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 pranava0x0/Commonwealth-MCP --skill code-topic-walkgit clone --depth 1 https://github.com/pranava0x0/Commonwealth-MCPWrote 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/pranava0x0/commonwealth-mcp/code-topic-walk)<a href="https://agentmods.dev/skills/pranava0x0/commonwealth-mcp/code-topic-walk"><img src="https://agentmods.dev/badge/skills/pranava0x0/commonwealth-mcp/code-topic-walk/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/pranava0x0/commonwealth-mcp/code-topic-walk"><img src="https://agentmods.dev/badge/skills/pranava0x0/commonwealth-mcp/code-topic-walk.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 | $0.00107 | $0.01562 |
| Opus 5.5 | $0.00043 | $0.00625 |
| Sonnet 5.5 | $0.00021 | $0.00312 |
| Haiku 4.5 | $0.00011 | $0.00156 |
Grade A, and why
code-topic-walk 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 1mo ago.
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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code of Virginia, by topic
The publisher runs no full-text search operation. Its own search backend was down when this was checked, and its JSON API has no search at all. So a reader who says "what does Virginia law say about short-term rentals" cannot be answered by searching, and the two ways to fail here are equally bad: guessing a citation that sounds right, or answering the legal question from memory and dressing it in a section number afterwards.
What is available is the Code's own structure: titles, a title's chapters, a chapter's sections. That is a hierarchy a reader can be walked down, and each level's rows carry the arguments for the level below. This walk is that descent, and it states where the descent stopped.
1. Establish the frame
- A title is a subject area, and the mapping from a question to a title is the hard step. Local government is Title 15.2. Motor vehicles is 46.2. Crimes is 18.2. That mapping is knowledge about the Code's organisation, not about the law, and it is the one place this walk reasons rather than reads.
- A citation is
title-section, and the section number carries the chapter: 15.2-2200 is in Title 15.2, chapter 22. Reading that structure off a citation is how a caller who has one skips straight to the text. - Sections are repealed, renumbered, and added. A citation that is not found is a fact about the Code as published today, not an error, and the publisher redirects rather than returning a not-found status.
- The published text is the text. It is not the annotations, the case law, or the regulations promulgated under it, and none of those are here.
2. Minimum data walk
Step 1 — name candidate titles. From the subject, propose the titles that plausibly hold it, and say why each. Two or three, not one: a subject often sits in more than one, and land use touches both local-government authority and the enabling statutes for specific tools.
Step 2 — read the title list and check the names. Walk the contents from the top and read the titles as published. This is the step that catches a title that was renumbered or one that never existed under the name assumed. A title the Code does not have and a title with no chapters come back the same way, so say which question was asked.
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.
- 1mo ago First seen · 128 lines · 107 tokens per session scan A 96e5892985e7
code-topic-walk is a skill published in the GitHub repository pranava0x0/Commonwealth-MCP (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 107 tokens to every session and 1,562 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 2026-09-10.
Other skills, from other repositories
find-the-public-record
Find which public record actually settles a question about a local market or a specific property in any US metro, then go and read it. Use before researching a local market, and whenever a question is about a place outside the Twin Cities where no dataset is loaded.
korean-law
A legal research connection to South Korea's official law information service. It can retrieve statutes, court decisions, administrative rules, local ordinances, treaties, and legal interpretations, then check cited provisions against the source.
forthepeople-district-expansion
Skill for expanding ForThePeople.in to new districts. Use when adding Bengaluru Urban, Mysuru, or any new Indian district to the platform. Triggers: 'add district', 'expand to Bangalore', 'expand to Mysore', 'unlock district', 'new city', 'seed data for district', 'add Bengaluru', 'add Mysuru', 'district-specific…
indian-district-hierarchy
Complete Indian district administrative hierarchy for ForThePeople.in. Use this skill when building leadership pages, org charts, hierarchy visualizations, or seeding officer data for any Indian district. Triggers: 'district hierarchy', 'leadership org chart', 'who governs', 'district officers', 'tahsildar', 'block…
vendor-management
Manage ServiceNow vendors and contracts — corecompany vendor records, astcontract with renewal alerts, astcontractsla performance tracking, vendorriskassessment scoring, and vendor scorecards.
procure-quotazioni
Genera in serie procure alle liti (art. 83 c.p.c.) e lettere di quotazione compensi D.M. 55/2014 in DOCX per posizioni di recupero crediti, partendo da un Excel di posizioni o dai dati forniti, con rilevamento della fase processuale (monitorio, esecuzione forzata, opposizione a decreto ingiuntivo). Usa quando l'utente…