local-first-search

local-first-search is a skill for Claude Code, Codex from monkey1wizard/Golem-Agents-Legion. It costs 42 tokens per session (698 once invoked), scanned A, original, MIT.

A repository-first search strategy for answering questions and planning work. It checks source code, tests, documentation, and repository notes before using optional external notes.

In plain words
What is it for?
Use it before explaining concepts, proposing solutions, or planning work related to project notes and local context.
Why use it?
It prevents generic answers that ignore the project's existing decisions and conventions. It also keeps external note systems optional rather than assuming a particular app or setup.

Skill for Claude CodeCodex

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

Good fit Use it before explaining concepts, proposing solutions, or planning work related to project notes and local context.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/monkey1wizard/golem-agents-legion/local-first-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 monkey1wizard/Golem-Agents-Legion --skill local-first-search
Clone the repo
git clone --depth 1 https://github.com/monkey1wizard/Golem-Agents-Legion

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 local-first-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/monkey1wizard/golem-agents-legion/local-first-search/github.svg)](https://agentmods.dev/skills/monkey1wizard/golem-agents-legion/local-first-search)
Your own site
<a href="https://agentmods.dev/skills/monkey1wizard/golem-agents-legion/local-first-search"><img src="https://agentmods.dev/badge/skills/monkey1wizard/golem-agents-legion/local-first-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 local-first-search

Your own site · 80×15
<a href="https://agentmods.dev/skills/monkey1wizard/golem-agents-legion/local-first-search"><img src="https://agentmods.dev/badge/skills/monkey1wizard/golem-agents-legion/local-first-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 698 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 $0.00042 $0.00698
Opus 5 $0.00021 $0.00349
Sonnet 5 $0.00008 $0.00140
Haiku 4.5 $0.00004 $0.00070

Measured 4d ago against content hash d6ed116a5941, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

local-first-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 4d 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.

plugins/gal-core/skills/local-first-search/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Local-First Search Strategy

Core Philosophy

Context first, local first means: before answering conceptual questions, proposing solutions, or planning note-adjacent work, search repo-owned material first.

Avoid generic answers that ignore existing local context.

Search Order

Use this order unless the user explicitly asks for a different source:

  1. codebase

    • source files
    • comments
    • tests
    • adjacent call sites
  2. docs

    • docs/
    • plan documents
    • workflow and convention docs
  3. repo text artifacts

    • .dev/
    • configuration files
    • notes stored in the repo itself
  4. optional external notes

    • only after the first three lanes are insufficient
    • only when the local-notes optional-capability lane is ready

Optional local-notes Lane

When repo-local retrieval is insufficient, consult the local-notes contract in optional-capabilities.md, with operational setup in docs/manual.md and docs/integrations.md.

Rules:

  • treat external notes as optional additional evidence, not a Core prerequisite
  • do not assume any specific note application, vault shape, diary ritual, or personal taxonomy
  • do not assume semantic search exists
  • if local-notes is not ready, degrade silently to repo-local retrieval only

Execution Workflow

Phase 1 — Codebase Search

  • search the owning code path first
  • prefer exact text or symbol search for known identifiers
  • read the minimum surrounding context needed to answer accurately

Phase 2 — Docs Search

  • search durable docs and plan files relevant to the question
  • use conventions and workflow docs when the question is about process or contract behavior

Phase 3 — Repo Artifact Search

  • search .dev/, repo-local notes, and tracked config surfaces when they carry task context
  • keep repo-owned state ahead of any private note system

Phase 4 — Optional External Notes

Read the full file on GitHub · 95 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. 4d ago First seen · 95 lines · 42 tokens per session scan A d6ed116a5941

Subscribe to this mod's changes

local-first-search is a skill published in the GitHub repository monkey1wizard/Golem-Agents-Legion (15 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 698 once invoked, about $0.0002 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 2026-09-04.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens