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 ash1794/vibe-engineering --skill vibe-quality-loopgit clone --depth 1 https://github.com/ash1794/vibe-engineeringWrote 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/ash1794/vibe-engineering/vibe-quality-loop)<a href="https://agentmods.dev/skills/ash1794/vibe-engineering/vibe-quality-loop"><img src="https://agentmods.dev/badge/skills/ash1794/vibe-engineering/vibe-quality-loop/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/ash1794/vibe-engineering/vibe-quality-loop"><img src="https://agentmods.dev/badge/skills/ash1794/vibe-engineering/vibe-quality-loop.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 | $0.00039 | $0.00644 |
| Opus 5.5 | $0.00016 | $0.00258 |
| Sonnet 5.5 | $0.00008 | $0.00129 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
vibe-quality-loop 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 20d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibe-quality-loop
The quality loop prevents premature "done" declarations. Keep iterating until the review is clean and the tests pass, and show the evidence.
When to Use This Skill
- After an implementation that touches more than a couple of files or any non-trivial logic
- After implementing a feature with tests
- Before creating a commit or PR on completed work
When NOT to Use This Skill
- Single-line fixes or typo corrections
- Documentation-only changes (use
vibe-doc-quality-gate) - When the user says "just get it working, we'll clean up later"
The Loop
Implement → Self-review diff → Run checks ─┬─ clean + green → EXIT
↑ │
└──────── Fix issues ←──────┘
Steps
-
Review the diff — Read the whole diff as a reviewer would. If the harness has a built-in review command (for example
/code-reviewin Claude Code or/reviewin Codex), run it. Otherwise check for:- Bugs: wrong conditions, off-by-one errors, unhandled error paths, broken edge cases
- Leftovers: unused imports and variables, debug output, commented-out code
- Consistency: does it match the naming and idioms of the surrounding code?
- Scope: anything not requested (
vibe-scope-guard) - Test integrity: were any tests weakened to pass? (
vibe-anti-rationalization-check)
-
Run the project's own checks — Use what the repo defines (Makefile,
package.jsonscripts, CI workflow) rather than guessing:- Full test suite, not just the tests you wrote
- Linter, formatter, type checker
- The race detector for concurrent code where the language has one (e.g.,
go test -race)
-
Fix only the issues found. Don't add features while fixing.
-
Loop back to step 1. Track the iteration count.
-
Exit when the review is clean and all checks pass. Quote the final check output. Don't paraphrase it.
Stop Conditions
- After 5 iterations without converging, stop and report what's stuck rather than looping further.
- A failure that also happens on the base branch is pre-existing. Report it; don't "fix" it silently in this change.
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.
- 20d ago First seen · 70 lines · 39 tokens per session scan A 521bd10a31d0
vibe-quality-loop is a skill published in the GitHub repository ash1794/vibe-engineering (164 stars, last pushed 8d ago), licensed MIT. It adds 39 tokens to every session and 644 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-26.
Other skills, from other repositories
pre-pr-audit
Pre-PR confidence audit with 5-dimension scoring. Use when: final check before commit/push/PR, evaluating PR readiness, assessing test quality + risk + coverage holistically. Triggers: pre-pr, readiness check, confidence audit, final verification, ready to PR, how confident. Not for: code review (use…
brooks-test
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…
test-review
Test coverage review via Codex exec. Use when: reviewing test sufficiency, identifying coverage gaps, test quality audit. Not for: generating tests (use codex-test-gen), code review (use codex-code-review). Output: coverage analysis + gap report.
precommit
Pre-commit checks — lint:fix -> build -> test.
pr-comment
Post friendly review comments to a GitHub PR — prepare locally, preview, then submit as atomic review. Use when: posting code review comments, giving PR feedback, sending inline suggestions. Not for: reading existing reviews (use load-pr-review), creating PRs (use create-pr), PR status (use pr-summary).
precommit-fast
Quick pre-commit checks — lint:fix -> test.