interlateral_agents: Skill for Claude Code

.agent/skills/search-synth/SKILL.md

search-synth is a skill for Claude Code, Codex from dazzaji/interlateral_agents. It costs 18 tokens per session (1,998 once invoked), scanned A, original, Apache-2.0.

A multi-agent web-research workflow that checks findings against one another and produces a combined report of verified information.

In plain words
What is it for?
Use it to investigate a topic on the web, cross-check evidence, and write a synthesized research result to a specified file.
Why use it?
Independent searches and fact-checking can expose unsupported claims or errors that a single search might miss. It requires the participating agents and their search abilities to be named.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Codex; mentions Gemini CLI.

This is dazzaji/interlateral_agents's own configuration. It tells Claude Code and Codex how to work on interlateral_agents itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything interlateral_agents configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dazzaji/interlateral_agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dazzaji/interlateral_agents/main/.agent/skills/search-synth/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dazzaji/interlateral_agents

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-synth

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/dazzaji/interlateral_agents/search-synth"><img src="https://agentmods.dev/badge/skills/dazzaji/interlateral_agents/search-synth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,998 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 $0.00018 $0.01998
Opus 5.5 $0.00007 $0.00799
Sonnet 5.5 $0.00004 $0.00400
Haiku 4.5 $0.00002 $0.00200

Measured 1mo ago against content hash 957b2543b7f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

search-synth 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 1mo 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.

.agent/skills/search-synth/SKILL.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Search-Synth: Multi-Agent Research with Fact-Checking

Purpose

Conduct thorough web research on a topic using multiple agents, cross-verify findings through fact-checking, and produce a synthesized "Best and Verified" response.

Required Inputs

Parameter Description
topic The research question or subject to investigate.
output_file File path where the synthesized result will be written.
agents Explicit list of participating agents, with each agent's search capability noted (see below).

Agent Roster and Search Capability

The invoker must declare which agents will participate and confirm which ones have web-search capability. Example:

agents:
  - name: CC
    role: MANAGER
    can_search: false
  - name: Codex
    role: SEARCHER
    can_search: true
    search_tool: <declared web-search tool>
  - name: Codex-peer-02
    role: SEARCHER
    can_search: true
    search_tool: <declared web-search tool>

Default roster: use Claude Code and Codex peers. Gemini CLI, Antigravity CLI, and Antigravity Desktop may participate only when the human explicitly selects them for this search run. Do not add them merely because they have a helper or search capability.

Pre-flight Check (Mandatory)

Before starting any phase, MANAGER must verify the roster:

  1. At least two agents must have can_search: true.
  2. At least one agent must be designated MANAGER (the MANAGER does not search).
  3. A CHIEF_AUTHOR must be designated (defaults to MANAGER if not specified).

If the roster cannot satisfy search requirements -- for example, no agent has web search, or fewer than two searchers are available -- STOP immediately and report the mismatch. Do not improvise, simulate, or pretend to search.

Roles

Role Responsibilities
MANAGER Orchestrates phases, assigns tasks, does NOT search.
SEARCHER Uses its declared search tool to research, writes expository response, fact-checks peers.
CHIEF_AUTHOR Writes the final "Best and Verified" synthesis. Defaults to MANAGER; can be reassigned.

Read the full file on GitHub · 261 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. 1mo ago First seen · 261 lines · 18 tokens per session scan A 957b2543b7f1

Subscribe to this mod's changes

search-synth is a skill published in the GitHub repository dazzaji/interlateral_agents (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 18 tokens to every session and 1,998 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-03.

Related

search-synth compared with skills from other repositories

search-synth next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
search-synthdazzaji/interlateral_agentsSkill1110d agoApache-2.0A18Claude Code, Codex
imagegenopenai/codexSkill133ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex