AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Validate

skill-bugroger-beastmode-validate · by BugRoger

Quality gate — testing, linting, validating. Use after implement. Runs tests and checks quality gates.

No reviews yet
0 installs
37 views
0.0% view→install

Install

$ agentstack add skill-bugroger-beastmode-validate

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-bugroger-beastmode-validate)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
5mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Validate? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

/validate

Verify code changes meet quality standards before release.

No release without passing validation.

Guiding Principles

  • All features must complete implementation before validation begins
  • Fix failures before reporting — attempt repairs, don't just stop at first error
  • Gates are pass/fail — no partial credit, no "close enough"
  • Validate the artifact, not the process — results matter, not how we got there

Phase 0: Pre-Execute

1. Check Feature Completion

Scan for implementation artifacts to verify all features have been implemented:

ls .beastmode/artifacts/implement/*-$epic-*.md 2>/dev/null

Cross-reference against the feature plan files to determine completion status.

Print status:

Feature Completion Check
────────────────────────
✓ feature-1 — completed
✓ feature-2 — completed
✗ feature-3 — pending

Result: BLOCKED — 1 feature still pending

If any features are NOT completed:

  • Print which features are pending
  • STOP — do not proceed to test execution
  • Suggest: "Run /beastmode:implement - to complete remaining features."

If all completed: proceed to next step.

2. Identify Test Strategy

From context, determine:

  • Test command (e.g., npm test, pytest)
  • Lint command (if configured)
  • Type check command (if configured)
  • Custom gates from design acceptance criteria

Phase 1: Execute

1. Run Tests

Capture output and exit code.

2. Run Lint (if configured)

3. Run Type Check (if configured)

4. Run Custom Gates

Execute any custom gates defined in .beastmode/context/VALIDATE.md.

Phase 2: Validate

1. Analyze Results

Check each gate:

  • Tests: PASS/FAIL
  • Lint: PASS/FAIL/SKIP
  • Types: PASS/FAIL/SKIP
  • Custom: PASS/FAIL/SKIP

2. Determine Overall Status

  • All required gates pass → PASS
  • Any required gate fails → FAIL

2b. Identify Failing Features

If any test gate fails, identify which features are responsible:

  1. Parse test output for feature-scoped test names (e.g., *.integration.test.ts, tagged with @)
  2. Map failures to feature slugs using naming conventions
  3. Record per-feature pass/fail results

If feature-level identification is not possible (tests are not feature-scoped), fall back to blanket failure.

3. Generate Report

# Validation Report

## Status: {PASS|FAIL}

### Tests
{output}

### Lint
{output or "Skipped"}

### Types
{output or "Skipped"}

### Custom Gates
{output or "None configured"}

Phase 3: Checkpoint

1. Save Report

Save to .beastmode/artifacts/validate/YYYY-MM-DD-.md where `` is the epic name.

The validation report must begin with YAML frontmatter:

---
phase: validate
epic-id: 
epic-slug: 
status: passed
failed-features: feat-a,feat-b
---

Set status to passed or failed matching the validation result.

  • failed-features is a comma-separated list of feature slugs that failed validation
  • Only present when status: failed and specific features can be identified
  • When absent on failure, the pipeline falls back to blanket regression (all features reset)

2. Commit and Handoff

If FAIL:

Validation failed.
Failing features: 
Re-dispatch count will increment for each failing feature (max 2 per feature).
The pipeline will automatically re-implement failing features.

STOP — do not proceed to commit.

If PASS:

Commit all work to the feature branch:

git add -A
git commit -m "validate(): checkpoint"

Print:

Next: beastmode release 

STOP. No additional output.

Constraints

  • No release without passing validation
  • Do not proceed to commit if validation fails
  • Do not proceed past Pre-Execute if features are incomplete

Reference

Quality Gates

Why Gates Matter

Quality gates prevent broken code from reaching release. Each gate is a checkpoint that must pass.

Default Gates

  1. Tests (required) - All tests must pass
  2. Lint (optional) - Code style compliance
  3. Types (optional) - Type checking passes

Custom Gates

Add custom gates in .beastmode/context/VALIDATE.md:

## Custom Gates

- [ ] Performance benchmarks pass
- [ ] Security scan clean
- [ ] Coverage > 80%

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.