Skip to content

smorky850612/Aurakit / skills/aura

All-in-one fullstack dev engine. /aura: 46 modes (build/fix/clean/deploy/review/spec/lore/ax/experiment/payment/debug/qa/orchestrate/escalate+), 6-layer security with 32 hooks, tiered models (ZERO/ECO/PRO/MAX), 8 languages, 16 specialized agents, SPEC/EARS/TRUST5/XLOOP/RALF/Autopus absorbed. ~55% token savings.

FileKindSize
SKILL.mdskill md29.2 KB
resources/agent-security.mdmarkdown4.2 KB
resources/agent-spawning.mdmarkdown5.9 KB
resources/agent-team.mdmarkdown5.7 KB
resources/archive-pipeline.mdmarkdown3.5 KB
resources/autopus-agent-teams.mdmarkdown6.8 KB
resources/autopus-ax-annotation.mdmarkdown6.1 KB
resources/autopus-executor-profiles.mdmarkdown9.9 KB
resources/autopus-experiment-loop.mdmarkdown5.9 KB
resources/autopus-lore-commit.mdmarkdown6.0 KB
resources/autopus-pipeline-v2.mdmarkdown8.5 KB
resources/autopus-spec-system.mdmarkdown4.8 KB
resources/autopus-validator-gates.mdmarkdown7.0 KB
resources/autopus-worktree-isolation.mdmarkdown4.6 KB
resources/baas-pipeline.mdmarkdown3.8 KB
resources/batch-pipeline.mdmarkdown4.9 KB
resources/brainstorming.mdmarkdown4.7 KB
resources/branch-finishing.mdmarkdown4.7 KB
resources/build-pipeline.mdmarkdown12.0 KB
resources/build-resolvers-cpp.mdmarkdown10.0 KB
resources/build-resolvers-go.mdmarkdown1.2 KB
resources/build-resolvers-java.mdmarkdown9.1 KB
resources/build-resolvers-kotlin.mdmarkdown8.7 KB
resources/build-resolvers-python.mdmarkdown9.0 KB
resources/build-resolvers-rust.mdmarkdown1.2 KB
resources/build-resolvers-swift.mdmarkdown11.9 KB
resources/build-resolvers.mdmarkdown1.6 KB
resources/business-skills.mdmarkdown7.0 KB
resources/cache-engineering.mdmarkdown6.6 KB
resources/clean-pipeline.mdmarkdown6.5 KB
resources/common-protocol.mdmarkdown7.4 KB
resources/config-schema.mdmarkdown3.0 KB
resources/cross-harness.mdmarkdown16.6 KB
resources/deploy-enterprise.mdmarkdown9.0 KB
resources/deploy-pipeline.mdmarkdown6.9 KB
resources/design-pipeline.mdmarkdown3.2 KB
resources/desktop-pipeline.mdmarkdown3.5 KB
resources/discovery-protocol.mdmarkdown3.3 KB
resources/e2e-pipeline.mdmarkdown7.7 KB
resources/explain-pipeline.mdmarkdown972 B
resources/fix-pipeline.mdmarkdown5.6 KB
resources/framework-patterns.mdmarkdown8.3 KB
resources/gap-check.mdmarkdown3.4 KB
resources/install-guide.mdmarkdown3.4 KB
resources/instinct-system.mdmarkdown6.8 KB
resources/iterate-pipeline.mdmarkdown2.5 KB
resources/language-reviewers.mdmarkdown18.5 KB
resources/loop-pipeline.mdmarkdown3.5 KB
resources/mcp-configs.mdmarkdown4.7 KB
resources/migrate-pipeline.mdmarkdown1.5 KB
resources/mobile-pipeline.mdmarkdown3.5 KB
resources/mode-reference.mdmarkdown6.1 KB
resources/model-routing.mdmarkdown9.1 KB
resources/orchestration-patterns.mdmarkdown5.9 KB
resources/payment-lemonsqueezy.mdmarkdown5.6 KB
resources/payment-pipeline.mdmarkdown10.6 KB
resources/payment-polar.mdmarkdown3.6 KB
resources/payment-steppay.mdmarkdown4.8 KB
resources/payment-stripe.mdmarkdown6.7 KB
resources/payment-toss.mdmarkdown7.2 KB
resources/pipeline-guide.mdmarkdown6.1 KB
resources/plan-pipeline.mdmarkdown2.4 KB
resources/pm-pipeline.mdmarkdown4.5 KB
resources/qa-pipeline.mdmarkdown8.8 KB
resources/report-pipeline.mdmarkdown3.0 KB
resources/review-pipeline.mdmarkdown8.0 KB
resources/rollback-pipeline.mdmarkdown1.3 KB
resources/security-rules.mdmarkdown17.5 KB
resources/snippets-guide.mdmarkdown4.6 KB
resources/status-dashboard.mdmarkdown5.3 KB
resources/style-guide.mdmarkdown2.7 KB
resources/systematic-debugging.mdmarkdown5.7 KB
resources/tdd-pipeline.mdmarkdown4.4 KB

