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 spec-vs-code-auditgit 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/spec-vs-code-audit)<a href="https://agentmods.dev/skills/mracal/vibe-engineering/spec-vs-code-audit"><img src="https://agentmods.dev/badge/skills/mracal/vibe-engineering/spec-vs-code-audit/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/spec-vs-code-audit"><img src="https://agentmods.dev/badge/skills/mracal/vibe-engineering/spec-vs-code-audit.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 | $0.00034 | $0.00485 |
| Opus 5.5 | $0.00014 | $0.00194 |
| Sonnet 5.5 | $0.00007 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
vibe-spec-vs-code-audit 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
100% identical to vibe-spec-vs-code-audit — 0 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.
What it actually says
vibe-spec-vs-code-audit
Specs drift from code. Code drifts from specs. This skill catches the gaps.
When to Use This Skill
- Implementation of a spec/design doc is claimed complete
- After a major refactor that should still conform to a spec
- During periodic compliance checks
- When debugging unexpected behavior (maybe the code doesn't match the spec)
When NOT to Use This Skill
- No spec or design doc exists (nothing to compare against)
- The spec is explicitly marked as aspirational/future
- Code was intentionally diverged with documented reasons
Steps
-
Identify the spec — Find the specification document (design doc, PRD section, API spec, etc.)
-
Identify the implementation — Find the code files that implement this spec
-
Line-by-line comparison — For each requirement/section in the spec:
- Find the corresponding code
- Check: Does the code match the spec exactly?
- If divergent: Record as a GAP
-
Classify each gap:
- ID: GAP-[section]-[number] (e.g., GAP-AUTH-001)
- Type: Missing (spec says X, code has nothing) / Incorrect (spec says X, code does Y) / Extra (code has X, spec doesn't mention it)
- Severity: Critical (breaks core functionality) / High (wrong behavior) / Medium (incomplete) / Low (cosmetic)
-
Report:
Output Format
Spec vs Code Audit
Spec: [document name/path] Implementation: [code path(s)] Gaps Found: X (Y critical, Z high)
| GAP ID | Type | Severity | Spec Says | Code Does |
|---|---|---|---|---|
| GAP-AUTH-001 | Missing | Critical | "Tokens expire after 24h" | No expiration logic found |
Top 3 Risks
- [Most dangerous gap]
Recommended Fix Order
- [Fix critical gaps first]
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 · 59 lines · 34 tokens per session scan A 6fe659ea613b
vibe-spec-vs-code-audit is a skill published in the GitHub repository mracal/vibe-engineering (3 stars, last pushed 7d ago), licensed MIT. It adds 34 tokens to every session and 485 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to vibe-spec-vs-code-audit, differing in 0 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.
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.
lua-client-server-contract-audit
Use when normalized Lua client/server RPC contract copies or generated protocol tables disagree on opcode, request-response fields, types, ordering, or source authority.
mmorpg-packet-protocol-review
Use when a C++ server and Unity client protocol manifest or wire compatibility review covers packet version negotiation, numeric opcode registry, byte layout order, direction, and request-response pairing.
codebase-sync
Convention discovery and rule generation from codebase analysis. Scans project structure, builds search indexes, identifies patterns, and generates enforceable rules.
code-review-pipeline
Multi-dimensional code review across correctness, security, performance, and maintainability with confidence-gated reporting and remediation loops.