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.
npx agentmods add skills/compozy/kb/architectural-analysisnpx skills add compozy/kb --skill architectural-analysisgit clone --depth 1 https://github.com/compozy/kbWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00049 | $0.04431 |
| Opus 5 | $0.00024 | $0.02216 |
| Sonnet 5 | $0.00010 | $0.00886 |
| Haiku 4.5 | $0.00005 | $0.00443 |
Grade A, and why
architectural-analysis 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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- architectural-analysis — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 646 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architectural Analysis
Instructions
Perform comprehensive architectural audit focused on structural issues, dead code, duplication, and systemic problems.
Phase 1: Discovery & Planning
Step 1: Map Codebase Structure
# Get directory structure
find . -type d -not -path "*/node_modules/*" -not -path "*/.git/*"
# Count files by type
find . -name "*.ts" -o -name "*.tsx" -o -name "*.js" -o -name "*.jsx" | wc -l
Step 2: Identify Entry Points
- Main application entry (
index.ts,main.ts,app.ts) - API routes/controllers
- Public exports (
index.tsfiles) - CLI entry points
- Test files
Step 3: Create Comprehensive File List
Use Glob to find all source files. Create todo list with one item per file to analyze.
Phase 2: Dead Code Detection
For EACH file in the todo list:
Step 1: Identify Exports
- What does this file export?
- Are exports functions, classes, types, constants?
- Is anything exported at all?
Step 2: Search for Usage
For each export, search if it's imported/used anywhere:
# Search for imports of this export
grep -r "import.*ExportName" . --include="*.ts" --include="*.tsx"
grep -r "from.*filename" . --include="*.ts" --include="*.tsx"
# Search for direct usage
grep -r "ExportName" . --include="*.ts" --include="*.tsx"
Step 3: Categorize Code
Dead Code (mark for removal):
- Exported but never imported
- Functions defined but never called
- Classes instantiated nowhere
- Types defined but never used
- Constants defined but never referenced
- Entire files with no imports from other files
Possibly Dead (needs verification):
- Only used in commented-out code
- Only used in dead code
- Only used in other unused exports
- Used only in tests for deprecated features
Internal Dead Code:
- Functions defined in file but never called (not exported)
- Variables assigned but never read
- Parameters accepted but never used
Step 4: Check for False Positives
Not dead if:
- Used in tests (may be public API)
- Dynamically imported/required
- Used via reflection/string references
- Part of public API (even if not used internally)
- Framework hooks (lifecycle methods, callbacks)
- Accessed via
windowor global scope
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.
- 2d ago First seen · 646 lines · 49 tokens per session scan A fc8746d270b9
architectural-analysis is a skill published in the GitHub repository compozy/kb (102 stars, last pushed 12d ago), licensed MIT. It adds 49 tokens to every session and 4,431 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.