psenger/ai-agent-skills

arch-lens

Explores a codebase for architectural friction through the lens of Ousterhout's deep-module principle (small interface, large implementation). Seven-step interactive experiences IS the signal. Surfaces candidate clusters with coupling reasons, call patterns, shared types, dependency categories, and existing tests that a boundary test would replace. User picks what to explore, frames the problem, then 3–4 parallel sub-agents design competing deep-module interfaces. Chosen design becomes a struct…

First seen Mar 17, 2026

Installation

$ npx skills add psenger/ai-agent-skills --skill arch-lens

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from psenger/ai-agent-skills · top by installs.

npx skills add psenger/ai-agent-skills

Browse all from psenger/ai-agent-skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 10
License LICENSE
Default branch main
Open issues 1
Status Active

Skill metadata

Parsed from SKILL.md frontmatter.

CompatibilityRequires git for churn analysis. No other external tools required.
Allowed toolsRead Grep Glob Write Bash(git *)

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,589 B
  • docs SUMMARY.md 879 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 23 installs

SKILL.md

Arch Lens

Seven-step interactive architectural review. An Explore sub-agent navigates the codebase the way a developer would — the confusion, file-bouncing, and untestable seams it encounters are the findings. No checklists, no rigid heuristics.

Deep module: small interface surface hiding a large, self-contained implementation.
Lets callers test at the boundary. Lets AI agents reason without reading internals.

Quick start

  1. If a path argument is given, scope to that directory; otherwise whole repo
  2. Load ${CLAUDESKILLDIR}/references/WORKFLOW.md — full step-by-step instructions
  3. Load ${CLAUDESKILLDIR}/references/DETECTION-PATTERNS.md
  4. Load ${CLAUDESKILLDIR}/references/INTERFACE-DESIGN.md
  5. Load ${CLAUDESKILLDIR}/references/RFC-FILE-FORMAT.md
  6. Execute the seven steps in WORKFLOW.md

Workflows

Step What happens Requires user input
1. Explore Spawn Explore sub-agent; navigate organically; record friction
2. Candidates Synthesise friction into clusters; present max 8 with full context
3. Pick User selects a cluster and directs the angle wait
4. Frame Problem statement, dependency category, blast radius, test boundary today
5. Design Spawn 3–4 parallel sub-agents with competing interface designs
6. Choose User picks interface or accepts recommendation wait
7. RFC file Write arch-rfcs-YYYY-MM-DD.md to project root

Full prompt text, cluster format, and step detail: see WORKFLOW.md.

Behavioural rules

  • Explore agent friction observations are primary evidence — never override with static analysis
  • Never propose interface designs before Step 5
  • Never advance past Steps 3 or 6 without a user response
  • Every RFC must include exact file:line references and a before/after illustration
  • Name every dependency category explicitly — it determines the testing strategy
  • Rank clusters: testability impact first, then cognitive load, then interface stability

Advanced features

  • Full workflow detail and Explore agent prompt: ${CLAUDESKILLDIR}/references/WORKFLOW.md
  • Friction vocabulary and dependency categories: ${CLAUDESKILLDIR}/references/DETECTION-PATTERNS.md
  • Sub-agent brief template and design constraints: ${CLAUDESKILLDIR}/references/INTERFACE-DESIGN.md
  • RFC action file format and complete example: ${CLAUDESKILLDIR}/references/RFC-FILE-FORMAT.md