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 tslateman/duet --skill vibe-checkgit clone --depth 1 https://github.com/tslateman/duetWrote 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/tslateman/duet/vibe-check)<a href="https://agentmods.dev/skills/tslateman/duet/vibe-check"><img src="https://agentmods.dev/badge/skills/tslateman/duet/vibe-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.
<a href="https://agentmods.dev/skills/tslateman/duet/vibe-check"><img src="https://agentmods.dev/badge/skills/tslateman/duet/vibe-check.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00057 | $0.01291 |
| Opus 5 | $0.00028 | $0.00646 |
| Sonnet 5 | $0.00011 | $0.00258 |
| Haiku 4.5 | $0.00006 | $0.00129 |
Grade A, and why
vibe-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 8d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vibe Check
Overview
"Vibe check?", a way of asking what's the energy like right now?
Static linters catch syntax. Code review catches everything but takes time. Vibe-check sits between: a quick judgment pass that asks whether AI-generated code feels like it was written with thought or just generated on autopilot.
Single-agent, one pass. Runs on the diff by default. Surfaces higher-order problems that require reasoning, the things a thoughtful reviewer notices in the first 30 seconds that no regex can detect.
Input
Default: Git diff (staged if present, unstaged otherwise).
# Check current changes
/vibe-check
# Check specific files or directories
/vibe-check src/auth/
Override: Named files or directories passed as arguments.
Assertion Categories
Each category reads a specific vibe. Findings require AI judgment, if a static linter could catch it, it doesn't belong here.
| Category | The vibe | What it catches |
|---|---|---|
| Earned complexity | "This feels over-engineered" | Abstractions that don't justify themselves, premature generalization, indirection without payoff |
| Prompt-shaped code | "This feels shaped by the prompt, not the problem" | Odd boundaries, misnamed concepts, structure that mirrors how the request was worded rather than the domain |
| Missing skepticism | "This feels like nothing can go wrong" | Happy-path-only logic, unchallenged assumptions, no failure modes considered, silent swallowing of errors |
| Cargo-culted patterns | "This feels ceremonial" | Design patterns applied without justification, boilerplate that adds ceremony without value, framework idioms used out of context |
| Integration blindness | "This feels written in a vacuum" | Duplicates existing utilities, contradicts established codebase patterns, ignores conventions visible in surrounding code |
| Shallow naming | "This feels like nobody thought about what it means" | Names describe implementation (handleData, processItems) instead of intent, a signal the author didn't reason about the domain |
| Security surface | "This feels like it trusts too much" | Auth gaps, unsanitized boundaries, trust assumptions, only the ones requiring judgment, not what semgrep catches |
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.
- 8d ago First seen · 119 lines · 0 tokens per session scan A 5f114aa80ef9
vibe-check is a skill published in the GitHub repository tslateman/duet (1 stars, last pushed 11d ago), licensed MIT. It adds 57 tokens to every session and 1,291 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.
Other skills, from other repositories
self-audit
Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.
gate-check
Final quality gate before reporting task completion (Gate 3). Fills confidence assessment, runs supplementary verification for <95% items, completes self-check checklist. Writes PASS/FAIL result to subtask.md, then calls autoworker:dispatch for routing.
verifying-task-output
Use after a dispatched task returns, to verify the output before marking it done.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…