interface-audit

An audit tool for reviewing product interfaces as component boundaries, meaning the points where parts of an interface meet and share responsibilities.

In plain words
What is it for?
It produces a report with scores, findings, confidence, and recommendations for cleaning up an interface. It does not implement the changes.
Why use it?
It identifies unnecessary complexity, over-engineering, and accumulated design debt using evidence from the current code and tests.

Skill for Claude CodeCodex

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 skills/conn-castle/agent-layer/interface-audit
Any agent
npx skills add conn-castle/agent-layer --skill interface-audit
Clone the repo
git clone --depth 1 https://github.com/conn-castle/agent-layer

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 522 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00055 $0.00522
Opus 5 $0.00028 $0.00261
Sonnet 5 $0.00011 $0.00104
Haiku 4.5 $0.00006 $0.00052

Measured 2d ago against content hash fa9bfa2ef186, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

interface-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 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.

internal/templates/skills/interface-audit/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

interface-audit

Produce one evidence-backed audit of product interface boundaries. Do not implement or launch planning.

Inputs and references

Run a fresh audit by default. --update [report-path] refreshes an existing report. Read references/report-structure.md; for an update also read references/update-workflow.md.

A fresh audit uses only current code, tests, docs, command output, and evidence created for this run. Do not inspect prior audit artifacts unless the user asks for an update.

Evidence contract

  • Score concrete component boundaries, not vague subsystems.
  • Verify names and numeric claims; use partial when exact measurement adds little value.
  • Ground complexity, over-engineering, debt, confidence, and recommendations in current evidence. Current code and tests outrank stale documentation.
  • Preserve row identifiers during updates and never reuse retired identifiers.
  • Protect discovered product requirements unless the user approves a behavior change. Do not preserve stale scores for continuity.

Workflow

  1. Establish fresh or update mode, repository baseline, report path, and scope.
  2. Trace the interface chain, contracts, ownership, state, tests, failure modes, and meaningful cleanup opportunities. Investigate directly unless coherent, independent boundary groups benefit from read-only parallel investigation.
  3. Calibrate neighboring rows, update the report, and select the highest-value coherent improvement. Revisit only evidence gaps or inconsistencies. If no candidate justifies its cost, record no-material-improvement.
  4. For a material candidate, decide whether it requires broad ownership, protocol, data-model, cross-language, or user-workflow redesign. Recommend that architecture only when a smaller interface improvement is insufficient; otherwise recommend the smallest coherent improvement. State any behavior change and require approval before it enters a plan. Include exact /implement input as a handoff, but do not run it.

Read the full file on GitHub · 56 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 56 lines · 55 tokens per session scan A fa9bfa2ef186

Subscribe to this mod's changes

interface-audit is a skill published in the GitHub repository conn-castle/agent-layer (10 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 522 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories