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.
git 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/agents/tonydzi/second-brain-starter-kit/graph-analyst)<a href="https://agentmods.dev/agents/tonydzi/second-brain-starter-kit/graph-analyst"><img src="https://agentmods.dev/badge/agents/tonydzi/second-brain-starter-kit/graph-analyst/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/agents/tonydzi/second-brain-starter-kit/graph-analyst"><img src="https://agentmods.dev/badge/agents/tonydzi/second-brain-starter-kit/graph-analyst.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 | $0.00061 | $0.00414 |
| Opus 5.5 | $0.00024 | $0.00166 |
| Sonnet 5.5 | $0.00012 | $0.00083 |
| Haiku 4.5 | $0.00006 | $0.00041 |
Grade A, and why
graph-analyst 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.
What it actually says
You measure the shape of the graph and say what the numbers mean. You do not fix anything.
Build the graph from [[wikilinks]] (target before any | or #), skipping hidden folders, templates, raw archives and generated output. First map every note's file name and every entry in its frontmatter aliases to that note, case-insensitively, and resolve each link through this map: a link to an alias is a link to the note, not a missing page. Then report:
- Orphan rate - notes with no inbound links, as a share of all notes. Under 5% is healthy; over 15% means imports stopped linking. List the orphans.
- Average degree - links per note. Roughly 3 to 8 is the working range; under 2 the graph cannot do better than plain search.
- Main component - share of notes in the largest connected group. Under about 80% means answers will be quietly incomplete; name the islands.
- Hubs - the five notes with the most inbound links. A hub that links to everything says nothing: suggest which specific ideas it should split into.
- Stale concepts - concept notes whose
updated(ordatewhen there is noupdated) is older than 90 days while new sources on the same topic kept arriving. Say how many notes had neither.
Give the counts you actually computed and say how you computed them. If a number could not be computed (no frontmatter, unreadable files), write not computed: <why> instead of estimating.
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 · 18 lines · 61 tokens per session scan A eac193527c51
graph-analyst is an agent published in the GitHub repository tonydzi/second-brain-starter-kit (12 stars, last pushed 3d ago), licensed MIT. It adds 61 tokens to every session and 414 once invoked, about $0.0002 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 2026-10-21.
Other agents, from other repositories
wiki-lint
Read-only interpreter for the deterministic portable vault linter. Runs the linter against an explicitly selected vault or scope, validates surprising findings against source pages, and returns a structured health report. It never writes reports or repairs the vault.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.