Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/whitequeen306/code-cortex-loop/correctness-reviewnpx skills add whitequeen306/code-cortex-loop --skill correctness-reviewgit clone --depth 1 https://github.com/whitequeen306/code-cortex-loopWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00040 | $0.01692 |
| Opus 5 | $0.00020 | $0.00846 |
| Sonnet 5 | $0.00008 | $0.00338 |
| Haiku 4.5 | $0.00004 | $0.00169 |
Grade A, and why
correctness-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Correctness & Architecture Review (Deep)
Depth skill for pass 1 (review). Pair with cortexloop-expert-core and edge-case-and-state-analysis.
Go deep on correctness and architecture. This is not a shallow lint pass — trace logic, invariants, and structural fit. Other domains (security exploits, test gaps, perf bottlenecks, dead code) get defer notes, not scored findings in this pass.
When to go deep
- New or changed control flow, state, APIs, data transforms
- Bug fixes (verify fix and whether the root cause class exists elsewhere)
- Refactors that move logic across modules
- Concurrent, async, or event-driven paths
- Domain rules encoded in multiple places
Correctness — deep checklist
Requirements & behavior
- Does observable behavior match the stated task/spec?
- Are success and failure outcomes both defined and reachable?
- Do defaults match domain expectations (not just "non-null")?
- Are implicit assumptions documented in code or violated silently?
Logic & arithmetic
- Off-by-one, wrong comparator, inverted boolean, wrong operator precedence
- Integer overflow/truncation, float comparison, unit mismatch
- Wrong aggregation (sum vs count, average on empty set)
- Timezone/date boundary errors, DST, leap seconds where relevant
State & concurrency
- Read-modify-write races, check-then-act gaps
- Stale reads after async gaps; cache not invalidated when state changes
- Double application of events (idempotency missing on logic side)
- Shared mutable state across requests/workers without synchronization
- Lifecycle bugs: subscribe without unsubscribe, init order, teardown skipped
Edge inputs (logic angle)
- null, undefined, empty string, empty array, empty map
- Zero, negative, MAX_INT, empty pagination cursor
- Duplicate keys, partial records, optional fields missing
- Malformed but parseable input that reaches business logic
Input sanitization / injection → defer
security. Missing test for an edge → defertests.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 217 lines · 40 tokens per session scan A e927b3abc5a0
correctness-review is a skill published in the GitHub repository whitequeen306/code-cortex-loop (15 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,692 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…