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 skills add tonydzi/second-brain-starter-kit --skill resume-lastgit 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/resume-last)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/resume-last"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/resume-last/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.
<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/resume-last"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/resume-last.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00066 | $0.00921 |
| Opus 5 | $0.00033 | $0.00461 |
| Sonnet 5 | $0.00013 | $0.00184 |
| Haiku 4.5 | $0.00007 | $0.00092 |
Grade A, and why
resume-last scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/resume-last — pick up the previous chat in one move
The pain: a session crashed or got lost in the interface → you used to have to dig through the
catalog, find it and copy it by hand. The native claude --resume does not work for a foreign or
cross-machine session (since v2.1.9 Claude rejects a "foreign" session). So the reliable way is to start a
NEW session pre-loaded with the full history of the old one.
What it does
- Finds your latest human session (service/robot ones are filtered out by the
session_authorclassifier) — or takes a specificcliSessionIdif you pass one. - Builds the seed: the whole history + "continue from here", and puts it on the clipboard
(plus a file
_Dashboards/sessions-md/_continue/<cli>.seed.md). - You open a New session and press Ctrl+V — the conversation continues.
How to run
The latest session on this machine:
python "$IMPORTS_ROOT/claude_sessions/continue_session.py" --last
A specific session (id from Sessions-Catalog.html or from the /resume-last header):
python "$IMPORTS_ROOT/claude_sessions/continue_session.py" <cliSessionId>
(On Macs: python3, and for a non-standard vault path set env CLAUDE_VAULT_ROOT=<...>.)
What to tell the operator
- Say WHICH session was picked up (title + date + cli) and that the seed is already on the clipboard.
- Give exactly one instruction: "Open a New session and press Ctrl+V — you will continue where you left off."
- If
clipboard: FAILED— say the seed is in the file<cli>.seed.md, open it and copy manually. - If the operator can already see the wanted session in Recents on the same machine — remind them the
native
claude --resume <cli>works there too (faster, no pasting).
Boundaries
- READ-only against the vault/sessions: it only READS transcripts and writes the seed file + clipboard. It sends nothing and changes nothing in live data.
- It is the twin of the SessionStart hook
session_resume_hook(that one SHOWS the previous session at startup; this one PICKS IT UP with a single command).
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.
- today First seen · 69 lines · 66 tokens per session scan A 88034819bd6b
resume-last is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (6 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 921 once invoked, about $0.0003 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 2026-09-09.
Other skills, from other repositories
superbrain-distill
Internal SuperBrain skill — run by the detached capture child to distill a session-event delta into routed Obsidian notes. Not for direct user invocation.
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.…