Filip-Podstavec/claude-leverage

Filip-Podstavec/claude-leverage

Agent

Part of claude-leverage

USE WHEN a test intermittently fails on unchanged code. Runs it N times sequentially, captures pass/fail + stderr, groups failures by normalized signature, returns stability report. Read-only — never modifies code or installs deps. For statistical signal across runs, not one-shot diagnosis.

Filip-Podstavec/claude-leverage

Agent

Part of claude-leverage

USE WHEN /repo-doctor --semantic runs. Judges whether discoverability artifacts (AGENTS.md, README, ADRs, GLOSSARY, per-dir AGENTS.md) are truthful, actionable, and mutually consistent — the quality layer deterministic checks cannot see. Read-only. Returns per-dimension JSON verdicts with file:line evidence. Advisory…

Filip-Podstavec/claude-leverage

Agent

Part of claude-leverage

USE BEFORE committing security-sensitive changes (auth, crypto, routes, templates, secrets). Audits current diff for OWASP-Top-10 patterns + deps typosquatting. Read-only. Returns Critical / Important / Nice schema with file:line. Model review — not a Semgrep/CodeQL replacement.

Filip-Podstavec/claude-leverage

Agent

Part of claude-leverage

Code review on Sonnet — security/correctness/maintainability findings, read-only. Use before commits or PRs.

Filip-Podstavec/claude-leverage

Agent

Part of claude-leverage

Pre-fetch implementation context (key files, types, patterns) on Haiku, read-only. Use before multi-file features.

Filip-Podstavec/claude-leverage

Agent

Part of claude-leverage

Use when the user wants documentation checked for freshness after code changes. Reads diff and existing docs, proposes specific updates to README, CHANGELOG, docstrings, and other documentation files. Read-only - returns prose-direction suggestions, never modifies files.

Filip-Podstavec/claude-leverage

Agent

Part of claude-leverage

Review pre-extracted code snippets passed in the prompt — never re-reads files, never runs git diff. Hard 500-token output cap. Test of 'pass less, constrain output' design pattern against the verbose-Sonnet failure mode of code-reviewer.

Filip-Podstavec/claude-leverage

Agent

Part of claude-leverage

Trivial commits on Haiku — 1 file, <20 lines, no sensitive paths. Speed-optimized, separate rate pool.

Filip-Podstavec/claude-leverage

Agent

Part of claude-leverage

Stage/commit/push non-trivial changes on Sonnet using Conventional Commits. Reads diff, matches repo style.

Filip-Podstavec/claude-leverage

Agent

Part of claude-leverage

Find all call sites of a symbol with structured output on Haiku — for 'what breaks if I change X?' questions. Returns file:line:snippet triples plus tests + external risk. Bounded to prevent Opus from reading every hit inline.

Filip-Podstavec/claude-leverage

Agent

Part of claude-leverage

Run a shell command and return structured digest of its output on Haiku — for commands that produce >2k tokens of output (pip install, docker build, npm audit, large test runs, etc.). Saves Opus from reading verbose logs.

Filip-Podstavec/claude-leverage

Agent

Part of claude-leverage

Use for codebase discovery. Use to find where something is defined or imported. Use to identify patterns used across files. Use proactively before making changes that might affect multiple files. Read-only - returns structured findings report. Does not propose changes, suggest refactoring, or write code.

Filip-Podstavec/claude-leverage

Agent

Part of claude-leverage

Use to understand how something works in the codebase before making changes. Use when asked to explain a pattern or flow that spans multiple files. Use proactively when planning non-trivial changes that depend on existing patterns. Read-only - returns structured synthesis. Does not propose changes, suggest…

Filip-Podstavec/claude-leverage

Agent

Part of claude-leverage

Run tests on Sonnet — auto-detects framework, returns structured failure analysis, read-only.