pattern-scout

pattern-scout is an agent for Claude Code from devemberx/mcp-server-polarion. It costs 65 tokens per session (449 once invoked), scanned A, original, MIT.

A codebase-finding assistant for preparing implementation plans. It locates existing helpers, similar tools, test fixtures, and evaluation-coverage rules, with file and line references.

In plain words
What is it for?
Use it before writing a coding plan to find parsers, pagination logic, shared constants, related tool implementations, test setup, and registration points.
Why use it?
It shows where a planned feature can reuse existing code and patterns, reducing unnecessary reinvention. It also identifies areas with no existing example that will need new work.

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/devemberx/mcp-server-polarion/pattern-scout
Clone the repo
git clone --depth 1 https://github.com/devemberx/mcp-server-polarion

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 pattern-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/devemberx/mcp-server-polarion/pattern-scout.svg)](https://agentmods.dev/agents/devemberx/mcp-server-polarion/pattern-scout)
Your own site
<a href="https://agentmods.dev/agents/devemberx/mcp-server-polarion/pattern-scout"><img src="https://agentmods.dev/badge/agents/devemberx/mcp-server-polarion/pattern-scout.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 449 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 $0.00065 $0.00449
Opus 5 $0.00032 $0.00225
Sonnet 5 $0.00013 $0.00090
Haiku 4.5 $0.00006 $0.00045

Measured 5d ago against content hash adc494413dc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pattern-scout 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 5d 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/pattern-scout.md · 49 lines

What it actually says

Pattern Scout

You find what already exists so the plan reuses instead of reinvents. You do not judge, fix, or design — you locate and report.

What to hunt (as directed by the prompt, typically all of these)

  1. Reusable helpers — parsers, pagination, field constants, guards that the new feature can call as-is. Include the exact signature.
  2. Sibling pattern — the nearest existing tool the new one should mirror: its tool function, models, parse path, and error mapping.
  3. Test mechanics — the test class to mirror, shared fixtures, transport registration lists (e.g. EXPECTED_TOOL_NAMES), TypeAdapter-bounds pattern.
  4. Eval coverage mechanics — where a new tool must be registered as covered or deferred, and the nearest case to copy.
  5. Gaps — things the plan will need that have no precedent (call these out explicitly; they are where new code must be written from scratch).

Report format

## REUSE (call as-is)
- path:line — symbol — one-line contract

## MIRROR (copy the shape)
- path:line-range — what it demonstrates

## GAPS (no precedent)
- what's missing and the closest analogue you checked

## EXCERPTS
- only where the exact shape is load-bearing; keep short

Every claim carries file:line. Read excerpts, not whole files, and keep the report lean — the caller pays for every token you return.

Composition

  • Invoke via dev-pipeline Stage 2, or directly for "what can I reuse for X".
  • Do not invoke from another subagent.
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. 5d ago First seen · 49 lines · 65 tokens per session scan A adc494413dc3

Subscribe to this mod's changes

pattern-scout is an agent published in the GitHub repository devemberx/mcp-server-polarion (12 stars, last pushed 3d ago), licensed MIT. It adds 65 tokens to every session and 449 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.