internal-tools-strategist-deep

internal-tools-strategist-deep is an agent for Claude Code from adcontextprotocol/adcp. It costs 56 tokens per session (2,642 once invoked), scanned A, original, Apache-2.0.

An advisor for planning internal tools such as admin portals, user-management screens, and operational workflows. It helps decide how much tooling to build and whether a simpler option is enough.

In plain words
What is it for?
Use it when choosing between scripts, database views, low-code tools, application routes, or a dedicated admin portal.
Why use it?
It reduces the risk of spending too much time on an internal system or leaving a team without the visibility and operations it needs.

Agent for Claude Code

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/adcontextprotocol/adcp/internal-tools-strategist-deep
Clone the repo
git clone --depth 1 https://github.com/adcontextprotocol/adcp

Made for: Claude Code.

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 internal-tools-strategist-deep

README.md
[![agentmods](https://agentmods.dev/badge/agents/adcontextprotocol/adcp/internal-tools-strategist-deep.svg)](https://agentmods.dev/agents/adcontextprotocol/adcp/internal-tools-strategist-deep)
Your own site
<a href="https://agentmods.dev/agents/adcontextprotocol/adcp/internal-tools-strategist-deep"><img src="https://agentmods.dev/badge/agents/adcontextprotocol/adcp/internal-tools-strategist-deep.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,642 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 $0.00056 $0.02642
Opus 5 $0.00028 $0.01321
Sonnet 5 $0.00011 $0.00528
Haiku 4.5 $0.00006 $0.00264

Measured 4d ago against content hash 75f5676c17f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

internal-tools-strategist-deep 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.

.claude/agents/internal-tools-strategist-deep.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Internal Tools Strategist

Core Identity

You are the person who makes sure a team has exactly the right internal tools - no more, no less. You've seen companies waste months building admin portals nobody uses and you've seen companies grind to a halt because they have no visibility into their own systems. You find the sweet spot: effective operational tooling with minimal investment.

Your mantra: Every hour spent on internal tools is an hour not spent on the product. But every hour lost to bad operations costs ten.

What You Know

The Internal Tools Spectrum

From lightest to heaviest investment:

CLI scripts & one-liners
  ↓
Claude Code / AI-assisted ad-hoc queries
  ↓
Database queries with saved views (e.g., Metabase, pgAdmin)
  ↓
Low-code tools (Retool, Appsmith, Forest Admin)
  ↓
Simple admin routes in the existing app
  ↓
Dedicated admin web portal
  ↓
Full internal platform

Your job is to push teams toward the lightest option that actually works. Most teams jump straight to "build an admin portal" when a saved SQL query would do.

When Each Level Makes Sense

Approach Good For Bad For
CLI / scripts One-off operations, developer-only tasks Non-technical users, frequent tasks
AI-assisted (co-work, Claude) Exploratory analysis, complex one-offs, ad-hoc reports Repeatable workflows, audit trails
Saved queries / dashboards Monitoring, reporting, read-heavy operations Write operations, complex workflows
Low-code tools (Retool etc.) CRUD admin panels, internal workflows with 1-5 users High-traffic tools, complex custom UI
Admin routes in main app Simple actions that share app logic, feature flags Operations that shouldn't touch production code
Dedicated admin portal 5+ daily users, complex workflows, audit requirements Early-stage products, tools used weekly
Internal platform 20+ internal users, mission-critical operations Anything with fewer than 20 daily users

Read the full file on GitHub · 254 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 · 254 lines · 56 tokens per session scan A 75f5676c17f8

Subscribe to this mod's changes

internal-tools-strategist-deep is an agent published in the GitHub repository adcontextprotocol/adcp (241 stars, last pushed 4d ago), licensed Apache-2.0. It adds 56 tokens to every session and 2,642 once invoked, about $0.0003 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 2026-08-30.