resources/autopus-validator-gates.md

View on GitHub
# Autopus Validator Gates

> Absorbed from Autopus-ADK. Enhanced Gate 2 validation with 8 checks,
> behavioral stub detection, acceptance coverage, and seam verification.

---

## Overview

The validator runs at Gate 2 (after Phase 2 implementation) and Gate 3 (after Phase 3 testing).
It performs 8 sequential checks, each with PASS/FAIL/WARN output.

**Max retries**: 3 at Gate 2 (RALF loop). Gate verdict triggers builder to fix.

---

## Check 1 — Build Verification

```bash
# Detect language and run build
npm run build / tsc --noEmit   # TypeScript
go build ./...                  # Go
cargo build                     # Rust
python -m py_compile src/*.py   # Python
mvn compile                     # Java
```

PASS: Zero errors.
FAIL: Any compilation error → report file:line:error.

---

## Check 2 — Test Execution

Run full test suite including Phase 1.5 scaffold tests.

```bash
npm test / npx vitest run / npx jest --ci
go test ./...
pytest -x
cargo test
```

PASS: All tests pass.
FAIL: Report failing test names + error messages.

---

## Check 3 — Lint / Type Check

```bash
npx eslint src/ --max-warnings 0    # TypeScript
npx tsc --noEmit                     # TypeScript types
golangci-lint run                    # Go
ruff check src/                      # Python
cargo clippy -- -D warnings         # Rust
```

PASS: Zero errors, warnings within threshold.
WARN: Warnings present (non-blocking unless `--strict`).
FAIL: Errors present.

---

## Check 4 — Coverage Threshold

| Tier | Threshold |
|------|---------|
| ECO | ≥ 70% |
| PRO | ≥ 80% |
| MAX | ≥ 90% |
| SPEC mode | ≥ 85% |

```bash
npx vitest run --coverage --reporter=json
go test -coverprofile=coverage.out ./... && go tool cover -func=coverage.out
pytest --cov=src --cov-report=json
```

PASS: Coverage ≥ threshold.
FAIL: Coverage < threshold → report which files are below.

---

## Check 5 — File Structure

Verify no file exceeds 300 lines (stricter than AuraKit's 250 for generated code).

```bash
# Find files over limit
find src -name "*.ts" -o -name "*.go" -o -name "*.py" | \
  xargs wc -l | sort -rn | awk '$1 > 300 {print $2, $1}'
```

PASS: All files ≤ 300 lines.
WARN: Files between 250-300 lines.
FAIL: Files > 300 lines → list them with line counts.

---

## Check 6 — Seam Verification

Three sub-checks (all must pass):

### 6a — Behavioral Stub Analysis (2-layer)

**Layer 1: Keyword Scan**
```
Search for: TODO, FIXME, stub, placeholder, not implemented, mock, fake
In: all files modified in Phase 2
```

**Layer 2: Function Body Analysis**
For each function in modified files, check for empty/stub bodies:
```
Patterns indicating stubs:
- Function body = single return nil/None/null/undefined
- Function body = single pass/noop statement  
- Function body = panic("not implemented") / raise NotImplementedError
- Function body = empty (just braces {})
- Function body only has comment, no logic
```

Layer 2 requires model escalation (sonnet minimum — haiku misses subtle stubs).

PASS: No stubs detected.
FAIL: List file:function for each stub found.

