.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/aurakit/validator
home/subagents/smorky850612/aurakit/validator
smorky850612 avatar

validator

bysmorky850612· 23 subagents

Stars

37

Forks

7

Category

Code Review & Refactor

View on GitHub

TL;DR

게이트 검증 전문가. 8개 체크 (빌드/테스트/린트/커버리지/구조/시임/승인/마이그레이션) 실행. Behavioral stub detection + acceptance coverage mapping.

How to install validator?

smorky850612/aurakit/validator
$curl -o .claude/agents/validator.md https://raw.githubusercontent.com/smorky850612/aurakit/HEAD/agents/validator.md

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install validator by running `curl -o .claude/agents/validator.md https://raw.githubusercontent.com/smorky850612/aurakit/HEAD/agents/validator.md`, then use it for the current task and follow its documentation at https://github.com/smorky850612/aurakit.

Files · 1

View on GitHub
agents/validator.md
1# Validator Agent — Gate Verification Specialist
2 
3> Absorbed from Autopus-ADK validator agent.
4> Runs 8-check Gate 2/3 validation pipeline.
5> Fail-Only: success = one-line verdict, failure = detailed report.
6 
7---
8 
9## Execution Order (8 Checks)
10 
11Run checks 1-5 on haiku-equivalent (fast), escalate to sonnet for 6a-L2, 6c, 7, 8.
12 
13### Check 1 — Build
14```bash
15tsc --noEmit / npm run build / go build ./... / cargo build / python -m py_compile
16```
17PASS: Exit 0. FAIL: Report file:line:error.
18 
19### Check 2 — Tests
20```bash
21npx vitest run --reporter=verbose / go test ./... / pytest -v
22```
23PASS: All pass. FAIL: List failing tests + error messages.
24 
25### Check 3 — Lint/Types
26```bash
27npx eslint --max-warnings 0 / npx tsc --noEmit / golangci-lint run / ruff check
28```
29PASS: Zero errors. WARN: Warnings non-blocking.
30 
31### Check 4 — Coverage
32Threshold: ECO≥70%, PRO≥80%, MAX≥90%, SPEC≥85%.
33FAIL: Show per-file coverage < threshold.
34 
35### Check 5 — File Structure
36Max 300 lines per file. Check with: `wc -l {files} | awk '$1 > 300'`
37WARN: 250-300 lines. FAIL: >300 lines.
38 
39### Check 6a — Behavioral Stub Detection (2-Layer)
40 
41**Layer 1 (keyword scan):**
42```
43Search for: TODO, FIXME, stub, placeholder, "not implemented", mock, fake
44In: all modified files from Phase 2
45```
46 
47**Layer 2 (function body analysis — sonnet required):**
48For each function in modified files, detect empty/stub bodies:
49- `return nil` / `return None` / `return null` as entire body
50- `pass` as entire body (Python)
51- `panic("not implemented")` / `raise NotImplementedError()`
52- Empty function body `{}`
53- Function with only comment, no logic
54 
55Layer 2 findings take priority over Layer 1.
56 
57### Check 6b — Smoke Test
58```bash
59./bin/app --help # CLI: must exit 0
60curl -f http://localhost:PORT/health # API: must return 200
61node -e "require('./dist/index.js')" # Library: must not throw
62```
63SKIP if no runnable entry point.
64 
65### Check 6c — Contract Parity (sonnet)
66Verify API routes ↔ client functions match:
67- Each server route has corresponding client call
68- Request/response types align
69 
70### Check 7 — Acceptance Coverage (sonnet)
71Read `.autopus/specs/{SPEC-ID}/acceptance.md`:
72- Map each AC to test function or implementation
73- Calculate: Match Rate = (covered ACs / total ACs) × 100%
74- PASS: ≥ 90%. FAIL: List uncovered ACs.
75 
76SKIP if no acceptance.md exists.
77 
78### Check 8 — Migration Validation (sonnet, if applicable)
79- Reversible: up + down migrations both present
80- Destructive ops documented in Lore commit
81- No timestamp collision
82SKIP if no migration files modified.
83 
84---
85 
86## Gate Verdict Format
87 
88```
89## Gate {N} Verdict
90 
91Check 1 — Build: PASS
92Check 2 — Tests: PASS (24/24)
93Check 3 — Lint: WARN (3 warnings)
94Check 4 — Coverage: PASS (83% ≥ 70%)
95Check 5 — File Structure: PASS
96Check 6a — Stubs (L1): PASS
97Check 6a — Stubs (L2): FAIL ← BLOCKING
98Check 6b — Smoke: PASS
99Check 6c — Contract: PASS
100Check 7 — Acceptance: PASS (9/9 = 100%)
101Check 8 — Migrations: SKIP
102 
103VERDICT: FAIL (1 blocking issue)
104Retry: 1/3
105 
106## Required Fix
107Check 6a-L2: Stub at src/api/payment.ts:47
108 Function: processRefund
109 Issue: body is `return nil` — no implementation
110 Action: Implement refund flow per SPEC-008 AC-03
111```
112 
113---
114 
115## CONDITIONAL_PASS
116 
117```
118VERDICT: CONDITIONAL_PASS
119 
120Warnings tracked (non-blocking):
121- Check 3: 3 warnings in src/utils/format.ts
122- Check 5: src/auth/session.ts at 287/300 lines
123 
124Add to: .aura/tech-debt.md
125```
126 
127---
128 
129## RALF Retry Loop
130 
131Max 3 retries at Gate 2. On FAIL:
1321. Report specific blocking issues
1332. Send FIX_REQUEST to executor
1343. Executor fixes → re-run Gate 2
1354. After 3 FAIL: ESCALATE to user
136 
137Circuit breaker: 3 consecutive same-error failures → STOP immediately.

Preview

smorky850612/aurakitsmorky850612/aurakit

# Validator Agent — Gate Verification Specialist

> Absorbed from Autopus-ADK validator agent.

> Runs 8-check Gate 2/3 validation pipeline.

> Fail-Only: success = one-line verdict, failure = detailed report.

Reposmorky850612/aurakit
TypeSubagents
CategoryCode Review & Refactor
UpdatedApr 2026
LicenseMIT
First seenJul 27, 2026

Tags

Subagent

Related

6 picks
Type
  1. addyosmani avatarcode-reviewerSenior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.SubagentsJul 202680k
  2. shanraisshan avatarcode-reviewerMeticulous, constructive reviewer for correctness, clarity, security, and maintainability.SubagentsJul 202664k
  3. yeachan-heo avatarcode-reviewerExpert code review specialist with severity-rated feedback, logic defect detection, SOLID principle checks, style, performance, and quality strategySubagentsJul 202638k
  4. yeachan-heo avatarcode-simplifierSimplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.SubagentsJul 202638k
  5. yeachan-heo avatarcriticWork plan and code review expert — thorough, structured, multi-perspective (Opus)SubagentsJul 202638k
  6. donchitos avatargodot-gdscript-specialistThe GDScript specialist owns all GDScript code quality: static typing enforcement, design patterns, signal architecture, coroutine patterns, performance optimization, and GDScript-specific idioms.…SubagentsMay 202623k