sdd-scout

sdd-scout is an agent for Claude Code from GregorBiswanger/featherspec. It costs 43 tokens per session (261 once invoked), scanned A, original, MIT.

A specialised coding agent for one step of an architecture review workflow. It reads a planned work item and writes a report about the repository's structure.

In plain words
What is it for?
It is for examining one worklist item at a time and saving its findings in the project's architecture-scan report folder.
Why use it?
It keeps architecture analysis focused and repeatable while avoiding changes to the codebase or other side effects.

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/gregorbiswanger/featherspec/sdd-scout
Clone the repo
git clone --depth 1 https://github.com/GregorBiswanger/featherspec

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 sdd-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/gregorbiswanger/featherspec/sdd-scout.svg)](https://agentmods.dev/agents/gregorbiswanger/featherspec/sdd-scout)
Your own site
<a href="https://agentmods.dev/agents/gregorbiswanger/featherspec/sdd-scout"><img src="https://agentmods.dev/badge/agents/gregorbiswanger/featherspec/sdd-scout.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 261 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 $0.00043 $0.00261
Opus 5 $0.00022 $0.00130
Sonnet 5 $0.00009 $0.00052
Haiku 4.5 $0.00004 $0.00026

Measured 4d ago against content hash 05a8c97d82a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdd-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 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/sdd-scout.md · 19 lines

What it actually says

You are the architecture scout for this repository's /sdd-architecture-scan workflow. You analyze exactly one worklist unit per invocation; the delegation message carries the unit, the report path, the schema and DocLanguage — follow it precisely. Analyze by reading and searching only — run no commands and build nothing: the scan must stay reproducible and side-effect-free, and command verification is Phase C's gated job. Write only inside .sdd-scan/reports/. If your unit is too large or incoherent for one honest report, return a structural note plus proposed child units instead of a shallow report. Return at most five summary 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 · 19 lines · 43 tokens per session scan A 05a8c97d82a8

Subscribe to this mod's changes

sdd-scout is an agent published in the GitHub repository GregorBiswanger/featherspec (45 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 261 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.