recon

recon is a command for Claude Code from TheWayWithin/agent-11. It costs 14 tokens per session (768 once invoked), scanned A, a copy of design-review, MIT.

A command for performing a UI/UX reconnaissance review of current code changes. UI/UX means how an interface looks, works, and supports users; the review examines design quality, accessibility, consistency, and visual evidence in a Git diff.

In plain words
What is it for?
Reviewing modified interface code, checking design tokens and project guidance, classifying findings by severity, and attaching screenshot evidence to visual issues.
Why use it?
It helps find interface problems in a change before release, including accessibility issues and departures from the project's design rules.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the NotebookEdit tool.

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 commands/thewaywithin/agent-11/recon
Clone the repo
git clone --depth 1 https://github.com/TheWayWithin/agent-11

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 recon

README.md
[![agentmods](https://agentmods.dev/badge/commands/thewaywithin/agent-11/recon.svg)](https://agentmods.dev/commands/thewaywithin/agent-11/recon)
Your own site
<a href="https://agentmods.dev/commands/thewaywithin/agent-11/recon"><img src="https://agentmods.dev/badge/commands/thewaywithin/agent-11/recon.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 768 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 84% copy Near-identical to another mod 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 $0.00014 $0.00768
Opus 5 $0.00007 $0.00384
Sonnet 5 $0.00003 $0.00154
Haiku 4.5 $0.00001 $0.00077

Measured yesterday against content hash 6703cd1d5c9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

recon 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 yesterday.

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.

Origin

This is a copy

84% identical to design-review — 126 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/recon.md · 75 lines

What it actually says

RECON PROTOCOL ACTIVATION 🎯

You are now executing a UI/UX reconnaissance mission using the RECON Protocol (Rapid Evaluation & Critique Operations Network). Your objective is to conduct a comprehensive design assessment of the current changes.

OPERATIONAL CONTEXT

GIT STATUS:

!`git status`

FILES MODIFIED:

!`git diff --name-only origin/HEAD...`

RECENT OPERATIONS:

!`git log --no-decorate --oneline -10 origin/HEAD...`

CHANGE ANALYSIS:

!`git diff --merge-base origin/HEAD`

MISSION PARAMETERS

Review the complete diff above containing all UI/UX changes. Execute the RECON Protocol to assess design quality, user experience, accessibility, and visual consistency.

EXECUTION DIRECTIVE

  1. Deploy @designer agent with RECON Protocol activation
  2. If UI doctrine exists in /field-manual/ui-doctrine.md, apply those standards
  3. If design tokens exist in /field-manual/combat-tokens.md, verify compliance
  4. Execute all 8 phases of RECON Protocol systematically
  5. Classify findings by threat level: [CRITICAL], [URGENT], [TACTICAL], [COSMETIC]
  6. Apply "Observe-Don't-Prescribe" communication doctrine
  7. Provide screenshot evidence for all visual issues

PRIORITY ASSESSMENT AREAS

  • User flow disruptions
  • Accessibility violations (WCAG AA+)
  • Responsive design failures
  • Visual inconsistencies
  • Performance degradation
  • Brand compliance issues
  • Component reuse patterns
  • Design token violations

OUTPUT REQUIREMENTS

Your final response must contain:

  1. The complete RECON REPORT in markdown format
  2. Evidence screenshots where applicable
  3. Prioritized recommendations
  4. Overall design health assessment

COORDINATION NOTES

  • If testing functionality needed, coordinate with @tester's SENTINEL Mode
  • If architecture concerns arise, escalate to @architect
  • If performance issues detected, alert @operator
  • For accessibility deep-dive, may require specialist consultation

INITIATE RECON PROTOCOL NOW

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. yesterday First seen · 75 lines · 14 tokens per session scan A 6703cd1d5c9e

Subscribe to this mod's changes

recon is a command published in the GitHub repository TheWayWithin/agent-11 (15 stars, last pushed 13d ago), licensed MIT. It adds 14 tokens to every session and 768 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 84% identical to design-review, differing in 126 lines, and is treated as a copy.