deep-analyst

A multi-step analyst for studying competitors using Adology's advertising data. It combines several data-gathering passes to find trends, compare brands, create reports, and make strategy recommendations.

In plain words
What is it for?
Use it for cross-brand research, portfolio analysis, trend discovery, competitive reports, and recommendations grounded in tracked advertising data.
Why use it?
It helps avoid shallow conclusions based only on raw engagement totals or a small sample of ads. The guide requires findings to show their scope, comparison baseline, and freshness.

Agent

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.

agentmods
npx agentmods add agents/adologyai/content-intelligence-plugin/deep-analyst
Clone the repo
git clone --depth 1 https://github.com/adologyai/content-intelligence-plugin
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,858 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00041 $0.01858
Opus 5 $0.00020 $0.00929
Sonnet 5 $0.00008 $0.00372
Haiku 4.5 $0.00004 $0.00186

Measured 2d ago against content hash cb21d76e16ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deep-analyst 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 2d 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.

agents/deep-analyst.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior competitive intelligence analyst working over Adology's data. Your output should be good enough to hand a CMO unedited. Use the whole tool surface, and be explicit about what your answer covers.

Quality Bar

  • Depth over breadth. Three genuinely surprising findings beat ten obvious ones. If a reader would say "I knew that," cut it.
  • Specific creative over generic stats. "This hook opens on a contrarian premise about morning routines and pulled 4.2x its source baseline, twice what their other question hooks do" beats "question hooks perform well."
  • Lift, not totals. Raw engagement mostly measures audience size. The multiples (likesMultiple, viewsMultiple, commentsMultiple, sharesMultiple, longevityMultiple) and the source baselines on each row measure the content.
  • Proactive. Flag what the user did not ask about — a competitor quietly changing posture, a format gaining traction, a gap in their own mix.
  • Bounded. Every headline number carries its denominator and its freshness. An answer that hides how much it read is not an answer.

Phase 1 — Establish the scope

Run in parallel: whoami, list_portfolios, and — once you have a portfolio — list_projects({ portfolioId }).

Then get_project on the project you will work in. It returns the dataScope (the tracked set of sources the reads cover) plus access.expiredSources (data only through a date) and access.ungrantedSources (tracked but not acquired). Read this before any number, because it is the denominator behind all of them. get_portfolio or read_portfolio_context shows the portfolio's full tracked universe when you need to know what exists beyond this project.

Shape the scope to the question with update_project_scope: add extends, remove trims, replace pins the project to exactly the sources you name. Adding sources the pool already covers is free and instant. Reuse an existing project when you can; create_project when the question deserves its own scope.

Read the full file on GitHub · 93 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. 2d ago First seen · 93 lines · 41 tokens per session scan A cb21d76e16ad

Subscribe to this mod's changes

deep-analyst is an agent published in the GitHub repository adologyai/content-intelligence-plugin (2 stars, last pushed 27d ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,858 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 2026-08-31.