check-correctness

check-correctness is a skill for Claude Code, Codex from leifericf/agentic-sdk. It costs 28 tokens per session (871 once invoked), scanned A, original, MIT.

A code-review checklist for finding logic errors in one part of a program. It focuses on arithmetic, boundary inputs, ordering, and concurrent events.

In plain words
What is it for?
It helps reviewer agents inspect loops, indexes, calculations, collections, missing values, transformations, callbacks, messages, and other behavior at the edges of a module.
Why use it?
It catches bugs that ordinary successful-case testing can miss, such as off-by-one errors, empty inputs, invalid values, and unsafe timing between operations.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/leifericf/agentic-sdk/check-correctness
Any agent
npx skills add leifericf/agentic-sdk --skill check-correctness
Clone the repo
git clone --depth 1 https://github.com/leifericf/agentic-sdk

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for check-correctness

README.md
[![agentmods](https://agentmods.dev/badge/skills/leifericf/agentic-sdk/check-correctness.svg)](https://agentmods.dev/skills/leifericf/agentic-sdk/check-correctness)
Your own site
<a href="https://agentmods.dev/skills/leifericf/agentic-sdk/check-correctness"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/check-correctness.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 871 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00028 $0.00871
Opus 5 $0.00014 $0.00436
Sonnet 5 $0.00006 $0.00174
Haiku 4.5 $0.00003 $0.00087

Measured 4d ago against content hash 5dabd1e71d7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

check-correctness 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 4d 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.

skills/check-correctness/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

check-correctness

Role: review the shard for behavior that is simply wrong.

Failure model: the code does not do what the surrounding system needs on some input or interleaving; the bug that ships is the edge the happy path hides.

Look for

  1. Arithmetic and indexing. Off-by-one in a loop bound; signed and unsigned mismatch; integer overflow on an accumulator or a size computation; a count flowing into indexing without a bound check; float precision loss in a long-running accumulator; a division whose divisor can be zero.
  2. nil, null, empty, and boundary inputs. Empty collection, single element, zero, negative, a missing map key, an empty string, an Option or Result unwrapped without the missing case. The happy path is not the test; the boundary is.
  3. Order and composition sensitivity. A transformation chain that produces a different result when applied in a different order; a filter or reduction that mishandles the empty case; a sort that is not stable where the caller depends on stability; a set versus list confusion that drops or duplicates elements.
  4. Concurrency and interleaving. A callback that fires mid-mutation; a message that arrives between a decision and its effect; a shared mutable value read and written without the synchronization the shell owns; a future or task awaited in the wrong order. The pure core avoids this by construction; the shell is where it lives.
  5. Protocol and state machine errors. A case, match, or switch with a missing arm; a state transition that skips an intermediate state the contract requires; an error code outside the documented catalog; a sentinel value stored where the domain expects absence.
  6. Error-path correctness. A recovery path that swallows the failure and returns a wrong success value; an error mapped to the wrong diagnostic; a cleanup path that skips a step the success path runs.
  7. Native edge dispatch. A wrapper that calls the wrong native function, passes arguments in the wrong order, or misreads the return shape. The lifetime and ownership of the handle are check-memory's; the dispatch logic is here.

Read the full file on GitHub · 90 lines

Changes

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.

  1. 4d ago First seen · 90 lines · 28 tokens per session scan A 5dabd1e71d7f

Subscribe to this mod's changes

check-correctness is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 871 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens