sniper-check
starsforks
How to install sniper-check?
fusengine/agents/sniper-check
$npx -y skills add fusengine/agents --skill sniper-checkUse when validating code quality after modifications. Runs sniper agent in isolated forked context for clean, fast validation.
SKILL.md
| 1 | **Target:** $ARGUMENTS |
| 2 | |
| 3 | # Sniper Check |
| 4 | |
| 5 | ## Overview |
| 6 | |
| 7 | Quick code quality validation using the sniper agent in an isolated forked context. Executes the full 6-phase workflow without polluting the main conversation context. |
| 8 | |
| 9 | | Feature | Detail | |
| 10 | |---------|--------| |
| 11 | | **Context** | Forked (isolated sub-agent) | |
| 12 | | **Agent** | sniper (Sonnet) | |
| 13 | | **Phases** | 6-phase code-quality workflow | |
| 14 | | **Result** | Only final report returns to parent | |
| 15 | |
| 16 | --- |
| 17 | |
| 18 | ## When to Use |
| 19 | |
| 20 | | Scenario | Use | |
| 21 | |----------|-----| |
| 22 | | After code modifications | `/sniper-check src/` | |
| 23 | | Validate specific file | `/sniper-check path/to/file.ts` | |
| 24 | | Full project check | `/sniper-check .` | |
| 25 | | After refactoring | `/sniper-check src/components/` | |
| 26 | |
| 27 | --- |
| 28 | |
| 29 | ## Workflow |
| 30 | |
| 31 | Execute the mandatory 6-phase `code-quality` workflow: |
| 32 | |
| 33 | 1. **PHASE 1+2 (PARALLEL)**: Launch both in parallel: |
| 34 | - `explore-codebase` (Haiku) → Architecture discovery |
| 35 | - `research-expert` (Sonnet) → Documentation verification |
| 36 | 2. **PHASE 3**: Grep all usages → Impact analysis |
| 37 | 3. **PHASE 4**: Run linters → Detect errors |
| 38 | 4. **PHASE 5**: Apply corrections → Minimal changes |
| 39 | 5. **PHASE 6**: Re-run linters → Zero errors |
| 40 | |
| 41 | **CRITICAL**: Phases 1+2 must run in PARALLEL (two Task calls in one message). |
| 42 | |
| 43 | --- |
| 44 | |
| 45 | ## Critical Rules |
| 46 | |
| 47 | | Rule | Reason | |
| 48 | |------|--------| |
| 49 | | Never skip phases 1+2 | Documentation-backed fixes only | |
| 50 | | Always run phases in order | Dependencies between phases | |
| 51 | | Zero linter errors | Non-negotiable exit criteria | |
| 52 | | Minimal changes only | Smallest fix necessary | |
| 53 | |
| 54 | --- |
| 55 | |
| 56 | ## Report Format |
| 57 | |
| 58 | Return a validation report with: |
| 59 | |
| 60 | - Architecture summary (from explore-codebase) |
| 61 | - Documentation references (from research-expert) |
| 62 | - Impact analysis table (usages, risk level) |
| 63 | - Errors fixed (critical, high, medium, low) |
| 64 | - SOLID compliance status |
| 65 | - Final linter status (must be ZERO errors) |
People who liked this also viewed
6 picksType
- tddSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- test-driven-developmentUse when implementing any feature or bugfix, before writing implementation codeSkillsJul 2026
- qaSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- verification-before-completionUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidenceSkillsJul 2026
- webapp-testingToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser lSkillsJul 2026
- playwright-best-practicesUse when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, teSkillsJul 2026
