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/ORDER.md

View on GitHub
<!-- TEMPLATE. Replace every <blank>. Delete this comment. -->

# <MODEL> sliced review — run order

RULE: one slice at a time. Never two at once.
<If there is a pre-flight guard, say its threshold. If there is NOT one, say so here in
 plain words — "there is no pre-flight quota check on this backend; a 429 is the only
 signal" — so the next reader does not assume protection that does not exist.>

    ./docs/<model>-review/run-slice.sh <first-slice-name>

Cost per slice is UNKNOWN until the first one runs. `ledger.tsv` records the cost of every
run, so after slice 1 the estimate below is replaced by a measurement.

## Tier 1 — <the worst-outcome class, named>
 1. <slice-name>        <lines>   <one line on what it covers>
 ...

## Tier 2 — credentials and anything that writes to someone else's system
 ...

## Tier 3 — concurrency, transactions, schema, silent wrong data
 ...

## Tier 4 — UI, performance, tests, documentation drift
 ...

## Why this order

<Two or three sentences. Name the worst outcome this project can produce and say that
 Tier 1 is where it lives. Then state explicitly what is still covered if the budget runs
 out after Tier 2 — that guarantee is the entire reason the order exists.>

## Estimate

<Slices remaining> slices at <estimate> each ≈ <total>. Budget remaining: <amount>.
[hypothesis] until slice 1 lands in `ledger.tsv`.
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