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 skills add softspark/ai-toolkit --skill architecture-auditgit clone --depth 1 https://github.com/softspark/ai-toolkitWrote 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.
[](https://agentmods.dev/skills/softspark/ai-toolkit/architecture-audit)<a href="https://agentmods.dev/skills/softspark/ai-toolkit/architecture-audit"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/architecture-audit.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.01508 |
| Opus 5 | $0.00017 | $0.00754 |
| Sonnet 5 | $0.00007 | $0.00302 |
| Haiku 4.5 | $0.00003 | $0.00151 |
Grade A, and why
architecture-audit 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.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Audit
$ARGUMENTS
Explore a codebase organically, surface architectural friction, and propose module-deepening refactors as GitHub issue RFCs.
Usage
/architecture-audit [area to audit or 'full codebase']
What This Command Does
- Explores codebase organically — friction IS the signal
- Presents deepening candidates to user
- Frames problem space for chosen candidate
- Spawns 3+ parallel sub-agents for radically different interface designs
- Compares and recommends
- Files RFC as GitHub issue
Key Concept
A deep module (Ousterhout) has a small interface hiding a large implementation. Deep modules enhance testability, AI navigation, and enable boundary testing.
A shallow module has a large interface with thin implementation — avoid.
Process
1. Organic Exploration
Use Agent (subagent_type=Explore) to navigate the codebase naturally. Note friction:
- Where does understanding one concept require bouncing between many small files?
- Where are modules so shallow the interface is nearly as complex as the implementation?
- Where have pure functions been extracted just for testability but real bugs hide in how they're called?
- Where do tightly-coupled modules create integration risk in the seams?
- What is untested or hard to test?
2. Present Candidates
Numbered list. For each candidate show:
| Field | Content |
|---|---|
| Cluster | Which modules/concepts are involved |
| Why coupled | Shared types, call patterns, co-ownership |
| Dependency category | In-process, Local-substitutable, Ports & Adapters, or True external (see reference/) |
| Test impact | What existing tests would be replaced by boundary tests |
Do NOT propose interfaces yet. Ask: "Which would you like to explore?"
3. Frame the Problem Space
For the chosen candidate, write a user-facing explanation:
- Constraints any new interface would satisfy
- Dependencies it would rely on
- Rough illustrative code sketch (not a proposal — just grounding)
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.
- 7d ago First seen · 166 lines · 34 tokens per session scan A d99c2e0d29d0
architecture-audit is a skill published in the GitHub repository softspark/ai-toolkit (170 stars, last pushed 2d ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,508 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
go-code-reviewer
Review Go code with a defect-first approach using repository policy (constitution.md first, then AGENTS.md fallback). Use for code review, PR review, quality checks, risk analysis, and regression detection.
go-review-lead
Orchestrate a comprehensive Go code review by triaging code changes, dispatching vertical review skills (security, concurrency, error, logic, performance, quality, test, observability) as parallel agents, then consolidating results into a unified report. Use for full Go PR review or comprehensive code review. Replaces…
security-review
A code-security review guide that checks code changes, pull requests, or services for risks an attacker could exploit.
go-concurrency-review
Review Go code for concurrency safety and goroutine lifecycle issues including race conditions, deadlocks, goroutine leaks, mutex misuse, and context propagation. Trigger when code contains go func, channels, sync primitives, WaitGroup, errgroup, or goroutine lifecycle management. Use for concurrency-focused review of…
go-error-review
Review Go code for error handling correctness, nil safety, and failure-path integrity including ignored errors, missing wrapping, panic misuse, SQL/HTTP resource lifecycle, and transaction patterns. Trigger when code contains error returns, panic calls, sql.Rows, transactions, HTTP client/server code, or nil-sensitive…
go-observability-review
Review Go code for observability gaps: missing structured logging, broken trace context propagation, Prometheus cardinality explosions, span lifecycle errors, and sensitive fields in logs. Dispatched by go-review-lead as a vertical reviewer. Also trigger directly when the user says "review my logging", "check my…