agentleFS
tyler-berggrentyler-berggren/tb-claude-kit/.claude/skills/cto/SKILL.md

cto

Skill2 starsChanged 5 days agoMITView on GitHub

Re-runnable architecture observatory — scans the codebase, maps components and relationships into a SQLite DB, generates a self-contained HTML document with Mermaid diagrams at multiple C4 levels. Delta tracking across runs reveals architectural drift.

12 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use cpo and cmo.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • sahinSkill

    cpo

    CPO Co-Pilot - product strategy, roadmap prioritization, competitive positioning, and product-market fit validation

    Also in 4 projects that use this

  • sahinSkill

    cmo

    CMO Co-Pilot - GTM strategy, growth frameworks, and marketing leadership (composite GTM leader voice)

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read cowork/architecture/PROCEDURE.md for the full scan/synthesize/output procedure.

    line 21
  2. Very specific:

    If .claude/kit.json has a rules."cto" entry, read it and apply it as an additional instruction for this skill.

    line 47

“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Last Run

!sqlite3 -separator ' | ' cowork/architecture/CTO.db "SELECT '#' || id, started_at, git_sha, substr(summary, 1, 150) FROM runs ORDER BY started_at DESC LIMIT 1;" 2>/dev/null || echo "No prior runs — first run will establish baseline"

Subsystem Summary

!sqlite3 -separator ' | ' cowork/architecture/CTO.db "SELECT subsystem, component_count || ' components', total_loc || ' LOC' FROM v_subsystem_summary LIMIT 10;" 2>/dev/null || echo "No data yet"

Complexity Hotspots (Top 5)

!sqlite3 -separator ' | ' cowork/architecture/CTO.db "SELECT path, loc || ' LOC', CAST(complexity_score AS INTEGER) || ' score' FROM v_complexity_hotspots WHERE loc > 0 LIMIT 5;" 2>/dev/null || echo "No data yet"

Recent Drift

!sqlite3 -separator ' | ' cowork/architecture/CTO.db "SELECT path, drift_type, loc_delta FROM v_architectural_drift LIMIT 5;" 2>/dev/null || echo "No drift data — need 2+ runs"


Read cowork/architecture/PROCEDURE.md for the full scan/synthesize/output procedure.

Key paths

  • CTO.db: cowork/architecture/CTO.db — structured architecture data across runs
  • Schema: cowork/architecture/schema.sql — recreate DB if missing
  • Seed data: cowork/architecture/seed.sql — project-specific context (edit per project)
  • Procedure: cowork/architecture/PROCEDURE.md — full three-phase procedure
  • HTML output: cowork/architecture/architecture.html — self-contained HTML with Mermaid diagrams
  • Summaries: cowork/architecture/YYYY-MM-DD_architecture-summary.md — dated markdown summaries (git-diffable, visible in Obsidian)

Rules

  • No permission needed — Execute immediately.
  • Fully automated — No interactive brainstorm phase (unlike vibe-audit). Scan → synthesize → output.
  • Idempotent — Running twice on the same SHA produces the same output. Delta tracking handles the rest.
  • Subagent fan-out for synthesis — Each subsystem gets its own subagent for summarization. Keeps context windows clean.
  • Mermaid for diagrams — C4 levels: Context (L0), Container (L1), Component (L2). All rendered client-side via Mermaid.js CDN.
  • HTML is the deliverable — architecture.html is self-contained, dark-themed, and shareable. Opens in any browser.
  • DB is the memory — CTO.db accumulates data across runs. Component history tracks first/last seen, LOC drift, role changes.
  • Seed data is project-specific — Edit seed.sql to define your project's subsystems and patterns. The scan discovers everything else automatically.

Project overrides

If .claude/kit.json has a rules."cto" entry, read it and apply it as an additional instruction for this skill. Absent file or key means no overrides — that is the normal case.

jq -r '.rules."cto" // empty' .claude/kit.json 2>/dev/null

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.