus 5 | $0.00039 | $0.00452 |
| Sonnet 5 | $0.00015 | $0.00181 |
| Haiku 4.5 | $0.00008 | $0.00090 |
Grade A, and why
five-hard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/five-hard — five hard questions
🧒 When reporting to a non-technical operator, end with a child-simple "In plain words" recap in their language.
Why: the identity layer (belief-* + concept-bible-*, ~24 notes) is "how I think".
That gets dangerous once part of it is wrong and nobody has checked. Here the brain itself starts the pressure-test.
Run
python "$IMPORTS_ROOT/five_hard_pick.py" -> the 5 most stagnant notes (oldest mtime)
-> $IMPORTS_ROOT/_five_hard_pick.json. Override: env FIVE_HARD_N=7.
The questions (top-model quality — identity synthesis, not grunt work)
Read each note IN FULL and give ONE hard question per note:
N. **[<stem>]** — <the owner's thesis in your own words>
Question: <sharp, Socratic, capable of forcing a rethink>
Why it is hard: <which counter-fact or trend could flip it>
Style: Socratic — not "you are wrong" but "what makes you sure today?"; lean on CONCRETE recent
signals; epistemic-neutrality; aim at the UNTESTED edge (the "tension / nuance" section),
not at the part already reflected on. "The rule still stands" is a valid answer (bible-as-prompt).
Recording the answer (long memory; backup-first: vault_backup.py)
-> $OBSIDIAN_VAULT/04-Coach/_Five-Hard/five-hard-YYYY-MM-DD.md
Frontmatter: title, date, type: five-hard, source: claude-session,
tags: [five-hard, coach, identity-layer]. Body: the questions + the owner's answers verbatim;
if they changed position, propose a diff to the belief/bible note with supersedes: (via /intake). NO 🧒 block inside the note.
Scheduled twin
Cron five-hard-monthly: 1st of the month, 05:25 Lisbon (the briefing window, routines-run-at-night).
Picker -> questions (top-model subagent) -> the fleet log chat via python $USERPROFILE/.claude/scripts/bus_ping.py --post "..."
(canon: alerts go to the fleet log chat, never to Saved Messages) + "answer by voice or text, I will file it into the vault".
The manual twin is this skill; the single source of truth is the picker.
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.
- 4d ago First seen · 62 lines · 77 tokens per session scan A 349f5f89a739
five-hard is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (5 stars, last pushed 5d ago), licensed MIT. It adds 77 tokens to every session and 905 once invoked, about $0.0004 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 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…
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.
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…
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…
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.…
wiki-cli
Detect and use the official Obsidian command-line interface for read-only vault access; use for wiki-cli, Obsidian CLI, Obsidian read, Obsidian search, vault transport, which transport, transport detection, backlinks, tags, or Obsidian command line. Mutations always go through the claude-obsidian transaction core.