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 retrogit 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/retro)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/retro"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/retro/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/retro"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/retro.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 | $0.00101 | $0.06484 |
| Opus 5 | $0.00051 | $0.03242 |
| Sonnet 5 | $0.00020 | $0.01297 |
| Haiku 4.5 | $0.00010 | $0.00648 |
Grade A, and why
retro 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 yesterday.
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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/retro — session retrospective (what we built · what we keep)
🧒 When reporting to a non-technical owner: end with a child-simple "In plain words" recap in his language. His standing request (memory
eli5-always). Reports TO him only — not inside vault notes.
A retro = the Agile end-of-cycle ritual (Keep / Drop / Try) applied to a work session: look back, decide what survives. The goal is that nothing reusable drowns in the transcript — tools, rules, and lessons get caught and put in their right home.
Step 0 — RECALL & RECONCILE FIRST (situate this session in the WHOLE collaboration)
Before any inventory, RECALL WIDE — this is the heart of the retro, not a formality (the owner, 2026-07-02). A session never happened in a vacuum: I run on multiple machines + a Cowork fleet concurrently, and this retro may be running days/weeks/months after the work. So recall here serves TWO jobs, not one:
- (A) De-dupe — a rule/skill/note I'm about to capture may already be done by a parallel session.
- (B) Reconcile — line up what THIS session did against everything the whole hub / vault / peers decided since; catch drift, superseded decisions, contradictions, and durable work not yet propagated. This is the RECALL-before-activity rule (
capture-rules-into-bible) applied to retro.
⏳ Measure the time-gap FIRST. Check when this session's work actually happened (turnstate ledger / the digest's day-span) vs now. Old session → widen every lookup below to cover "what changed SINCE" — don't recall only the session's own window.
Recall stack — cheap→expensive, mostly 0 tokens (use the existing tools, don't reinvent):
- This session's spine (0 tok):
python "$IMPORTS_ROOT/turnstate/turnstate_show.py"— the black box of what THIS session actually asked / decided / touched (facts, not memory). - Recent retros:
ls "$OBSIDIAN_VAULT/01-Conversations/Claude/Retros/"— widen the window to span the gap; read any same-topic retro since. - Neighboring chats (lexical, 0 tok):
/search <topic words>(search_catalog.db, ~99k Telegram/FB/ChatGPT/Claude) — what did the owner or another session dictate elsewhere about this topic? - Vault meaning (RAG):
/ask <topic>($IMPORTS_ROOT/brain_ask.py) — what does the Second Brain already hold / already decide on this? - Memory + vault grep for every rule/concept/decision this session touched — already captured? superseded / changed since?
- Peers & cross-machine:
/inbox+_machine-bus+ consensus commits — everything agreed on the OTHER machines; did a peer already decide, or undo, this? - Declined journal: skill
/declined— did we already reject something this session quietly re-did?
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.
- yesterday First seen · 184 lines · 101 tokens per session scan A e50d715555d3
retro is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (6 stars, last pushed yesterday), licensed MIT. It adds 101 tokens to every session and 6,484 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-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…
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.
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…
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…
defuddle
Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.