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 mracal/vibe-engineering --skill gap-analysisgit clone --depth 1 https://github.com/mracal/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/mracal/vibe-engineering/gap-analysis)<a href="https://agentmods.dev/skills/mracal/vibe-engineering/gap-analysis"><img src="https://agentmods.dev/badge/skills/mracal/vibe-engineering/gap-analysis/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/mracal/vibe-engineering/gap-analysis"><img src="https://agentmods.dev/badge/skills/mracal/vibe-engineering/gap-analysis.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 | $0.00036 | $0.01358 |
| Opus 5.5 | $0.00014 | $0.00543 |
| Sonnet 5.5 | $0.00007 | $0.00272 |
| Haiku 4.5 | $0.00004 | $0.00136 |
Grade A, and why
vibe-gap-analysis 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 1mo 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.
This is a copy
95% identical to vibe-gap-analysis — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibe-gap-analysis
Cynical gap analysis comparing specs/architecture to actual implementation. Three modes from fast to exhaustive. Works with any project that has architecture docs and implementation code.
When to Use This Skill
- Before launching to production
- After a major refactor to verify nothing was lost
- When inheriting a codebase and need to assess completeness
- Periodic production readiness audits
- When stakeholders ask "how done are we?"
When NOT to Use This Skill
- Greenfield projects with no specs yet (write specs first)
- Simple bug fixes or feature additions
- Frontend-only or design-only reviews
Usage
/vibe-gap-analysis # Quick static (5 structural dimensions)
/vibe-gap-analysis --deep # Full 17-dimension audit with parallel agents
/vibe-gap-analysis --dim N # Single dimension deep-dive (1-17)
/vibe-gap-analysis --dim 1,4,9 # Multiple specific dimensions
Modes
Quick Static (default)
Fast, single-agent structural audit. No subagents dispatched.
- Read architecture/design docs in
docs/or similar - Read implementation code in
src/,internal/,lib/etc. - Compare implementation against architecture doc section by section
- Cover dimensions 1-5 (structural):
- Dim 1: Spec Compliance — check specs against implementation
- Dim 2: Backend Code Quality — test coverage, error handling, lint issues
- Dim 3: Frontend Completeness — UI components, routes, test coverage
- Dim 4: Deployment & Ops — deploy scripts, CI/CD, Docker, TLS
- Dim 5: Architecture Integrity — design pattern compliance, component boundaries
- Produce structured gap report: component, expected status, actual status, % complete, action items
- Save to
docs/plans/gap-analysis-$(date +%Y%m%d).md - Commit with
docs: gap analysis $(date +%Y%m%d)
Deep (--deep)
Full 17-dimension audit using parallel subagents. Exhaustive production readiness assessment.
Dispatch parallel agents (model: sonnet) in 3 rounds:
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.
- 1mo ago First seen · 144 lines · 36 tokens per session scan A 092ddcd537ea
vibe-gap-analysis is a skill published in the GitHub repository mracal/vibe-engineering (3 stars, last pushed 7d ago), licensed MIT. It adds 36 tokens to every session and 1,358 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 95% identical to vibe-gap-analysis, differing in 9 lines, and is treated as a copy.
Other skills, from other repositories
code-intelligence-contract
Use when dependency, call-chain, blast-radius, architecture, domain-flow, or unfamiliar-codebase analysis needs an optional vendor-neutral code-intelligence provider.
do-it-audit
Use when the user explicitly requests a deep repository or scoped audit; not for ordinary diff review.
evidence-first-debugging
Use when debugging a crash, lỗi, failing game, tool, build, service, script, or reproducible local code failure requires repro or reproduction, giả thuyết or ranked hypotheses, instrumentation, root-cause isolation, a minimal fix, regression proof, and a regression test.
review-swarm
Use when reviewing a known change set through parallel read-only code, architecture, test, safety, or product lanes with disjoint concerns and one integrator verdict.
unity-ui-rendering-debugging
Use when a Unity UI, HUD, screen item, or NGUI widget is missing, clipped, behind another canvas, wrongly sorted, disconnected from a prefab or atlas, misanchored, or invisible despite correct gameplay state.
bug-hunt-swarm
Use when an unknown crash, intermittent failure, or cross-subsystem bug needs parallel read-only reproduction lanes, ranked hypotheses, suspect paths, and an integrator root-cause plan.