private-repo-search

private-repo-search is a skill for Claude Code, Codex from patrickserrano/lacquer. It costs 75 tokens per session (749 once invoked), scanned A, original, MIT.

A search tool for finding code, file names, and past implementations across GitHub repositories you can access, including private repositories. It uses GitHub's command-line tool and can narrow results by owner, repository, language, or file.

In plain words
What is it for?
Use it to find a function's uses across an organisation, locate configuration examples, or compare how other repositories solve a problem.
Why use it?
A normal search only checks the repository currently checked out on your computer. This helps when the example or shared code you need is stored somewhere else.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to find a function's uses across an organisation, locate configuration examples, or compare how other repositories solve a problem.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/patrickserrano/lacquer/private-repo-search
Install

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.

Any agent
npx skills add patrickserrano/lacquer --skill private-repo-search
Clone the repo
git clone --depth 1 https://github.com/patrickserrano/lacquer

Made for: Claude Code, Codex.

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.

agentmods badge for private-repo-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/patrickserrano/lacquer/private-repo-search/github.svg)](https://agentmods.dev/skills/patrickserrano/lacquer/private-repo-search)
Your own site
<a href="https://agentmods.dev/skills/patrickserrano/lacquer/private-repo-search"><img src="https://agentmods.dev/badge/skills/patrickserrano/lacquer/private-repo-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.

agentmods 80×15 button for private-repo-search

Your own site · 80×15
<a href="https://agentmods.dev/skills/patrickserrano/lacquer/private-repo-search"><img src="https://agentmods.dev/badge/skills/patrickserrano/lacquer/private-repo-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 749 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00075 $0.00749
Opus 5 $0.00037 $0.00375
Sonnet 5 $0.00015 $0.00150
Haiku 4.5 $0.00007 $0.00075

Measured 10d ago against content hash 2edc9b98bfe0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

private-repo-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 10d 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.

core/skills/private-repo-search/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gh search code — GitHub's code search API through the CLI you already have authenticated, scoped to exactly the repos/orgs you need instead of a raw gh api call.

Prerequisites

Requires the gh CLI installed.

gh auth status  # confirm authenticated; code search needs no extra scope beyond default

Core usage

gh search code <query> [flags]
Flag Use for
--owner <org-or-user> Scope to everything an org/user owns
--repo <owner/name> (repeatable) Scope to specific repo(s)
--language <lang> Filter by language
--filename <name> Filter by filename (e.g. package.json)
--extension <ext> Filter by file extension
--match file|path Restrict the match to file contents or the path itself
--json path,repository,sha,textMatches,url + -q <jq-expr> Structured output for scripting
-L, --limit <n> Result cap (default 30)
# Find where a symbol is used across every repo in an org
gh search code "someFunctionName" --owner patrickserrano

# Narrow to specific repos and a language
gh search code "RLSPolicy" --repo patrickserrano/harness --language go

# Find a config file by name across everything you can see
gh search code --filename .lacquer.toml

# Machine-readable output for a downstream step
gh search code "TODO(migration)" --owner patrickserrano --json path,repository,url -q '.[] | "\(.repository.nameWithOwner): \(.path)"'

After finding a hit

gh search code returns matched paths, not full file content. Fetch the actual content once you know the repo and path:

gh api repos/<owner>/<repo>/contents/<path> --jq '.content' | base64 -d
# or, simpler for a quick look:
gh api repos/<owner>/<repo>/contents/<path> -H "Accept: application/vnd.github.raw" 

Caveats

  • Results lag behind pushes. The index isn't real-time — a just-pushed commit may not show up for a few minutes.
  • Legacy search engine. gh search code uses GitHub's older code-search API, not the newer engine github.com's web UI uses — results and available qualifiers (no regex) can differ from what you'd see in the browser.
  • Scope is "everywhere gh can see." A search with no --owner/--repo filter that returns nothing from a private repo you expect usually means an auth/visibility gap, not that the content isn't there — check gh auth status and repo access before concluding a miss is real.

Read the full file on GitHub · 78 lines

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.

  1. 10d ago First seen · 78 lines · 75 tokens per session scan A 2edc9b98bfe0

Subscribe to this mod's changes

private-repo-search is a skill published in the GitHub repository patrickserrano/lacquer (3 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 749 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

printing-press-amend

Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…

mvanhorn/cli-printing-press · 222 tokens

printing-press-score

Score a generated CLI against the Steinberger bar, compare two CLIs side-by-side.

mvanhorn/cli-printing-press · 22 tokens

printing-press-output-review

Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…

mvanhorn/cli-printing-press · 102 tokens

printing-press

Set up a new integration, connector, or CLI binding for any API. Wrap or generate a ship-ready Go CLI from an OpenAPI, HAR, or Postman spec via the lean research -> generate -> build -> shipcheck loop. Use when the user says build a CLI, wrap this API, set up a new integration, add a connector, integrate with a…

mvanhorn/cli-printing-press · 86 tokens

gograph

Go repository intelligence for Claude Code. Use when reading, navigating, editing, reviewing, or refactoring a Go codebase. Exposes 64 query, analysis, and workflow capabilities through the local gograph MCP server, including bounded first-call exploration, AST-aware call graphs, blast-radius analysis, impact, and…

ozgurcd/gograph · 69 tokens

performance

A guide to measuring and improving the speed and resource use of Go programs. It explains benchmarks and profiling, which records where a program spends time or memory.

Insajin/autopus-adk · 19 tokens