Skip to content

Mariomarquezt/multi-flow-skills / skills/sliced-review

sliced-review

Flagged

Review a whole codebase with several models by cutting it into small file-listed slices ordered by blast radius, then triage every finding with three judges, and optionally fix. Use when the user asks to review or audit a whole project or repo with other models, wants a second opinion on a codebase, wants a review split into slices or tiers, has a whole-repo review that died on credits, or wants a check before a launch or handover. Modes (`3`, `5`, `8`, `fast`, `fix …`, `fix fast …`, `fix only`, `report`, `no wrap`) are in the body. Not for a plan before code exists (/grill-me-codex, /codex-review) or a single diff, branch or PR (/code-review).

references/prices.json

View on GitHub
{
  "_about": "USD per 1M tokens. Read by usage.py `price`. Lookup order: this file -> the runner's own table ($RUNNERS_DIR/devin/prices.json, $RUNNERS_DIR/scripts/claude-prices.json) -> OpenRouter public list (cached 24h). Missing cache_read = 0.1 x input, missing cache_write = 1.25 x input. A free route is priced as its paid twin: the point is the API-equivalent cost.",
  "_source": "the user 2026-10-15 (Claude 5.5 family, Opus 5, Fable 5.1).",
  "models": {
    "claude-haiku-5-5": {
      "in": 0.1,
      "out": 0.5
    },
    "claude-sonnet-5-5": {
      "in": 2.0,
      "out": 10.0
    },
    "claude-opus-5-5": {
      "in": 4.0,
      "out": 20.0
    },
    "claude-opus-5": {
      "in": 5.0,
      "out": 25.0
    },
    "claude-fable-5-1": {
      "in": 10.0,
      "out": 50.0
    },
    "grok-4.7": {
      "in": 2.0,
      "out": 6.0,
      "cache_read": 0.5,
      "from": "openrouter:x-ai/grok-4.7",
      "saved": "2026-10-25"
    },
    "gpt-6.1-sol": {
      "in": 2.0,
      "out": 10.0,
      "cache_read": 0.1,
      "cache_write": 2.5,
      "from": "openrouter:openai/gpt-6.1-sol",
      "saved": "2026-10-25"
    },
    "grok-4.6": {
      "in": 2.0,
      "out": 6.0,
      "cache_read": 0.5,
      "from": "openrouter:x-ai/grok-4.6",
      "saved": "2026-10-25"
    },
    "mimo-v2.6-flash": {
      "in": 0.14,
      "out": 0.28,
      "cache_read": 0.0028,
      "from": "openrouter:xiaomi/mimo-v2.6-flash",
      "saved": "2026-10-31"
    },
    "deepseek-v4-pro": {
      "in": 1.6,
      "out": 3.2,
      "cache_read": 0.135,
      "from": "openrouter:deepseek/deepseek-v4-pro",
      "saved": "2026-10-31"
    }
  },
  "_aliases_about": "Ids that do not match an OpenRouter id by name. Key = id as the runner prints it (provider prefix, effort suffix and -free are stripped first; dots and dashes are treated alike). 'id@provider' applies only to that provider (Cesego labels DeepSeek V4.1 Flash as deepseek-v4-flash). Value = the id to price it as.",
  "aliases": {
    "deepseek-v4-flash-max": "deepseek-v4.1-flash",
    "deepseek-v4-flash@cesego": "deepseek-v4.1-flash",
    "glm5.3-flash-max": "glm-5.3-flash",
    "glm5.3-flash": "glm-5.3-flash",
    "qwen3.8-flash-max": "qwen3.8-flash"
  }
}
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