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 ttgit 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/tt)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/tt"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/tt/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/tt"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/tt.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 | $0.00108 | $0.03330 |
| Opus 5 | $0.00054 | $0.01665 |
| Sonnet 5 | $0.00022 | $0.00666 |
| Haiku 4.5 | $0.00011 | $0.00333 |
Grade A, and why
tt 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/tt — the quality gate right after building
🧒 When reporting to a non-technical operator: end with a short "In plain words" recap in their language (standing rule [[eli5-always]]). Only in the message TO them — never inside artifacts.
This is not a retrospective. Retro = packaging the whole session at the end. /tt = a narrow check of the one thing we just built, while the context is hot. The pain that created it (2026-06-25): "we built it, said 'done', moved on — and it was only 2/3 finished." /tt catches that BEFORE the word "done".
When: immediately after building/editing a skill · script · routine · hook · vault pipeline · mechanism note — anything that is supposed to DO something. Not for conversational replies and not for trivial text edits.
Boundary vs neighbors: /1 = is the SYSTEM alive after a crash; a browser verify = does the APP work; /tt = does the exact thing we just built work.
Step 0 — RECALL the scope (what did we actually change)
Not from memory — from facts. List what this task really created/touched:
- fresh/modified files:
~/.claude/skills,~/.claude(memory/CLAUDE.md/hooks/scheduled-tasks),$IMPORTS_ROOT, vault notes; - quick anchor:
python "$IMPORTS_ROOT/retro_inventory.py" 1(the same inventory the retro skill uses) OR simply list what you edited in THIS session. - Take only what belongs to the CURRENT task (ignore other machines' fleet edits — not ours, see [[session-machine-tagging]]).
- RECALL existing knowledge on the topic (a gate born from a real miss on 2026-07-04: we fixed a pipeline without checking memory first and nearly duplicated a parallel session's work): before running/fixing, pull up what is ALREADY known — grep the memory folder + semantic search + grep the vault for the changed area. A parallel session may have already done/documented it ([[capture-rules-into-bible]] → RECALL-before-activity).
Step 1 — RUN it live (on real data, not in theory)
Run the thing for real on real data and show actual output:
- a skill → execute its procedure by hand right here;
- a script → run it (read-only/dry-run if it has side effects);
- a routine/hook → trigger it manually or verify it actually fires (not "it should");
- a rule note → check that links/slugs resolve and the frontmatter is valid. "Works in theory" ≠ proven. You need live output.
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 · 136 lines · 108 tokens per session scan A 1afd33780095
tt is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (6 stars, last pushed today), licensed MIT. It adds 108 tokens to every session and 3,330 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 2026-09-09.
Other skills, from other repositories
wiki-lint
Run a deterministic, read-only health check on an Obsidian wiki. Use for lint, vault health check, audit wiki health, find orphans, find dead links, frontmatter audit, provenance audit, or wiki audit. Reports graph, link, frontmatter, provenance-ledger, empty-section, and stale-index findings; it does not reason…
lint
A health check for the LLM Wiki, a knowledge base about large language models. It looks for missing pages, broken links, conflicting or outdated content, missing fields, incomplete topic maps, weak bias checks, and an old core-context snapshot.
wiki-ingest
Ingest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this…
autoresearch
Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomous or deep research that may access the public web. Triggers: /autoresearch, autoresearch, research this topic, deep dive into, investigate, find…
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…
canvas
Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.