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/templates/lanes.tsv

View on GitHub
# lanes.tsv — one line per lane: <lane>TAB<provider>TAB<model id>TAB<command>. Lines starting with # are ignored.
# {P} = prompt file, {T} = temp path, {APP} = app name. The command prints the report on stdout.
# Provider = the codexbar key from models.md (pick it with pick-provider.py). Cursor lanes: wrap in hb.sh.
sol	codex	gpt-6.2-sol	codex exec --skip-git-repo-check -s read-only -o {T}.out -m gpt-6.2-sol -c model_reasoning_effort="high" "$(cat {P})" < /dev/null > {T}.tr 2>&1; cat {T}.out
astra	codex	gpt-6.2-astra	codex exec --skip-git-repo-check -s read-only -o {T}.out -m gpt-6.2-astra -c model_reasoning_effort="high" "$(cat {P})" < /dev/null > {T}.tr 2>&1; cat {T}.out
opus	claude	claude-opus-5-5	claude -p --strict-mcp-config --tools Read,Grep,Glob --output-format json --effort high --model claude-opus-5-5 "$(cat {P})" > {T}.json; python3 ~/.claude/skills/sliced-review/references/templates/claude_extract.py {T}.json
grok-cur	cursor	cursor-grok-4.6-high	bash ~/.claude/skills/sliced-review/references/templates/hb.sh $RUNNERS_DIR/cursor/cursor-run.sh --model cursor-grok-4.6-high "$(cat {P})" < /dev/null
grok-xai	xai	grok-4.6	$RUNNERS_DIR/xai/xai-run.sh --grok46 "$(cat {P})" < /dev/null
deepseek-oc	opencodego	deepseek-v4.1-flash	$RUNNERS_DIR/pi/pi-run.sh --deepseek "$(cat {P})" < /dev/null
deepseek-cline	cline	deepseek-v4.1-flash	$RUNNERS_DIR/cline/cline-run.sh --thinking high --deepseek "$(cat {P})" < /dev/null
glmflash-oc	opencodego	glm-5.3-flash	$RUNNERS_DIR/pi/pi-run.sh --glm "$(cat {P})" < /dev/null
glmflash-cline	cline	glm-5.3-flash	$RUNNERS_DIR/cline/cline-run.sh --thinking high --glm-flash "$(cat {P})" < /dev/null
mimo-oc	opencodego	mimo-v2.6-flash	$RUNNERS_DIR/pi/pi-run.sh --mimo-flash "$(cat {P})" < /dev/null
mimo-cmd	cmd	mimo-v2.6-flash	$RUNNERS_DIR/cmd/cmd-run.sh --model xiaomi/mimo-v2.6-flash "$(cat {P})" < /dev/null
mimo-cline	cline	mimo-v2.6-flash	$RUNNERS_DIR/cline/cline-run.sh --thinking high --mimo-flash "$(cat {P})" < /dev/null
qwenflash-oc	opencodego	qwen3.8-flash	$RUNNERS_DIR/pi/pi-run.sh --qwen-flash "$(cat {P})" < /dev/null
qwenflash-cmd	cmd	qwen3.8-flash	$RUNNERS_DIR/cmd/cmd-run.sh --model qwen/qwen3.8-flash "$(cat {P})" < /dev/null
mmflash-oc	opencodego	minimax-m3.1-flash	$RUNNERS_DIR/opencode/oc-run.sh --model opencode-go/minimax-m3.1-flash "$(cat {P})" < /dev/null
crouton	orfree	stealth/crouton-alpha	~/work/sr-kits/crouton-route.sh "$(cat {P})" < /dev/null
pulse	ocpulse	pulse-alpha-free	$RUNNERS_DIR/opencode/oc-run.sh --model opencode/pulse-alpha-free "$(cat {P})" < /dev/null
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: 196kUpdated Claude CodeCodexVerifiedInstall