A project-documentation search skill for Markdown files, such as README files and documents in docs/. It builds a searchable index so you can find relevant passages by exact, partial, or similar wording.

Use it to answer questions about how a project works, find where a rule is documented, view documentation statistics, or generate a browsable map of the knowledge base.

It avoids searching files one by one and helps locate the project's documented source of truth before making decisions.

kb-search — Skill for Claude Code by vakovalskii

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add vakovalskii/ontoship

Claude Code

/plugin install ontoship

Made for: Claude Code.

Or install ontoship, the plugin that ships this one along with the rest of its 3 skills, 5 commands.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vakovalskii/ontoship/kb-search/github.svg)](https://agentmods.dev/skills/vakovalskii/ontoship/kb-search)

Your own site

<a href="https://agentmods.dev/skills/vakovalskii/ontoship/kb-search"><img src="https://agentmods.dev/badge/skills/vakovalskii/ontoship/kb-search/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vakovalskii/ontoship/kb-search"><img src="https://agentmods.dev/badge/skills/vakovalskii/ontoship/kb-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 654 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00097	$0.00654
Opus 5	$0.00048	$0.00327
Sonnet 5	$0.00019	$0.00131
Haiku 4.5	$0.00010	$0.00065

Measured 11d ago against content hash 260c2a2c0f91, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

kb-search 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (gitmark.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/kb-search/SKILL.md · 51 lines

What it actually says

GitMark — knowledge-base search

This plugin treats the repo's markdown as a md + README(index) + git knowledge base. Markdown is the source of truth; the search index and HTML map are derived and regenerated from md (.gitmark/ is gitignored). The CLI is pure Python stdlib.

Script: ${CLAUDE_PLUGIN_ROOT}/skills/kb-search/gitmark.py (when run as a project-local copy, it's .claude/skills/kb-search/gitmark.py).

When to use

You need to find where something is documented → gitmark search, not a grep/rg fan-out. Results are file:line · heading · snippet.
"How does X work here", "where are the docs for Y".
Before reading files at random — locate the exact spots first.
Want an overview/graph of the KB → gitmark map.

Commands

G="python3 ${CLAUDE_PLUGIN_ROOT:-.claude/plugins/gitmark}/skills/kb-search/gitmark.py"

$G index                 # (re)build .gitmark/index.db  (fast)
$G search "<query>"      # bm25 + trigram(substring) + fuzzy(3-gram); -k N, --json
$G map -o docs-map.html  # self-contained HTML: tree + rendered md + radial graph
$G serve -p 8799         # local http server to view the map
$G stat                  # files/chunks/links/index state
$G lint [paths…]         # ontology check (frontmatter/links/README/broken links)
$G version

Workflow

If the index may be stale (docs changed) → gitmark index.
gitmark search "<terms>" — typos and morphology are tolerated (trigram/fuzzy). [bm25] = exact term, [trigram] = substring, [fuzzy] = n-gram (typos/forms).
Open the returned file:line and read the exact place.
--json for machine-readable results.

Principles

Markdown is the source of truth. Edit knowledge in .md, never the index.
Don't commit .gitmark/ (it's in .gitignore).
Index is a cache — if results look stale, rebuild with gitmark index --force.
How to maintain the KB (ontology, file placement) — see the kb-curate skill.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

gitmark.py 45 KB runs code

Changes

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.

11d ago First seen · 51 lines · 97 tokens per session scan A 260c2a2c0f91

Subscribe to this mod's changes

kb-search is a skill published in the GitHub repository vakovalskii/ontoship (77 stars, last pushed 15d ago), licensed MIT. It adds 97 tokens to every session and 654 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 2026-08-30.

Research

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens