ClawHub

Nm Tome Code Search

v1.0.0

Search GitHub for existing code implementations, libraries, and patterns related to a given topic or query.

⭐ 0· 87·1 current·1 all-time
by@athola

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for athola/nm-tome-code-search.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Nm Tome Code Search" (athola/nm-tome-code-search) from ClawHub.
Skill page: https://clawhub.ai/athola/nm-tome-code-search
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install nm-tome-code-search

ClawHub CLI

Package manager switcher

npx clawhub@latest install nm-tome-code-search
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (search GitHub for implementations) aligns with the instructions: build search queries, run web searches, parse and rank GitHub results, and optionally call the GitHub API. There are no unrelated environment variables, binaries, or install steps demanded by the skill. (Minor note: the SKILL.md lists an upstream project and a different internal version string than the registry entry, which is a provenance/metadata inconsistency but not a security mismatch.)
✓
Instruction Scope
The SKILL.md only instructs the agent to construct queries, run WebSearch, parse results, optionally use the GitHub API for richer metadata, rank findings, and return results. It does not instruct the agent to read local files, other environment variables, system paths, or send data to unexpected endpoints.
✓
Install Mechanism
There is no install spec and no code files — this is instruction-only. Nothing is downloaded or written to disk by the skill itself, so install-risk is minimal.
ℹ
Credentials
The skill declares no required environment variables, which is coherent for a web-search-based GitHub lookup. However, SKILL.md mentions optional use of the GitHub API; using that in practice would typically require providing a GitHub token. The skill does not declare or request such a credential up front, so if the agent or user later supplies a token, be aware of the scope and exposure of that credential.
✓
Persistence & Privilege
always:false (default) and no special persistence or cross-skill config changes are requested. Autonomous invocation is allowed (the platform default) but the skill itself has no elevated or persistent privileges.
Assessment
This is an instruction-only GitHub code-search helper and appears internally consistent. It performs web searches and parses GitHub results — no files or secrets are requested by default. If you or your agent choose to enable the optional GitHub API calls, you may need to supply a GitHub token; only provide a token with the minimum scopes necessary and be aware of where it is stored. Also note the skill references an upstream repo (claude-night-market/tome); if provenance matters, review that upstream project before installing.

Like a lobster shell, security has layers — review code before you run it.

latestvk971cnbx69sc9w5239c4dv8p7h858s8g
87downloads
0stars
1versions
Updated 1w ago
v1.0.0
MIT-0
@athola
latest
Download

Night Market Skill — ported from claude-night-market/tome. For the full experience with agents, hooks, and commands, install the Claude Code plugin.

Code Search

When To Use

  • Finding existing implementations or libraries on GitHub
  • Part of a /tome:research session or standalone search

When NOT To Use

  • Searching local codebase (use Grep or Explore agent)
  • Academic literature (use /tome:papers)

Search GitHub for implementations of a given topic.

Usage

Invoked as part of /tome:research or standalone.

Workflow

  1. Build search queries using tome.channels.github.build_github_search_queries()
  2. Execute queries via WebSearch
  3. Parse results via parse_github_result()
  4. Optionally use GitHub API via build_github_api_search() for richer metadata
  5. Rank via rank_github_findings()
  6. Return Finding objects

Comments

Loading comments...