Borrowing it
Nothing to install: this file belongs to fpt/go-dev-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fpt/go-dev-mcp/main/.claude/skills/verify-doc-parsing/SKILL.mdgit clone --depth 1 https://github.com/fpt/go-dev-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/fpt/go-dev-mcp/verify-doc-parsing)<a href="https://agentmods.dev/skills/fpt/go-dev-mcp/verify-doc-parsing"><img src="https://agentmods.dev/badge/skills/fpt/go-dev-mcp/verify-doc-parsing.svg" alt="Measured on agentmods" 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 | $0.00137 | $0.01811 |
| Opus 5 | $0.00068 | $0.00905 |
| Sonnet 5 | $0.00027 | $0.00362 |
| Haiku 4.5 | $0.00014 | $0.00181 |
Grade A, and why
verify-doc-parsing 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 8d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify dq-based Documentation Parsing
The go-dev-mcp server scrapes documentation sites (pkg.go.dev, docs.rs,
docs.python.org) by walking HTML with the pkg/dq package and matching on
specific CSS classes/IDs. Those selectors are brittle: if the site changes
its markup, the parser silently returns empty output and the golden tests
(which run against saved HTML) won't notice. This skill verifies the parsers
against the live site.
When to use which parser file
| Site | Parser | Key selectors to confirm |
|---|---|---|
| pkg.go.dev | internal/app/godoc.go |
div.Documentation, section.Documentation-*, div.Documentation-declaration > pre, span.Documentation-sinceVersion, div.SearchResults(-summary), div.SearchSnippet(-infoLabel), div.Overview-readmeContent |
| docs.rs | internal/app/rustdoc.go |
confirm from the file's dq.NewMatchFunc(...) calls |
| docs.python.org | internal/app/pydoc.go |
confirm from the file's dq.NewMatchFunc(...) calls |
Always derive the selector list from the code, not memory — grep it:
grep -n "NewMatchFunc\|hasClass\|NodeFilter\|Overview-readme\|Documentation-" internal/app/<parser>.go
Step-by-step
Phase 1: Extract what the parser expects
- Read the target parser (
internal/app/{godoc,rustdoc,pydoc}.go). List every selector passed todq.NewMatchFunc(...)and every class checked in customNodeFilterfunctions. These are your verification targets. - Note the page types the parser handles. For pkg.go.dev there are three:
- doc page (
parseDocument) — e.g.https://pkg.go.dev/golang.org/x/net/html - search page (
parseSearchResult) — e.g.https://pkg.go.dev/search?q=yaml - README page (
parseReadme) — e.g.https://pkg.go.dev/github.com/stretchr/testify
- doc page (
- Recall the dq traversal rule (see
pkg/dq/dq.goTraverse): an unmatched matcher propagates down to descendants. So aprematcher placed under adivmatcher still reaches a<pre>nested several levels deeper (e.g. insidediv.Documentation-declaration). Don't flag deep nesting as broken — verify the selector exists somewhere under the expected root.
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.
- 8d ago First seen · 160 lines · 137 tokens per session scan A 0a731edda890
verify-doc-parsing is a skill published in the GitHub repository fpt/go-dev-mcp (13 stars, last pushed 23d ago), licensed MIT. It adds 137 tokens to every session and 1,811 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
experimental-read-code-coverage-metrics
Retrieves and analyzes Chromium per-CL code coverage data from the Findit API. Records per-CL coverage metrics for all modified source files and extracts unexecuted code lines.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…