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.
curl -O https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/.agents/skills/vibecheck/SKILL.mdgit clone --depth 1 https://github.com/mtarcure/claude-vibe-squadWrote 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/mtarcure/claude-vibe-squad/vibecheck)<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/vibecheck"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/vibecheck/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/mtarcure/claude-vibe-squad/vibecheck"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/vibecheck.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low Excessive Agency · line 62 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00051 | $0.01565 |
| Opus 5 | $0.00026 | $0.00783 |
| Sonnet 5 | $0.00010 | $0.00313 |
| Haiku 4.5 | $0.00005 | $0.00156 |
Grade A, and why
vibecheck 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 11d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vibecheck
A last sweep before done. It exists because the defects that survive to the end of a task are not
usually logic errors — those get caught by tests. They are discipline defects: scratch files nobody
removed, work done outside what was asked, a refactor nobody requested, a summary that oversells. Each
is individually small and each erodes the trust that makes the next completion claim believable.
Run it when the work is finished and before the completion message is written.
Relationship to claim-evidence work
Vibecheck does not re-do claim verification. Run every falsifying check after the last edit and pair
its evidence to the corresponding claim; claim-verification owns decomposing load-bearing claims and
mapping each to exact evidence. Check C1 below confirms that work happened; it does not repeat it.
The checks unique to this skill are the behavioural ones — C2 through C9. That is where its value is.
The checks
C1 — no false done. The summary must not claim verification that did not occur. If it says tests pass, a validator is green, or something works, the corresponding output must have been run and read this session, after the last edit. Confirm the falsifying checks ran after the last edit and their evidence is paired to those claims; do not repeat the checks here.
C2 — leftover artifacts are detected and reported, not silently removed. Scan for scratch files, temp scripts, debug output, commented-out experiments, and one-off helpers left in the tree, and list them in your response. Two specific traps: a throwaway script written for a one-time job is not a deliverable and should not persist as though it were reusable; and a test spawn, mock, or fixture left behind will later read as real state and mislead whoever finds it.
Do not delete them. Cleanup and deletion require explicit operator approval under Hard Rule 6, and neither authorship nor write scope waives that gate — "I made it, so I may remove it" is exactly the reasoning the rule exists to stop. Report the inventory and let Chrono obtain approval. This check may still block "done" while cleanup is pending: an unreported leftover is a defect, an unapproved deletion is a rule violation, and reporting is the only move that is neither.
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.
- 11d ago First seen · 108 lines · 51 tokens per session scan A 441a756500d3
vibecheck is a skill published in the GitHub repository mtarcure/claude-vibe-squad (148 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 1,565 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 2026-08-30.
Other skills, from other repositories
cw-slice
Use before writing code for any Codewhale feature, upgrade, or refactor: find the existing owner of the behavior, bound the change to one reviewable slice, and fix the evidence bar before you start.
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
gh-compile-issues
Triage N GitHub issues into a coverage matrix: fetch each, check current code, classify already-done/quick-fix/design/defer with cited evidence.
review
Read-only correctness review with actionable findings first, tight file/line evidence, severity, and a concise residual-risk summary.
simplify
Improve clarity and reduce needless complexity after behavior is understood; preserve behavior and keep cleanup separate from correctness fixes.
review-team
Use when assigned a review or when an authored review boundary is reached.