scout-writer

scout-writer is a skill for Claude Code, Codex from DojoGenesis/mcp. It costs 61 tokens per session (2,420 once invoked), scanned A, original, MIT.

A structured way to explore an important engineering decision before choosing a direction. It maps the main tension, lays out three to five options with tradeoffs, and recommends a next step.

In plain words
What is it for?
Use it to compare architecture or design options, prepare the reasoning for a technical specification, or inform an ADR, a written record of an engineering decision.
Why use it?
It helps teams avoid committing to an approach before they understand the choices and consequences. It turns an unclear question into a reasoned decision.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: model in frontmatter.

Good fit Use it to compare architecture or design options, prepare the reasoning for a technical specification, or inform an ADR, a written record of an engineering decision.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dojogenesis/mcp/scout-writer
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.

Any agent
npx skills add DojoGenesis/mcp --skill scout-writer
Clone the repo
git clone --depth 1 https://github.com/DojoGenesis/mcp

Made for: Claude Code, Codex.

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 scout-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/dojogenesis/mcp/scout-writer.svg)](https://agentmods.dev/skills/dojogenesis/mcp/scout-writer)
Your own site
<a href="https://agentmods.dev/skills/dojogenesis/mcp/scout-writer"><img src="https://agentmods.dev/badge/skills/dojogenesis/mcp/scout-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,420 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00061 $0.02420
Opus 5 $0.00030 $0.01210
Sonnet 5 $0.00012 $0.00484
Haiku 4.5 $0.00006 $0.00242

Measured 7d ago against content hash 11d2d4aa5049, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

scout-writer 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 7d 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.

internal/skills/bundled/dojo-craft/scout-writer/SKILL.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scout Writer Skill

I. Philosophy

A scout does not arrive with a solution. A scout arrives with a map.

The most expensive engineering decisions are the ones made before the terrain was understood. A well-written scout document is the cheapest possible way to stress-test a direction before committing resources. It costs an hour of careful thinking and saves days or weeks of course-correction.

The scout is not neutral. The scout has a point of view — grounded in evidence, stated explicitly, open to reframe. "Here are some options" is not scouting. Scouting is: "Here is the landscape, here is what I see in it, here is where I would go and why — and here is what would change my mind."

II. When to Use

  • Before committing to an architectural direction with significant consequences
  • When a team is stuck between competing legitimate approaches
  • Before writing a specification — the scout produces the "why" that the spec translates into "what"
  • When the question is "which direction?" not "how do we implement this direction?"
  • As input to the adr-writer skill when the decision warrants formal recording

Do not use this skill when the direction is already decided and the question is implementation. Scouting a decided question wastes time and introduces doubt where certainty is needed.

III. Workflow

Step 1: TENSION

Frame the situation as a tension between competing forces — not a problem to solve, but a landscape to navigate.

A tension statement has the form: "[Force A] vs. [Force B]" with a brief explanation of why both forces are legitimate and why they pull in different directions.

Examples:

  • "Velocity vs. coherence: shipping fast risks architectural drift, but slowing down to audit means missing the grant deadline."
  • "Simplicity vs. extensibility: a single-file solution ships today but cannot accommodate the multi-tenant requirement arriving in Q3."
  • "Build vs. buy: the existing library covers 80% of the need but the missing 20% is load-bearing."

Read the full file on GitHub · 219 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. 7d ago First seen · 219 lines · 61 tokens per session scan A 11d2d4aa5049

Subscribe to this mod's changes

scout-writer is a skill published in the GitHub repository DojoGenesis/mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 2,420 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 2026-08-31.