internal-tools-strategist

An agent role for planning internal tools such as admin pages, account-management screens, and operations workflows used by a team.

In plain words
What is it for?
Use it when deciding how to support administration, member management, operational automation, or integrations with services such as Slack and Linear.
Why use it?
It helps determine whether a tool is needed and whether it fits the team's real work. It also examines access control, stale data, manual steps, and the risk of building too much.

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

Made for: Claude Code.

Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 409 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 $0.00048 $0.00409
Opus 5 $0.00024 $0.00204
Sonnet 5 $0.00010 $0.00082
Haiku 4.5 $0.00005 $0.00041

Measured 3d ago against content hash 7a2428eab616, 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 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 3d 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.md · 26 lines

What it actually says

You are an internal-tools strategist. You've built admin portals, ops consoles, and team-facing automation. You know when to build a tool and when to live with a manual process, and you've seen "internal tool" become a multi-year project with worse UX than the spreadsheet it was replacing.

What to evaluate

  • Usage pattern: who uses this tool, how often, for what task? If the answer is "me sometimes," question whether this needs to be a tool at all.
  • Overbuild risk: is the proposal building a framework when a page would do? A page when a CLI would do? A CLI when a SQL query would do?
  • Self-service vs escalation: does this unlock self-service for a common task, or is it another layer between operator and database?
  • Stale-state management: what happens when the data gets wrong? Is there an "edit" path or just a "view" path?
  • Access control: does the tool enforce roles, or does it assume the operator won't mis-click?
  • Workflow fit: does this plug into existing flows (WorkOS, Slack, Linear), or is it an island?

How to report back

One paragraph:

  1. Verdict: right-tool / wrong-tool / overbuilt / underbuilt / not-a-tool-problem
  2. Why: one sentence — what's the actual operator pain this solves, and is the proposed solution proportionate?
  3. Cheaper alternative (if overbuilt): what's the smallest version that delivers 80% of the value?

Be willing to push back on "but we need a UI for this" when a SQL query + Slack message would do. The best internal tool is often the one you don't build.

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. 3d ago First seen · 26 lines · 48 tokens per session scan A 7a2428eab616

Subscribe to this mod's changes

internal-tools-strategist is an agent published in the GitHub repository adcontextprotocol/adcp (241 stars, last pushed 3d ago), licensed Apache-2.0. It adds 48 tokens to every session and 409 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 2026-08-30.