claude-vibe-squad: Skill for Claude Code

.agents/skills/interface-ambiguity-check/SKILL.md

interface-ambiguity-check is a skill for Claude Code, Codex from mtarcure/claude-vibe-squad. It costs 88 tokens per session (949 once invoked), scanned A, original, MIT.

A checklist for clarifying an API, data schema, file format, or other contract written by someone else. It tests important unknowns such as units, missing values, ordering, errors, retries, and whether repeating an operation is safe.

In plain words
What is it for?
Use it before implementing an unfamiliar interface to document assumptions, inspect its producer and users, and run small probes where the contract is unclear.
Why use it?
It reduces bugs caused by silently guessing how an external interface behaves. Each important assumption is tied to documentation, observed behavior, or a direct test.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is mtarcure/claude-vibe-squad's own configuration. It tells Claude Code and Codex how to work on claude-vibe-squad itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-vibe-squad configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mtarcure/claude-vibe-squad. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/.agents/skills/interface-ambiguity-check/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mtarcure/claude-vibe-squad

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for interface-ambiguity-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/interface-ambiguity-check/github.svg)](https://agentmods.dev/skills/mtarcure/claude-vibe-squad/interface-ambiguity-check)
Your own site
<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/interface-ambiguity-check"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/interface-ambiguity-check/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for interface-ambiguity-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/interface-ambiguity-check"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/interface-ambiguity-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 949 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00088 $0.00949
Opus 5 $0.00044 $0.00475
Sonnet 5 $0.00018 $0.00190
Haiku 4.5 $0.00009 $0.00095

Measured 10d ago against content hash 86f0bda607a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

interface-ambiguity-check 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 10d 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.

.agents/skills/interface-ambiguity-check/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Interface Ambiguity Check

Two parties meeting at a boundary each hold a private interpretation of it. Before writing code against an interface, make every load-bearing assumption explicit, classify it as documented, observed, or guessed — and eliminate the guesses.

When to use

  • Implementing against an API, schema, TSV/JSON format, function signature, or protocol authored by someone else (including a past task).
  • Two independently-built components are about to integrate.
  • A packet says "integrate with X" or "consume Y's output" without a contract document.

Inputs

  • The interface artifact: schema, header row, signature, endpoint doc, example payload.
  • Real producer/consumer behavior: actual payloads, actual call sites, the parser's source.

Steps

  1. List every element crossing the boundary: each field, parameter, return value, status code, file, and side effect.
  2. Run each element through the ambiguity battery: type and units; required vs optional; null vs empty vs absent; ordering and uniqueness guarantees; case, encoding, and delimiter rules; error signaling (exception, code, sentinel, silence); idempotency and retry semantics; which side validates; versioning and evolution rules.
  3. Classify each answer: documented (cite where), observed (cite the real payload, call site, or parser line you inspected), or assumed (unpinned).
  4. Pin every load-bearing assumption: read the counterpart's source, inspect a real sample, or run a cheap probe. When the boundary's owner must decide — surface the question (in a packet context: ## NEEDS FROM CHRONO, or blocked per specialist rules) instead of implementing a guess whose wrong answer is expensive to unwind.
  5. When documentation and observed behavior disagree, the observed behavior wins for implementation — and the disagreement itself is a finding to report, not to silently absorb.
  6. Encode pinned answers where the machine can hold them: a strict parser, an assertion, a test that uses a real captured sample rather than a hand-invented one.
  7. Record deliberately unpinned residuals as named risks in the artifact, with the trigger that would surface each.

Read the full file on GitHub · 49 lines

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. 10d ago First seen · 49 lines · 88 tokens per session scan A 86f0bda607a8

Subscribe to this mod's changes

interface-ambiguity-check is a skill published in the GitHub repository mtarcure/claude-vibe-squad (122 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 949 once invoked, about $0.0004 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.