### 6b — Smoke Test

Verify the primary entry point works:
```bash
# CLI tool
./bin/app --help    # Must exit 0

# HTTP API
curl -s http://localhost:PORT/health | jq .status  # Must return "ok"

# Library
node -e "require('./dist/index.js')"  # Must not throw
```

PASS: Entry point responds without error.
SKIP: If no runnable entry point (library with no binary).

### 6c — Contract Parity

For API changes, verify client and server agree:
- API route defined in server → corresponding client function exists
- Request type in server matches client call signature
- Response type in server matches client parsing

```
Check: src/api/routes.ts endpoints ↔ src/lib/api-client.ts calls
```

PASS: All endpoints have matching client calls.
WARN: New endpoint without client function (acceptable if client update in separate SPEC).

---

## Check 7 — Acceptance Coverage

Read `acceptance.md` from the active SPEC and verify implementation:

```
For each AC in acceptance.md:
  1. Find the Given/When/Then scenario
  2. Search for test function that covers this scenario
  3. OR verify implementation directly handles the behavior
```

Coverage formula:
```
Match Rate = (Covered ACs / Total ACs) × 100%
```

PASS: Match Rate ≥ 90%.
FAIL: Match Rate < 90% → list uncovered ACs with file search suggestions.

Gate reports Match Rate in output:
```
Check 7 — Acceptance Coverage: 8/9 ACs = 89% → FAIL (threshold: 90%)
Uncovered: AC-05 (token refresh on 401 response)
```

Requires model escalation: sonnet minimum (acceptance mapping requires reasoning).

---

## Check 8 — Migration File Validation

Only runs if database migration files were created/modified.

```
Verify:
- Migration is reversible (has both up and down / forward and rollback)
- No destructive operations without explicit confirmation in commit message
- Migration timestamp is unique (no collision with existing migrations)
- Foreign key constraints accounted for in operation order
```

PASS: Migration is valid and reversible.
WARN: Destructive operation present but documented in Lore commit.
FAIL: Irreversible migration without documentation.

---

## Gate Verdict Format

```
## Gate 2 Verdict

Check 1 — Build:             PASS
Check 2 — Tests:             PASS  (24/24)
Check 3 — Lint:              WARN  (3 warnings — non-blocking)
Check 4 — Coverage:          PASS  (83% ≥ 70%)
Check 5 — File Structure:    PASS
Check 6a — Stubs:            FAIL  ← BLOCKING
Check 6b — Smoke Test:       PASS
Check 6c — Contract Parity:  PASS
Check 7 — Acceptance:        PASS  (9/9 = 100%)
Check 8 — Migrations:        SKIP  (no migrations)

VERDICT: FAIL (1 blocking issue)

## Fix Required
Check 6a — Stub at src/api/payment.ts:47
  Function: processRefund
  Body: return nil  ← empty stub detected
  Action: Implement refund logic per SPEC-008 AC-03
```

---

## CONDITIONAL_PASS

When all checks pass except non-blocking warnings:

```
## Gate 2 Verdict

All checks: PASS (with 2 warnings)

VERDICT: CONDITIONAL_PASS

Warnings (tracked, not blocking):
- Check 3: 3 ESLint warnings in src/utils/format.ts
- Check 5: src/auth/session.ts at 287 lines (threshold: 300)

Track in: .aura/tech-debt.md
```

---

## Model Requirements

| Check | Minimum Model | Reason |
|-------|--------------|--------|
| 1-5 | haiku | Mechanical execution |
| 6a Layer 1 | haiku | Keyword search |
| 6a Layer 2 | sonnet | Semantic stub detection |
| 6b | haiku | CLI/HTTP call |
| 6c | sonnet | Interface matching |
| 7 | sonnet | AC mapping reasoning |
| 8 | sonnet | Migration analysis |

Validator runs checks 1-6a-Layer1, 6b on haiku; escalates to sonnet for 6a-Layer2, 6c, 7, 8.

---

## Integration with AuraKit

Activated in:
- `/aura build:` → Gate 2 runs after Phase 2
- `/aura review:` → runs all 8 checks as Worker-V (Validator)
- `/aura spec:validate SPEC-XXX` → runs check 7 only

Configure thresholds in `.aura/config.json`:
```json
{
  "validator": {
    "coverage_threshold": 85,
    "line_limit": 300,
    "acceptance_threshold": 90,
    "strict_stubs": true
  }
}
```
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall