search-first

search-first is a skill for Claude Code, Codex from jxoesneon/Ciel. It costs 35 tokens per session (847 once invoked), scanned A, original, Apache-2.0.

A research-first workflow for checking existing libraries, services, and project solutions before writing new code.

In plain words
What is it for?
Use it at the start of non-trivial implementation work to compare existing options, choose whether to adopt or extend them, and plan dependency changes.
Why use it?
It reduces duplicated work and avoids adding custom code when a suitable, maintained solution already exists. New dependencies still require human confirmation.

Skill for Claude CodeCodex

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

Good fit Use it at the start of non-trivial implementation work to compare existing options, choose whether to adopt or extend them, and plan dependency changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jxoesneon/ciel/search-first
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 jxoesneon/Ciel --skill search-first
Clone the repo
git clone --depth 1 https://github.com/jxoesneon/Ciel

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 search-first

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jxoesneon/ciel/search-first"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/search-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 847 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 $0.00035 $0.00847
Opus 5 $0.00017 $0.00424
Sonnet 5 $0.00007 $0.00169
Haiku 4.5 $0.00003 $0.00085

Measured 9d ago against content hash a3eccceba1ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

search-first 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 9d 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.

skills/search-first/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CIEL ADAPTATION: Search-First (Research Mandate)

This skill operationalizes CIEL's core "Research-Before-Strategy" mandate. It acts as a hard gate preventing the premature generation of net-new code when robust, maintained solutions already exist in the ecosystem, the repository, or via MCP servers.

Integration Context

Adapted from ~/.agents/skills/search-first/. This skill heavily influences the Strategy Layer (specifically the make-plan skill). It dictates that the initial phase of any non-trivial implementation MUST be a dedicated research turn.

The Search-First Decision Matrix

Before proposing a custom implementation, agents must evaluate existing solutions against this matrix:

Signal / Finding Required Action
Exact match, well-maintained, MIT/Apache Adopt: Propose installation. REQUIRE HUMAN CONFIRMATION before modifying package files. Do not wrap unnecessarily.
Partial match, strong foundation Extend: Propose installation. REQUIRE HUMAN CONFIRMATION. Write a thin, specific wrapper.
Multiple weak matches Compose: Combine small packages. REQUIRE HUMAN CONFIRMATION for all new dependencies.
Nothing suitable found Build: Write custom code, informed by the research phase.

Orchestration Workflow

When triggered, execute the following workflow:

  1. Need Analysis: Define the exact constraints (language, framework, license).
  2. Local Context Search:
    • Use grep_search and glob to verify the functionality doesn't already exist in the repo.
    • Check available MCP servers (e.g., via cli_help or direct MCP tool listing).
  3. Ecosystem Search:
    • If internet tools (like google_web_search or exa-search) are available, search the relevant package manager (npm, PyPI, crates.io).
    • Evaluate community trust, download counts, and recent update activity to mitigate supply chain risks.
  4. Evaluate & Decide: Score candidates and apply the Decision Matrix.
  5. Documentation (Evolution): If a new external dependency is adopted, the agent MUST document the rationale, version, and alternatives considered in the project's architectural log (e.g., ARCHITECTURE.md) or via memory.

Read the full file on GitHub · 69 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. 9d ago First seen · 69 lines · 35 tokens per session scan A a3eccceba1ed

Subscribe to this mod's changes

search-first is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 5d ago), licensed Apache-2.0. It adds 35 tokens to every session and 847 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 2026-09-03.

Related

Other skills, from other repositories

surge

Use when a user provides a PRD, spec, or detailed requirements document and needs a full project delivered through iterative expert orchestration — multi-round analyze/research/design/implement/QA cycles with convergence detection. NOT for: single-file edits, quick prototypes, simple Q&A, or tasks without a written…

carbonshow/intent-fluid · 66 tokens

ai-native-software-dev

Use when the user asks to build, change, modernize, or reconstruct non-trivial software with an AI-native workflow, including greenfield development, work in an existing codebase, or authorized reference-based product reconstruction; also use when lifecycle planning, architecture, implementation, testing, review…

carbonshow/intent-fluid · 101 tokens

ticket-spec

Turn a raw Linear Triage ticket into a fully specified ai:agent-ready one by exploring the codebase. Use when specifying, refining, or promoting tickets, or when asked why a ticket isn't dispatchable.

watt-mind/factory · 45 tokens

Code Quality Review

Conduct a comprehensive code quality review focused on clean code, architecture, and project standards.

asap-protocol/asap-protocol · 21 tokens

redpolicy-guide

An editorial policy for turning webinar transcripts into self-contained guides. A transcript is a written record of spoken material, while a self-contained guide can be understood without watching the webinar.

mikeshu2001/content-factory · 49 tokens

write-overview

A workflow for researching and writing a review essay about a project topic when no finished source text exists. It gathers the facts, studies example essays when available and produces the article in a project output folder.

mikeshu2001/content-factory · 17 tokens