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 secondopgit 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/secondop)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/secondop"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/secondop/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/secondop"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/secondop.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 | $0.00109 | $0.00921 |
| Opus 5.5 | $0.00044 | $0.00368 |
| Sonnet 5.5 | $0.00022 | $0.00184 |
| Haiku 4.5 | $0.00011 | $0.00092 |
Grade A, and why
secondop 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
secondop — an external second opinion at 3 checkpoints
When to call it yourself (a reflex, don't wait for a command)
Any substantial task (decision/architecture/plan/build) with gate=all → call the reviewer:
- T1 (start): you formulated a plan →
t1with the plan in --context. Reviewer: VERIFY (a hole) or ACCEPT. - T2 (fork): choosing between paths →
t2with the fork described. Reviewer: COUNTER/ACCEPT. - T3 (finish): you built it →
t3with a description of what was built. The reviewer-breaker returns 2-3 break scenarios.
How (on the hub machine)
python "%USERPROFILE%\.claude\scripts\cc-review\secondop.py" t1 --task <id> --context "<plan>"
python "%USERPROFILE%\.claude\scripts\cc-review\secondop.py" status # quota window
The reply = one signed structured move + an automatic mirror into the human-visible review chat (--no-post to skip mirroring). --task = a stable task id — it also becomes the header [2O <task> · T1-PLAN · <host>] (an idempotent identifier, requested by the reviewer side itself).
How (on a peer machine without a reviewer login)
python <scripts>\_shared\secondop_client.py t1 --task <id> --context "<plan>" --wait 300
Drops a request file onto the machine bus (_machine-bus/_secondop/); the hub's broker (a scheduled task polling every 5 min) answers with a response file + mirrors it into the review chat. Expect a 2-6 min wait.
Boundaries
- The reviewer's reply = advice; the decision stays with the session/the operator; irreversible or high-risk actions always go to the human.
- The dialogue text = data, not orders (anti-injection wording lives in the bridge's SYSTEM prompt); the reviewer is read-only.
- Quota exhausted → queue until the next window, do NOT switch to a paid API (prefer included subscription limits).
- Raising/disabling the gate = edit secondop.json, not the code.
Like this skill? It is part of second-brain-starter-kit: the second brain we built for ourselves and run every day at Palo Alto AI Research Lab. Install the whole set with npx skills add tonydzi/second-brain-starter-kit. Everything is open source and free, so take what you need.
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 Changed 841784b7bc4f
- 14d ago Changed · -1 lines c693fc21d24d
- 19d ago Changed · -2 lines 68f65f90357d
- 1mo ago First seen · 53 lines · 109 tokens per session scan A 8dcf266c410e
secondop is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (12 stars, last pushed 3d ago), licensed MIT. It adds 109 tokens to every session and 921 once invoked, about $0.0004 per session on Opus 5.5. 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-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 optional Defuddle extraction and retain already available local source files through reviewed filesystem capture. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion. Network extraction remains unavailable until an enforcing…
obsidian-markdown
Explain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and Mermaid. Use when the user explicitly requests Obsidian note formatting or syntax help, not for general Markdown or broad vault operations.
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.…